1
|
Zhao Y, Li L, Yu X, Han K, Duan J, Liang D, Chai N, Li ZC. SurvGraph: A hybrid-graph attention network for survival prediction using whole slide pathological images in gastric cancer. Neural Netw 2025; 189:107607. [PMID: 40375420 DOI: 10.1016/j.neunet.2025.107607] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2024] [Revised: 04/27/2025] [Accepted: 05/08/2025] [Indexed: 05/18/2025]
Abstract
Whole slide pathological images have shown significant potential for patient prognostication. Graph representation learning provides a robust framework for in-depth analysis of whole-slide images to construct predictive models. In this study, we introduce SurvGraph, an innovative graph-based deep learning network designed for gastric cancer survival prediction using whole slide pathological images. SurvGraph employs a hybrid graph construction approach that integrates multiple feature types, including color, texture, and deep learning features extracted from the pathological images to build node representations. SurvGraph utilizes a multi-head attention graph network, which performs survival prediction based on the graph structure. We evaluate the SurvGraph model on a large dataset of 708 gastric cancer patients from three independent cohorts for overall survival prediction. To assess the impact of various feature sets, we examine their performance when used individually and in combination. With five-fold cross-validation, our results demonstrate that the SurvGraph model achieves an average concordance index (C-index) of 0.706 with a standard deviation (SD) of 0.019. The proposed SurvGraph model has also attained a C-index of 0.708 (SD = 0.040) in the external testing set. In addition to baseline comparisons, we conducted a comprehensive benchmarking study comparing SurvGraph against established graph neural network architectures and multiple instance learning-based deep learning frameworks. The results indicate that the SurvGraph model outperforms the compared prediction models, suggesting its potential as a valuable tool for enhancing gastric cancer prognosis estimation.
Collapse
Affiliation(s)
- Yuanshen Zhao
- Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, PR China
| | - Longsong Li
- Department of Gastroenterology, The First Medical Center of Chinese PLA General Hospital, Beijing, PR China
| | - Xi Yu
- Department of Gastroenterology, Longgang District Central Hospital of Shenzhen, Shenzhen, PR China
| | - Ke Han
- Department of Gastroenterology, The First Medical Center of Chinese PLA General Hospital, Beijing, PR China
| | - Jingxian Duan
- Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, PR China; Pazhou Lab (Huangpu), Guangdong, PR China
| | - Dong Liang
- Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, PR China; The Key Laboratory of Biomedical Imaging Science and System, Chinese Academy of Sciences, State Key Laboratory of Biomedical Imaging Science and System, Shenzhen, PR China
| | - Ningli Chai
- Department of Gastroenterology, The First Medical Center of Chinese PLA General Hospital, Beijing, PR China; Pazhou Lab (Huangpu), Guangdong, PR China.
| | - Zhi-Cheng Li
- Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, PR China; The Key Laboratory of Biomedical Imaging Science and System, Chinese Academy of Sciences, State Key Laboratory of Biomedical Imaging Science and System, Shenzhen, PR China; University of Chinese Academy of Sciences, Beijing, PR China.
| |
Collapse
|
2
|
Su J, Liu Z, Li H, Kang L, Huang K, Wu J, Huang H, Ling F, Yao X, Huang C. Artificial intelligence-based model to predict recurrence after local excision in T1 rectal cancer. EUROPEAN JOURNAL OF SURGICAL ONCOLOGY 2025; 51:109717. [PMID: 40043596 DOI: 10.1016/j.ejso.2025.109717] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2024] [Revised: 01/17/2025] [Accepted: 02/19/2025] [Indexed: 05/26/2025]
Abstract
BACKGROUND According to current guideline, patients with resected specimens showing high-risk features are recommended additional surgery after local excision (LE) of T1 colorectal cancer, despite the low incidence of recurrence. However, surgical resection in patients with low rectal cancer (RC) is challenging and may compromise anal function, leading to a low quality of life. To reduce unnecessary surgical resection in these patients, we used artificial intelligence (AI) to develop and validate a prediction model for the risk of recurrence after LE. MATERIALS AND METHODS We constructed an artificial neural network (ANN) to predict recurrence using pathological images from endoscopically or transanal surgically resected T1 RC specimens. Data were retrospectively obtained from two hospitals between 2001 and 2015. The model was constructed using 496 images obtained from the Guangdong Provincial People's Hospital (GDPH), and then validated using independent external datasets (150 images from Sun Yat-sen Memorial Hospital [SYSMH]) to verify its generalizability. RESULTS The ANN model yielded good discrimination, achieving areas under the receiver operating characteristic curves (AUC) of 0.979 in the training cohort (GDPH). The AUC for the validation cohort (SYSMH) was 0.978. More importantly, the AI-based prediction model avoided more than 34.9 % of unnecessary additional surgeries compared with the current US guideline in all enrolled patients. CONCLUSIONS We propose a novel ANN model for the risk of recurrence prediction in patients with T1 RC to provide physicians and patients guidance for decisions after LE. Furthermore, this may lead to a reduction in unnecessary invasive surgeries in patients with T1 RC.
Collapse
Affiliation(s)
- Jiarui Su
- Department of Gastrointestinal Surgery, Department of General Surgery, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Southern Medical University, Guangzhou, 510000, China; The Second School of Clinical Medicine, Southern Medical University, Guangzhou, 510000, China; Department of General Surgery, Guangdong Provincial People's Hospital Ganzhou Hospital (Ganzhou Municipal Hospital), Ganzhou, 341000, China
| | - Zhiyuan Liu
- Department of Gastrointestinal Surgery, Department of General Surgery, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Southern Medical University, Guangzhou, 510000, China; The Second School of Clinical Medicine, Southern Medical University, Guangzhou, 510000, China; Department of General Surgery, Guangdong Provincial People's Hospital Ganzhou Hospital (Ganzhou Municipal Hospital), Ganzhou, 341000, China
| | - Haiming Li
- School of Mathematics, South China University of Technology, Guangzhou, 510006, China
| | - Li Kang
- School of Software Engineering, South China University of Technology, Guangzhou, 510006, China
| | - Kaihong Huang
- Department of Gastroenterology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, 510000, China
| | - Jiawei Wu
- Department of Gastrointestinal Surgery, Department of General Surgery, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Southern Medical University, Guangzhou, 510000, China; Department of General Surgery, Guangdong Provincial People's Hospital Ganzhou Hospital (Ganzhou Municipal Hospital), Ganzhou, 341000, China; Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Southern Medical University, Guangzhou, 510000, China
| | - Han Huang
- School of Software Engineering, South China University of Technology, Guangzhou, 510006, China.
| | - Fei Ling
- School of Biology and Biological Engineering, South China University of Technology, Guangzhou, 510006, China.
| | - Xueqing Yao
- Department of Gastrointestinal Surgery, Department of General Surgery, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Southern Medical University, Guangzhou, 510000, China; The Second School of Clinical Medicine, Southern Medical University, Guangzhou, 510000, China; Department of General Surgery, Guangdong Provincial People's Hospital Ganzhou Hospital (Ganzhou Municipal Hospital), Ganzhou, 341000, China; Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Southern Medical University, Guangzhou, 510000, China; School of Medicine, South China University of Technology, Guangzhou, 510006, China.
| | - Chengzhi Huang
- Department of Gastrointestinal Surgery, Department of General Surgery, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Southern Medical University, Guangzhou, 510000, China.
| |
Collapse
|
3
|
Zhang X, Lai R, Bai L, Ji J, Qin R, Jiang L, Meng B, Zhang Y, Zheng X, Wang Y, Kui X, Zhang L, Ning D, Wang L, Chen Y, Wang X, Li S, Hua M, Wang J, Cao Y, Wang Y, Ma C, Dai Y, Song Y, Wang H, Wang M, He J, Fan L, Li K, Yin M, Cao L. A cell-interacting and multi-correcting method for automatic circulating tumor cells detection. Artif Intell Med 2025; 167:103164. [PMID: 40449145 DOI: 10.1016/j.artmed.2025.103164] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/16/2024] [Revised: 04/24/2025] [Accepted: 05/10/2025] [Indexed: 06/02/2025]
Abstract
Sensitive detection of circulating tumor cells (CTCs) from peripheral blood can serve as an effective tool in the early diagnosis and prognosis of cancer. Many methods based on modern object detectors were proposed in recent years for automatic abnormal cells detection in slide images. Although the modes of these methods can also be applied to the CTCs detection, several practical difficulties lead to suboptimal performance of them, such as accurate capture of CTCs in a large number of mixed cells and identification of CTCs and CTC-like cells with similar visual characteristics. Here, we develop a new cell-interacting and multi-correcting detector called CMD, and apply H&E-stained slide images to detect CTCs automatically for the first time. Specifically, the proposed method incorporates two task-oriented novel modules: (1) a self-attention module for aggregating feature interactions between cells and allowing the model to pay more attention to key abnormal cells, (2) a hard sample mining sampler for progressively correcting predictions of cells with ambiguous classification boundaries. Experiments conducted on a multi-center dataset of 1247 annotated slide images confirm the superiority of our method over state-of-the-art cell detection methods. The results of ablation experiment part also prove the effectiveness of two modules. The source codes of this paper are available at https://github.com/zx333445/CMD.
Collapse
Affiliation(s)
- Xuan Zhang
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Rensheng Lai
- Department of Pathology, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing 210023, China
| | - Ling Bai
- Department of Pathology, Baoan Central Hospital of Shenzhen, Shenzhen 518101, China
| | - Jianxin Ji
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Ruihao Qin
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Lihong Jiang
- Department of Pathology, Xi'an Chang'an District Hospital, Xi'an 710199, China
| | - Bin Meng
- Department of Pathology, Tianjin Medical University Cancer Hospital, Tianjin 300060, China
| | - Ying Zhang
- Department of Pathology, General Hospital of Eastern Theater Command Qinhuai Medical District, Nanjing 210002, China
| | - Xiaohan Zheng
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Yan Wang
- Department of Pathology, The Second Affiliated Hospital of Kunming Medical University, Kunming 650106, China
| | - Xiang Kui
- Department of Pathology, The Second Affiliated Hospital of Kunming Medical University, Kunming 650106, China
| | - Liuchao Zhang
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Dimin Ning
- Department of Pathology, Nanjing Jiangbei Jizhi Clinic, Nanjing 210008, China
| | - Liuying Wang
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Yujiang Chen
- Department of Pathology, The First Affiliated Hospital of Guizhou University of Chinese Medicine, Guizhou 550001, China
| | - Xinling Wang
- Department of Pathology, Nanjing Hospital of Chinese Medicine affiliated to Nanjing University of Chinese Medicine, Nanjing 210001, China
| | - Shuang Li
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Menglei Hua
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Junkai Wang
- Department of Pathology, Nanjing Jiangbei Jizhi Clinic, Nanjing 210008, China
| | - Yong Cao
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Yuanning Wang
- Department of Pathology, Nanjing Jiangbei Jizhi Clinic, Nanjing 210008, China
| | - Chenjing Ma
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Yanyan Dai
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Yongzhen Song
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Hesong Wang
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Meng Wang
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Jia He
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China
| | - Lijun Fan
- Center for Endemic Disease Control, Chinese Center for Disease Control and Prevention, Harbin Medical University, Harbin 150086, China
| | - Kang Li
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China.
| | - Mingzhu Yin
- Medical Pathology Center, Chongqing University Three Gorges Hospital, Chongqing 404000, China.
| | - Lei Cao
- Department of Biostatistics, School of Public Health, Harbin Medical University, Harbin 150081, China.
| |
Collapse
|
4
|
Ding R, Luong KD, Rodriguez E, da Silva ACAL, Hsu W. Combining graph neural network and Mamba to capture local and global tissue spatial relationships in whole slide images. Sci Rep 2025; 15:18261. [PMID: 40415116 DOI: 10.1038/s41598-025-99042-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2024] [Accepted: 04/16/2025] [Indexed: 05/27/2025] Open
Abstract
In computational pathology, extracting and representing spatial features from gigapixel whole slide images (WSIs) are fundamental tasks, but due to their large size, WSIs are typically segmented into smaller tiles. A critical aspect of analyzing WSIs is how information across tiles is aggregated to predict outcomes such as patient prognosis. We introduce a model that combines a message-passing graph neural network (GNN) with a state space model (Mamba) to capture both local and global spatial relationships among the tiles in WSIs. The model's effectiveness was demonstrated in predicting progression-free survival among patients with early-stage lung adenocarcinomas (LUAD). We compared the model with other state-of-the-art methods for tile-level information aggregation in WSIs, including statistics-based, multiple instance learning (MIL)-based, GNN-based, and GNN-transformer-based aggregation. Our model achieved the highest c-index (0.70) and has the largest number of parameters among comparison models yet maintained a short inference time. Additional experiments showed the impact of different types of node features and different tile sampling strategies on model performance. Code: https://github.com/rina-ding/gat-mamba .
Collapse
Affiliation(s)
- Ruiwen Ding
- Medical and Imaging Informatics, Department of Radiological Sciences, Department of Bioengineering, University of California, Los Angeles, CA, 90024, USA
| | - Kha-Dinh Luong
- Department of Computer Science, University of California, Santa Barbara, Santa Barbara, CA, 93106, USA
| | - Erika Rodriguez
- Department of Pathology and Laboratory Sciences, University of California, Los Angeles, CA, 90024, USA
| | | | - William Hsu
- Medical and Imaging Informatics, Department of Radiological Sciences, Department of Bioengineering, University of California, Los Angeles, CA, 90024, USA.
| |
Collapse
|
5
|
Liao H, Weber TD, Tan RY, Liu J, Fujimoto JG, Rosen S, Sun Y. Real-time histological evaluation of gastrointestinal tissue using non-linear microscopy. J Clin Pathol 2025; 78:364-369. [PMID: 40127917 DOI: 10.1136/jcp-2024-210031] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2024] [Accepted: 03/08/2025] [Indexed: 03/26/2025]
Abstract
AIM Over the past several decades, optical sectioning technologies have emerged as valuable tools for evaluating tissue histology. Unlike conventional tissue sectioning, these technologies allow for real-time intraoperative assessments and more efficient tissue triage. In the era of digital pathology, the demand for high-quality, high-throughput optical sectioning platforms is increasing, as they eliminate the need for traditional slide preparation and scanning, potentially transforming anatomical pathology workflows. While non-linear microscopy (NLM) has demonstrated promise in histological evaluation across various tissue types, its application in gastrointestinal tissue assessment remains unexplored. METHODS This study extends the use of NLM to gastrointestinal histology and develops an image atlas to highlight its potential as an automated digital pathology platform. RESULTS Our results indicate that NLM generates diagnostic-quality images comparable to traditional H&E slides. Moreover, NLM provides valuable three-dimensional (3D) spatial information, improving clinical evaluations of key histological features such as depth of invasion, lymphovascular and perineural invasion, tumour budding and margin assessment. Time-lapse videos further demonstrate NLM's capability to capture 3D histological structures up to a depth of approximately 100 µm. CONCLUSION Our findings demonstrate that NLM can serve as an optical sectioning platform for gastrointestinal histology, providing both diagnostic-quality imaging and advanced 3D visualisation. The introduction of an NLM-based atlas has the potential to redefine anatomical pathology workflows and advance digital pathology image analysis.
Collapse
Affiliation(s)
- Haihui Liao
- Department of Pathology, Mass General Brigham Salem Hospital, Salem, Massachusetts, USA
| | - Timothy D Weber
- Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
| | - Rachel Yixuan Tan
- Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
| | - Jeffrey Liu
- Lexington High School, Lexington, Massachusetts, USA
| | - James G Fujimoto
- Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
| | - Seymour Rosen
- Department of Pathology, Beth Israel Deaconess Medical Center, Boston, Massachusetts, USA
| | - Yue Sun
- Department of Pathology, Beth Israel Deaconess Medical Center, Boston, Massachusetts, USA
| |
Collapse
|
6
|
Mahl D, Schäfer MS, Voinea SA, Adib K, Duncan B, Salvi C, Novillo-Ortiz D. Responsible artificial intelligence in public health: a Delphi study on risk communication, community engagement and infodemic management. BMJ Glob Health 2025; 10:e018545. [PMID: 40409762 DOI: 10.1136/bmjgh-2024-018545] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2024] [Accepted: 04/08/2025] [Indexed: 05/25/2025] Open
Abstract
INTRODUCTION Artificial intelligence (AI) holds the potential to fundamentally transform how public health authorities use risk communication, community engagement and infodemic management (RCCE-IM) to prepare for, manage and mitigate public health emergencies. As research on this crucial transformation remains limited, we conducted a modified Delphi study on the impact of AI on RCCE-IM. METHODS In two successive surveys, 54 experts-scholars with expertise in public health, digital health, health communication, risk communication and AI, as well as RCCE-IM professionals-from 27 countries assessed opportunities, challenges and risks of AI, anticipated future scenarios, and identified principles and actions to facilitate the responsible use of AI. The first Delphi round followed an open, exploratory approach, while the second sought to prioritise and rank key findings from the initial phase. Qualitative thematic analysis and statistical methods were applied to evaluate responses. RESULTS According to the expert panel, AI could be highly beneficial, particularly for risk communication (eg, tailoring messages) and infodemic management (eg, social listening), while its utility for fostering community engagement was viewed more critically. Challenges and risks affect all three components of RCCE-IM equally, with algorithmic bias and privacy breaches being of particular concern. Panellists anticipated both optimistic (eg, democratisation of information) and pessimistic (eg, erosion of public trust) future scenarios. They identified seven principles for the responsible use of AI for public health practices, with equity and transparency being the most important. Prioritised actions ranged from regulatory measures, resource allocation and feedback loops to capacity building, public trust initiatives and educational training. CONCLUSION To responsibly navigate the multifaceted opportunities, challenges and risks of AI for RCCE-IM in public health emergencies, clear guiding principles, ongoing critical evaluation and training as well as societal collaboration across countries are needed.
Collapse
Affiliation(s)
- Daniela Mahl
- Department of Communication and Media Research, University of Zurich, Zurich, Switzerland
| | - Mike S Schäfer
- Department of Communication and Media Research, University of Zurich, Zurich, Switzerland
| | | | - Keyrellous Adib
- World Health Organization Regional Office for Europe, Copenhagen, Denmark
| | - Ben Duncan
- World Health Organization Regional Office for Europe, Copenhagen, Denmark
| | - Cristiana Salvi
- World Health Organization Regional Office for Europe, Copenhagen, Denmark
| | | |
Collapse
|
7
|
Sarvepalli S, Vadarevu S. Role of artificial intelligence in cancer drug discovery and development. Cancer Lett 2025; 627:217821. [PMID: 40414522 DOI: 10.1016/j.canlet.2025.217821] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2024] [Revised: 04/17/2025] [Accepted: 05/23/2025] [Indexed: 05/27/2025]
Abstract
The role of artificial intelligence (AI) in cancer drug discovery and development has garnered significant attention due to its potential to transform the traditionally time-consuming and expensive processes involved in bringing new therapies to market. AI technologies, such as machine learning (ML) and deep learning (DL), enable the efficient analysis of vast datasets, facilitate faster identification of drug targets, optimization of compounds, and prediction of clinical outcomes. This review explores the multifaceted applications of AI across various stages of cancer drug development, from early-stage discovery to clinical trial design, development. In early-stage discovery, AI-driven methods support target identification, virtual screening (VS), and molecular docking, offering precise predictions that streamline the identification of promising compounds. Additionally, AI is instrumental in de novo drug design and lead optimization, where algorithms can generate novel molecular structures and optimize their properties to enhance drug efficacy and safety profiles. Preclinical development benefits from AI's predictive modeling capabilities, particularly in assessing a drug's toxicity through in silico simulations. AI also plays a pivotal role in biomarker discovery, enabling the identification of specific molecular signatures that can inform patient stratification and personalized treatment approaches. In clinical development, AI optimizes trial design by leveraging real-world data (RWD), improving patient selection, and reducing the time required to bring new drugs to market. Despite its transformative potential, challenges remain, including issues related to data quality, model interpretability, and regulatory hurdles. Addressing these limitations is critical for fully realizing AI's potential in cancer drug discovery and development. As AI continues to evolve, its integration with other technologies, such as genomics and clustered regularly interspaced short palindromic repeats (CRISPR), holds promise for advancing personalized cancer therapies. This review provides a comprehensive overview of AI's impact on the cancer drug discovery and development and highlights future directions for this rapidly evolving field.
Collapse
Affiliation(s)
- Sruthi Sarvepalli
- College of Pharmacy and Health Sciences, St. John's University, Queens, NY, USA.
| | | |
Collapse
|
8
|
Yi X, Yu X, Li C, Li J, Cao H, Lu Q, Li J, Hou J. Deep learning radiopathomics based on pretreatment MRI and whole slide images for predicting over survival in locally advanced nasopharyngeal carcinoma. Radiother Oncol 2025:110949. [PMID: 40409367 DOI: 10.1016/j.radonc.2025.110949] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/08/2024] [Revised: 04/27/2025] [Accepted: 05/19/2025] [Indexed: 05/25/2025]
Abstract
PURPOSE To develop an integrative radiopathomic model based on deep learning to predict overall survival (OS) in locally advanced nasopharyngeal carcinoma (LANPC) patients. MATERIALS AND METHODS A cohort of 343 LANPC patients with pretreatment MRI and whole slide image (WSI) were randomly divided into training (n = 202), validation (n = 91), and external test (n = 50) sets. For WSIs, a self-attention mechanism was employed to assess the significance of different patches for the prognostic task, aggregating them into a WSI-level representation. For MRI, a multilayer perceptron was used to encode the extracted radiomic features, resulting in an MRI-level representation. These were combined in a multimodal fusion model to produce prognostic predictions. Model performances were evaluated using the concordance index (C-index), and Kaplan-Meier curves were employed for risk stratification. To enhance model interpretability, attention-based and Integrated Gradients techniques were applied to explain how WSIs and MRI features contribute to prognosis predictions. RESULTS The radiopathomics model achieved high predictive accuracy in predicting the OS, with a C-index of 0.755 (95 % CI: 0.673-0.838) and 0.744 (95 % CI: 0.623-0.808) in the training and validation sets, respectively, outperforming single-modality models (radiomic signature: 0.636, 95 % CI: 0.584-0.688; deep pathomic signature: 0.736, 95 % CI: 0.684-0.810). In the external test, similar findings were observed for the predictive performance of the radiopathomics, radiomic signature, and deep pathomic signature, with their C-indices being 0.735, 0.626, and 0.660 respectively. The radiopathomics model effectively stratified patients into high- and low-risk groups (P < 0.001). Additionally, attention heatmaps revealed that high-attention regions corresponded with tumor areas in both risk groups. CONCLUSIO n: The radiopathomics model holds promise for predicting clinical outcomes in LANPC patients, offering a potential tool for improving clinical decision-making.
Collapse
Affiliation(s)
- Xiaochun Yi
- Department of Diagnostic Radiology, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha 410013 Hunan, PR China
| | - Xiaoping Yu
- Department of Diagnostic Radiology, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha 410013 Hunan, PR China
| | - Congrui Li
- Department of Diagnostic Radiology, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha 410013 Hunan, PR China
| | - Junjian Li
- Hunan Provincial Key Laboratory on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha 410083, PR China
| | - Hui Cao
- Department of Health Service Center, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha 410013 Hunan, PR China
| | - Qiang Lu
- Department of Diagnostic Radiology, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha 410013 Hunan, PR China
| | - Junjun Li
- Department of Pathology, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, 283 Tongzipo Road, Yuelu District, Changsha, Hunan 410013, PR China
| | - Jing Hou
- Department of Diagnostic Radiology, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha 410013 Hunan, PR China.
| |
Collapse
|
9
|
Liu LL, Jing BZ, Liu X, Li RG, Wan Z, Zhang JY, Ouyang XM, Kong QN, Kang XL, Wang DD, Chen HH, Zhao ZH, Liang HY, Huang MY, Zheng CY, Yang X, Zheng XY, Zhang XK, Wei LJ, Cao C, Gao HY, Luo RZ, Cai MY. MMRNet: Ensemble deep learning models for predicting mismatch repair deficiency in endometrial cancer from histopathological images. Cell Rep Med 2025; 6:102099. [PMID: 40306276 DOI: 10.1016/j.xcrm.2025.102099] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2024] [Revised: 11/05/2024] [Accepted: 04/08/2025] [Indexed: 05/02/2025]
Abstract
Combining molecular classification with clinicopathologic methods improves risk assessment and chooses therapies for endometrial cancer (EC). Detecting mismatch repair (MMR) deficiencies in EC is crucial for screening Lynch syndrome and identifying immunotherapy candidates. An affordable and accessible tool is urgently needed to determine MMR status in EC patients. We introduce MMRNet, a deep convolutional neural network designed to predict MMR-deficient EC from whole-slide images stained with hematoxylin and eosin. MMRNet demonstrates strong performance, achieving an average area under the receiver operating characteristic curve (AUROC) of 0.897, with a sensitivity of 0.628 and a specificity of 0.949 in internal cross-validation. External validation using three additional datasets results in AUROCs of 0.790, 0.807, and 0.863. Employing a human-machine fusion approach notably improves diagnostic accuracy. MMRNet presents an effective method for identifying EC cases for confirmatory MMR testing and may assist in selecting candidates for immunotherapy.
Collapse
Affiliation(s)
- Li-Li Liu
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Bing-Zhong Jing
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Department of Information, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Xuan Liu
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Rong-Gang Li
- Department of Pathology, Jiangmen Central Hospital, Jiangmen 529000, China
| | - Zhao Wan
- Department of Pathology, Zhuhai Maternal and Child Health Care Hospital, Zhuhai 519000, China
| | - Jiang-Yu Zhang
- Department of Pathology, Affiliated Cancer Hospital and Institute of Guangzhou Medical University, Guangzhou 510095, China
| | - Xiao-Ming Ouyang
- Department of Pathology, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou 510260, China
| | - Qing-Nuan Kong
- Department of Pathology, Qingdao Municipal Hospital, Qingdao 266071, China
| | - Xiao-Ling Kang
- Department of Pathology, Guangdong Women and Children Hospital, Guangzhou 511400, China
| | - Dong-Dong Wang
- Department of Pathology, Guangdong Women and Children Hospital, Guangzhou 511400, China
| | - Hao-Hua Chen
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Department of Information, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Zi-Han Zhao
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Hao-Yu Liang
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Ma-Yan Huang
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Cheng-You Zheng
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Xia Yang
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Xue-Yi Zheng
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Xin-Ke Zhang
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Li-Jun Wei
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Chao Cao
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
| | - Hong-Yi Gao
- Department of Pathology, Guangdong Women and Children Hospital, Guangzhou 511400, China.
| | - Rong-Zhen Luo
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou 510060, China.
| | - Mu-Yan Cai
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou 510060, China.
| |
Collapse
|
10
|
Oskouei S, Valla M, Pedersen A, Smistad E, Dale VG, Høibø M, Wahl SGF, Haugum MD, Langø T, Ramnefjell MP, Akslen LA, Kiss G, Sorger H. Segmentation of Non-Small Cell Lung Carcinomas: Introducing DRU-Net and Multi-Lens Distortion. J Imaging 2025; 11:166. [PMID: 40423022 DOI: 10.3390/jimaging11050166] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2025] [Revised: 05/03/2025] [Accepted: 05/13/2025] [Indexed: 05/28/2025] Open
Abstract
The increased workload in pathology laboratories today means automated tools such as artificial intelligence models can be useful, helping pathologists with their tasks. In this paper, we propose a segmentation model (DRU-Net) that can provide a delineation of human non-small cell lung carcinomas and an augmentation method that can improve classification results. The proposed model is a fused combination of truncated pre-trained DenseNet201 and ResNet101V2 as a patch-wise classifier, followed by a lightweight U-Net as a refinement model. Two datasets (Norwegian Lung Cancer Biobank and Haukeland University Lung Cancer cohort) were used to develop the model. The DRU-Net model achieved an average of 0.91 Dice similarity coefficient. The proposed spatial augmentation method (multi-lens distortion) improved the Dice similarity coefficient from 0.88 to 0.91. Our findings show that selecting image patches that specifically include regions of interest leads to better results for the patch-wise classifier compared to other sampling methods. A qualitative analysis by pathology experts showed that the DRU-Net model was generally successful in tumor detection. Results in the test set showed some areas of false-positive and false-negative segmentation in the periphery, particularly in tumors with inflammatory and reactive changes. In summary, the presented DRU-Net model demonstrated the best performance on the segmentation task, and the proposed augmentation technique proved to improve the results.
Collapse
Affiliation(s)
- Soroush Oskouei
- Department of Circulation and Medical Imaging, Norwegian University of Science and Technology (NTNU), NO-7491 Trondheim, Norway
- Clinic of Medicine, Levanger Hospital, Nord-Trøndelag Health Trust, NO-7600 Levanger, Norway
| | - Marit Valla
- Department of Clinical and Molecular Medicine, Norwegian University of Science and Technology (NTNU), NO-7491 Trondheim, Norway
- Clinic of Laboratory Medicine, St. Olavs Hospital, Trondheim University Hospital, NO-7030 Trondheim, Norway
| | - André Pedersen
- Department of Clinical and Molecular Medicine, Norwegian University of Science and Technology (NTNU), NO-7491 Trondheim, Norway
- Clinic of Surgery, St. Olavs Hospital, Trondheim University Hospital, NO-7030 Trondheim, Norway
- Application Solutions, Sopra Steria, NO-7010 Trondheim, Norway
| | - Erik Smistad
- Department of Circulation and Medical Imaging, Norwegian University of Science and Technology (NTNU), NO-7491 Trondheim, Norway
- Department of Health Research, SINTEF Digital, NO-7465 Trondheim, Norway
| | - Vibeke Grotnes Dale
- Department of Clinical and Molecular Medicine, Norwegian University of Science and Technology (NTNU), NO-7491 Trondheim, Norway
- Department of Pathology, St. Olavs Hospital, Trondheim University Hospital, NO-7030 Trondheim, Norway
| | - Maren Høibø
- Department of Clinical and Molecular Medicine, Norwegian University of Science and Technology (NTNU), NO-7491 Trondheim, Norway
- Clinic of Laboratory Medicine, St. Olavs Hospital, Trondheim University Hospital, NO-7030 Trondheim, Norway
| | - Sissel Gyrid Freim Wahl
- Department of Pathology, St. Olavs Hospital, Trondheim University Hospital, NO-7030 Trondheim, Norway
| | - Mats Dehli Haugum
- Department of Pathology, St. Olavs Hospital, Trondheim University Hospital, NO-7030 Trondheim, Norway
| | - Thomas Langø
- Department of Health Research, SINTEF Digital, NO-7465 Trondheim, Norway
- Center for Innovation, Medical Devices and Technology, Research Department, St. Olavs Hospital, Trondheim University Hospital, NO-7491 Trondheim, Norway
| | - Maria Paula Ramnefjell
- Centre for Cancer Biomarkers CCBIO, Department of Clinical Medicine, University of Bergen, NO-5007 Bergen, Norway
- Department of Pathology, Haukeland University Hospital, NO-5020 Bergen, Norway
| | - Lars Andreas Akslen
- Centre for Cancer Biomarkers CCBIO, Department of Clinical Medicine, University of Bergen, NO-5007 Bergen, Norway
- Department of Pathology, Haukeland University Hospital, NO-5020 Bergen, Norway
| | - Gabriel Kiss
- Center for Innovation, Medical Devices and Technology, Research Department, St. Olavs Hospital, Trondheim University Hospital, NO-7491 Trondheim, Norway
- Department of Computer Science, Norwegian University of Science and Technology (NTNU), NO-7491 Trondheim, Norway
| | - Hanne Sorger
- Department of Circulation and Medical Imaging, Norwegian University of Science and Technology (NTNU), NO-7491 Trondheim, Norway
- Clinic of Medicine, Levanger Hospital, Nord-Trøndelag Health Trust, NO-7600 Levanger, Norway
| |
Collapse
|
11
|
Horbas H, Bauer M, Eckert A, Bethmann D, Wilfer A, Seliger B, Wickenhauser C. Comparison of Manual Versus QuPath Software-based Immunohistochemical Scoring Using Oral Squamous Cell Carcinoma as a Model. J Histochem Cytochem 2025:221554251335698. [PMID: 40371713 DOI: 10.1369/00221554251335698] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/16/2025] Open
Abstract
Gold standard for immunohistochemical analyses is the manual assessment by two specialist pathologists. This process is time-consuming, highly dependent on the respective evaluator and often difficult to reproduce. The use of image analysis software, such as ImageJ, QuPath, or CellProfiler, which employ machine learning and/or deep learning mechanisms to perform biomarker analyses, offers a potential solution to these problems. The objective of our study is to evaluate whether digital assessment using the open-source software QuPath is comparable to manual evaluation and to examine the inter-evaluator variability between the two manual evaluators and two software-based evaluations. Six tissue microarrays (TMAs) were constructed for a cohort of 309 patients with primary oral squamous cell carcinoma (OSCC). The tumor tissue and corresponding non-lesional squamous epithelial mucosa specimen were immunohistochemically stained for the biomarkers Ki67, as a nuclear marker; the epidermal growth factor receptor (EGF-R), as a membranous marker; and the major histocompatibility complex class I (MHC-I) heavy chain (HC) expressed on the membrane and in the cytoplasm. The staining pattern was analyzed by two experienced, independent manual evaluators and by QuPath. The percentage of positive cells, for Ki67, and the histoscore (H-score) based on the percentage of positive cells and their staining intensity, for EGF-R and MHC-I, were determined as final values. The results yielded high to excellent spearman correlation coefficients for all three biomarkers (p<0.001) in lesional and non-lesional tissues. The Bland-Altman plots demonstrated a high degree of agreement between manual and software-based analysis, as well as inter-evaluator variability demonstrating a high comparability of the evaluation methods. However, a prerequisite for a proper software-based analysis is an accurate, time-consuming annotation of the single specimen, which requires users with a comprehensive understanding of histology and extensive training in QuPath. Once these requirements are met, the software-based analysis offers advantages for large-scale biomarker studies due to objective and reproducible comparability of the stainings leading to a greater accuracy as well as the reuse of established conditions across similar analyses without requiring further operator input.
Collapse
Affiliation(s)
- Hannah Horbas
- Institute of Pathology, University Hospital Halle, Martin-Luther-University Halle-Wittenberg, Halle (Saale), Germany
| | - Marcus Bauer
- Institute of Pathology, University Hospital Halle, Martin-Luther-University Halle-Wittenberg, Halle (Saale), Germany
| | - Alexander Eckert
- Clinic for Oral and Maxillofacial Surgery, University Hospital of the Paracelsus Medical Private University, Nürnberg, Germany
| | - Daniel Bethmann
- Institute of Pathology, University Hospital Halle, Martin-Luther-University Halle-Wittenberg, Halle (Saale), Germany
| | - Andreas Wilfer
- Institute of Pathology, University Hospital Halle, Martin-Luther-University Halle-Wittenberg, Halle (Saale), Germany
- Krukenberg Cancer Center Halle, University Hospital Halle, Martin-Luther-University Halle-Wittenberg, Halle (Saale), Germany
| | - Barbara Seliger
- Medical Faculty, Martin-Luther-University Halle-Wittenberg, Halle (Saale), Germany
- Fraunhofer Institute for Cell Therapy and Immunology, Leipzig, Germany
- Institute of Translational Immunology and Center for Translational Medicine, Medical School "Theodor Fontane," Brandenburg an der Havel, Germany
- Faculty of Health Sciences Brandenburg, Brandenburg Medical School "Theodor Fontane," Brandenburg, Germany
| | - Claudia Wickenhauser
- Institute of Pathology, University Hospital Halle, Martin-Luther-University Halle-Wittenberg, Halle (Saale), Germany
| |
Collapse
|
12
|
Monabbati S, Corredor G, Pathak T, Peacock C, Yang K, Koyfman S, Scacheri P, Lewis J, Madabhushi A, Viswanath SE, Gryder B. Pathogenomic fingerprinting to identify associations between tumor morphology and epigenetic states. Eur J Cancer 2025; 221:115429. [PMID: 40239399 PMCID: PMC12042128 DOI: 10.1016/j.ejca.2025.115429] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/19/2025] [Accepted: 03/25/2025] [Indexed: 04/18/2025]
Abstract
INTRODUCTION Measuring the chromatin state of a tumor provides a powerful map of its epigenetic commitments; however, as these are generally bulk measurements, it has not yet been possible to connect changes in chromatin accessibility to the pathological signatures of complex tumors. In parallel, recent advances in computational pathology have enabled the identification of spatial features and immune cells within oral cavity tumors and their microenvironment. METHODS Here, we present pathogenomic fingerprinting (PaGeFin), a novel method that integrates morphological tumor features with chromatin states using ATAC-seq. This framework links spatial morphologic and epigenetic features, offering insights into tumor progression and immune evasion within and across tumors. Morphologic features describing spatial relationships between tumor and lymphocyte cells that are prognostic of oral cavity squamous cell carcinoma (OSCC) were identified through AI-driven pathology analysis. These pathomic features were spatially colocalized within the epigenome of 4 distinct sections of 4 OSCC tumors. RESULTS These key features pinpointed chromatin regions responsible for critical immune cell function through peak locations and enrichment analysis, highlighting loci of CD27+ memory B cells, helper CD4+ T cells, and cytotoxic CD8 naïve T cells that likely drive morphologic changes in the distribution of lymphocytes in the tumor microenvironment and promote aggressive tumor behavior. Gene Ontology analysis revealed that the CTLA4, CD79A, CD3D, and CCR7 genes were embedded in these regions. CONCLUSION This computational approach is the first to assess the correlation between pathomic and epigenetic features in the context of cancer.
Collapse
Affiliation(s)
- Shayan Monabbati
- Dept. of Genetics and Genome Sciences, Case Western Reserve University School of Medicine, Cleveland, OH, USA
| | - Germán Corredor
- Dept. of Biomedical Engineering, Emory University School of Medicine, Atlanta, GA, USA; Mayo Clinic, AZ, USA
| | - Tilak Pathak
- Dept. of Biomedical Engineering, Emory University School of Medicine, Atlanta, GA, USA
| | - Craig Peacock
- Dept. of Genetics and Genome Sciences, Case Western Reserve University School of Medicine, Cleveland, OH, USA
| | - Kailin Yang
- Dept. of Radiation Oncology, Holden Comprehensive Cancer Center, University of Iowa, Iowa City, IA, USA
| | - Shlomo Koyfman
- Dept. of Radiation Oncology, Cleveland Clinic, Cleveland, OH, USA
| | - Peter Scacheri
- Dept. of Genetics and Genome Sciences, Case Western Reserve University School of Medicine, Cleveland, OH, USA
| | | | - Anant Madabhushi
- Dept. of Biomedical Engineering, Emory University School of Medicine, Atlanta, GA, USA; Atlanta VA Medical Center, Atlanta, GA, USA.
| | - Satish E Viswanath
- Dept. of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA; Cleveland VA Medical Center, Cleveland, OH, USA
| | - Berkley Gryder
- Dept. of Genetics and Genome Sciences, Case Western Reserve University School of Medicine, Cleveland, OH, USA.
| |
Collapse
|
13
|
Chelebian E, Avenel C, Wählby C. Combining spatial transcriptomics with tissue morphology. Nat Commun 2025; 16:4452. [PMID: 40360467 PMCID: PMC12075478 DOI: 10.1038/s41467-025-58989-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2024] [Accepted: 04/04/2025] [Indexed: 05/15/2025] Open
Abstract
Spatial transcriptomics has transformed our understanding of tissue architecture by preserving the spatial context of gene expression patterns. Simultaneously, advances in imaging AI have enabled extraction of morphological features describing the tissue. This review introduces a framework for categorizing methods that combine spatial transcriptomics with tissue morphology, focusing on either translating or integrating morphological features into spatial transcriptomics. Translation involves using morphology to predict gene expression, creating super-resolution maps or inferring genetic information from H&E-stained samples. Integration enriches spatial transcriptomics by identifying morphological features that complement gene expression. We also explore learning strategies and future directions for this emerging field.
Collapse
Affiliation(s)
- Eduard Chelebian
- Department of Information Technology and SciLifeLab, Uppsala University, Uppsala, Sweden
| | - Christophe Avenel
- Department of Information Technology and SciLifeLab, Uppsala University, Uppsala, Sweden
| | - Carolina Wählby
- Department of Information Technology and SciLifeLab, Uppsala University, Uppsala, Sweden.
| |
Collapse
|
14
|
Yang K, Chen L, Zheng X, Li X, Lan J, Wu Y, Tsang JYS, Tse GM. Ray-Aided Quadruple Affiliation Network for Calculating Tumor-Stroma Ratios in Breast Cancers. IEEE TRANSACTIONS ON IMAGE PROCESSING : A PUBLICATION OF THE IEEE SIGNAL PROCESSING SOCIETY 2025; 34:2811-2825. [PMID: 40266855 DOI: 10.1109/tip.2025.3561679] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/25/2025]
Abstract
Tumor-stroma ratio (TSR), which is the area ratio between two components within tumor beds, namely tumor cells and tumor stroma, has been suggested as a promising prognostic feature in breast cancers. However, due to imperfect datasets, and the similarity between tumor stroma and non-tumor stroma, previous algorithms struggle to delineate tumor beds, especially those of histomorphologies with a fibrotic focus. To overcome these limitations, we propose a novel ray-aided quadruple affiliation network (RQA-Net) for calculating TSRs in breast cancers. RQA-Net uses quadruple branches to segment tumor cells and tumor beds simultaneously, where a crisscross task subtraction module (CTS-Module) is designed to locate tumor stroma, grounded on its affiliation relationships with tumor beds. Moreover, we propose an affiliation loss (Aff-Loss) to force identified tumor beds to incorporate tumor cells to enhance their affiliation relationships. Furthermore, we propose a ray-based hypothesis testing (RH-Testing) to obtain line segments from ray equations in tumor beds that can decorate identified tumor beds by overlapping. In summary, RQA-Net precisely predicts tumor cells and tumor beds, and thus supports the calculation of TSRs. We also create a cancerous dataset (CrD-Set) containing 100 slides with an average resolution of $50,000\times 50,000$ pixels from real breast cancer cases, which is the first dataset with pixel-wise tumor bed annotations. Experimental results on existing datasets and CrD-Set demonstrate that compared with previous methods, RQA-Net better calculates breast cancer TSRs by precisely identifying tumor cells and tumor beds. The created CrD-Set and codes in this work will be available online at https://github.com/Kunpingyang1992/Breast-Cancer-TSR-Calculation.
Collapse
|
15
|
Badve S, Kumar GL, Lang T, Peigin E, Pratt J, Anders R, Chatterjee D, Gonzalez RS, Graham RP, Krasinskas AM, Liu X, Quaas A, Saxena R, Setia N, Tang L, Wang HL, Rüschoff J, Schildhaus HU, Daifalla K, Päpper M, Frey P, Faber F, Karasarides M. Augmented reality microscopy to bridge trust between AI and pathologists. NPJ Precis Oncol 2025; 9:139. [PMID: 40355526 PMCID: PMC12069518 DOI: 10.1038/s41698-025-00899-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2025] [Accepted: 04/02/2025] [Indexed: 05/14/2025] Open
Abstract
Diagnostic certainty is the cornerstone of modern medicine and critical for maximal treatment benefit. When evaluating biomarker expression by immunohistochemistry (IHC), however, pathologists are hindered by complex scoring methodologies, unique positivity cut-offs and subjective staining interpretation. Artificial intelligence (AI) can potentially eliminate diagnostic uncertainty, especially when AI "trustworthiness" is proven by expert pathologists in the context of real-world clinical practice. Building on an IHC foundation model, we employed pathologists-in-the-loop finetuning to produce a programmed cell death ligand 1 (PD-L1) CPS AI Model. We devised a multi-head augmented reality microscope (ARM) system overlayed with the PD-L1 CPS AI Model to assess interobserver variability and gauge the pathologists' trust in AI model outputs. Using difficult to interpret regions on gastroesophageal biopsies, we show that AI-assistance improved case agreement between any 2 pathologists by 14% (agreement on 77% vs 91%) and among 11 pathologists by 26% (agreement on 43% vs 69%). At a clinical cutoff of PD-L1 CPS ≥ 5, the number of cases diagnosed as positive by all 11 pathologists increased by 31%. Our findings underscore the benefits of fully engaging pathologists as active participants in the development and deployment of IHC AI models and frame the roadmap for trustworthy AI as a bridge to increased adoption in routine pathology practice.
Collapse
Affiliation(s)
- Sunil Badve
- Emory University School of Medicine, Atlanta, GA, USA.
| | | | | | | | | | - Robert Anders
- Johns Hopkins University Baltimore, Baltimore, MD, USA
| | | | | | | | | | - Xiuli Liu
- Washington University School of Medicine, St Louis, MO, USA
| | | | - Romil Saxena
- Emory University School of Medicine, Atlanta, GA, USA
| | | | - Laura Tang
- Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Hanlin L Wang
- UCLA David Geffen School of Medicine, Los Angeles, CA, USA
| | - Josef Rüschoff
- Discovery Life Sciences Biomarker Services GmbH, Kassel, Germany
| | | | | | | | | | | | | |
Collapse
|
16
|
Dia AK, Kolnohuz A, Yolchuyeva S, Tonneau M, Lamaze F, Orain M, Gagné A, Blais F, Coulombe F, Malo J, Belkaid W, Elkrief A, Williamson D, Routy B, Joubert P, Laplante M, Bilodeau S, Manem VS. Computational analysis of whole slide images predicts PD-L1 expression and progression-free survival in immunotherapy-treated non-small cell lung cancer patients. J Transl Med 2025; 23:510. [PMID: 40329352 PMCID: PMC12056990 DOI: 10.1186/s12967-025-06487-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2024] [Accepted: 04/13/2025] [Indexed: 05/08/2025] Open
Abstract
BACKGROUND Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment by significantly improving the efficacy of treatments and tolerability for patients with non-small cell lung cancer (NSCLC). However, even after meticulous selection based on molecular criteria, only 20-30% of the patients respond to ICIs. This highlights the urgent clinical need to develop more precise biomarkers to better identify individuals who will benefit from these expensive therapies. METHODS Data from NSCLC patients treated with immunotherapy were collected from two institutions. From the histological images of tumors, pathomics features were extracted. We employed six machine learning models and seven feature selection methods to predict expression of the programmed death-ligand 1 (PD-L1), a current biomarker used to select patients for immunotherapy, and progression-free survival (PFS). The association between pathomics features and biological pathways was explored to validate pathomics-based signatures. We performed gene set enrichment analysis to identify the pathways enriched with the predictive signatures. RESULTS Handcrafted histological features were extracted from the whole slide images (WSI). The Support Vector Machines model with the SurfStar feature selection method, offered the best results, with an area under the curve (AUC) of around 0.66 for both the training and validation sets to predict PD-L1. For the prediction of PFS, the most effective model was linear discriminant analysis using the Multi Surf feature selection method with an AUC of 0.71 for the training set and 0.62 for the validation set. We found immune pathways to be upregulated in the high PD-L1 and high PFS groups, confirming the utility of image analysis for predicting clinical endpoints in patients treated with immunotherapy. CONCLUSION Our models, based on the analysis of histological images, can serve as predictive biomarkers for PD-L1 and PFS. This approach, focused on histological images, enables the distinction of patients based on treatment response, thus providing clinicians with a valuable tool for patient management. With further validation on external cohorts, these models could enhance clinical decision-making through analysis of routine medical images.
Collapse
Affiliation(s)
- Abdou Khadir Dia
- Centre de Recherche du CHU de Québec - Université Laval, Québec, Canada
| | - Alona Kolnohuz
- Quebec Heart & Lung Institute Research Center, Québec, Canada
- Université Laval, Québec, Canada
| | - Sevinj Yolchuyeva
- Centre de Recherche du CHU de Québec - Université Laval, Québec, Canada
- Department of Molecular Biology, Medical Biochemistry and Pathology, Université Laval, Québec, Canada
| | - Marion Tonneau
- Centre de Recherche du Centre Hospitalier Universitaire de Montréal, Montréal, Canada
- Université de médecine de Lille, Lille, France
| | - Fabien Lamaze
- Quebec Heart & Lung Institute Research Center, Québec, Canada
| | - Michele Orain
- Quebec Heart & Lung Institute Research Center, Québec, Canada
| | | | | | | | - Julie Malo
- Centre de Recherche du Centre Hospitalier Universitaire de Montréal, Montréal, Canada
| | - Wiam Belkaid
- Centre de Recherche du Centre Hospitalier Universitaire de Montréal, Montréal, Canada
| | - Arielle Elkrief
- Centre de Recherche du Centre Hospitalier Universitaire de Montréal, Montréal, Canada
| | - Drew Williamson
- Department of Pathology and Laboratory Medicine, Emory University School of Medicine, Atlanta, USA
| | - Bertrand Routy
- Centre de Recherche du Centre Hospitalier Universitaire de Montréal, Montréal, Canada
| | - Philippe Joubert
- Quebec Heart & Lung Institute Research Center, Québec, Canada
- Department of Molecular Biology, Medical Biochemistry and Pathology, Université Laval, Québec, Canada
| | - Mathieu Laplante
- Quebec Heart & Lung Institute Research Center, Québec, Canada
- Université Laval, Québec, Canada
| | - Steve Bilodeau
- Centre de Recherche du CHU de Québec - Université Laval, Québec, Canada
- Department of Molecular Biology, Medical Biochemistry and Pathology, Université Laval, Québec, Canada
- Cancer Research Center, Université Laval, Québec, Canada
- Big Data Research Center, Université Laval, Québec, Canada
| | - Venkata Sk Manem
- Centre de Recherche du CHU de Québec - Université Laval, Québec, Canada.
- Quebec Heart & Lung Institute Research Center, Québec, Canada.
- Department of Molecular Biology, Medical Biochemistry and Pathology, Université Laval, Québec, Canada.
- Cancer Research Center, Université Laval, Québec, Canada.
- Big Data Research Center, Université Laval, Québec, Canada.
| |
Collapse
|
17
|
Nguyen MH, Le MHN, Bui AT, Le NQK. Artificial intelligence in predicting EGFR mutations from whole slide images in lung Cancer: A systematic review and Meta-Analysis. Lung Cancer 2025; 204:108577. [PMID: 40339270 DOI: 10.1016/j.lungcan.2025.108577] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2024] [Revised: 04/11/2025] [Accepted: 05/02/2025] [Indexed: 05/10/2025]
Abstract
BACKGROUND Epidermal growth factor receptor (EGFR) mutations play a pivotal role in guiding targeted therapy for lung cancer, making their accurate detection essential for personalized treatment. Recently, artificial intelligence (AI) has emerged as a promising tool for identifying EGFR mutation status from digital pathology images. This systematic review and meta-analysis evaluate the diagnostic accuracy of AI models in predicting EGFR mutations from whole slide images (WSIs) in lung cancer patients. METHODS A comprehensive search was conducted across four databases (EMBASE, PubMed, Web of Science, and Scopus) for studies published up to June 20th, 2024. Studies employing AI algorithms, including machine learning and deep learning techniques, to predict EGFR mutations from digital pathology images were included. The risk of bias and applicability concerns were assessed using the QUADAS-AI tool. Diagnostic accuracy metrics such as sensitivity, specificity, and the Area Under the Curve (AUC) were extracted. Random-effects models were applied to synthesize the AI model performance. This study is registered with PROSPERO (CRD42024570496). RESULTS Out of 1,828 identified studies, 16 met the inclusion criteria, with 4 eligible for meta-analysis. The pooled results demonstrated that AI algorithms achieved an AUC of 0.756 (95% CI: 0.669-0.824), a sensitivity of 66.3% (95% CI: X-Y), and a specificity of 68.1% (95% CI: X-Y). Subgroup analyses revealed that AI models using in-house datasets, surgical resection samples, the ResNet architecture, and tumor-focused regions exhibited improved predictive performance. CONCLUSION AI models exhibit potential for non-invasive prediction of EGFR mutations in lung cancer patients using WSIs, although current accuracy and precision warrant further refinement. Future research should aim to enhance AI algorithms, validate findings on larger datasets, and integrate these tools into clinical workflows to optimize lung cancer management.
Collapse
Affiliation(s)
- Mai Hanh Nguyen
- International Ph.D. Program in Cell Therapy and Regenerative Medicine, College of Medicine, Taipei Medical University, Taipei 110, Taiwan; Pathology and Forensic Medicine Department, 103 Military Hospital, Hanoi, Vietnam; AIBioMed Research Group, Taipei Medical University, Taipei 110, Taiwan
| | - Minh Huu Nhat Le
- International Ph.D. Program in Medicine, College of Medicine, Taipei Medical University, Taipei 110, Taiwan; AIBioMed Research Group, Taipei Medical University, Taipei 110, Taiwan
| | - Anh Tuan Bui
- Department of Spine Surgery, 103 Military Hospital, Hanoi, Vietnam
| | - Nguyen Quoc Khanh Le
- In-Service Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, Taipei 110, Taiwan; AIBioMed Research Group, Taipei Medical University, Taipei 110, Taiwan; Translational Imaging Research Center, Taipei Medical University Hospital, Taipei 110, Taiwan.
| |
Collapse
|
18
|
Panzeri D, Laohawetwanit T, Akpinar R, De Carlo C, Belsito V, Terracciano L, Aghemo A, Pugliese N, Chirico G, Inverso D, Calderaro J, Sironi L, Di Tommaso L. Assessing the diagnostic accuracy of ChatGPT-4 in the histopathological evaluation of liver fibrosis in MASH. Hepatol Commun 2025; 9:e0695. [PMID: 40304570 PMCID: PMC12045550 DOI: 10.1097/hc9.0000000000000695] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/17/2024] [Accepted: 01/26/2025] [Indexed: 05/02/2025] Open
Abstract
BACKGROUND Large language models like ChatGPT have demonstrated potential in medical image interpretation, but their efficacy in liver histopathological analysis remains largely unexplored. This study aims to assess ChatGPT-4-vision's diagnostic accuracy, compared to liver pathologists' performance, in evaluating liver fibrosis (stage) in metabolic dysfunction-associated steatohepatitis. METHODS Digitized Sirius Red-stained images for 59 metabolic dysfunction-associated steatohepatitis tissue biopsy specimens were evaluated by ChatGPT-4 and 4 pathologists using the NASH-CRN staging system. Fields of view at increasing magnification levels, extracted by a senior pathologist or randomly selected, were shown to ChatGPT-4, asking for fibrosis staging. The diagnostic accuracy of ChatGPT-4 was compared with pathologists' evaluations and correlated to the collagen proportionate area for additional insights. All cases were further analyzed by an in-context learning approach, where the model learns from exemplary images provided during prompting. RESULTS ChatGPT-4's diagnostic accuracy was 81% when using images selected by a pathologist, while it decreased to 54% with randomly cropped fields of view. By employing an in-context learning approach, the accuracy increased to 88% and 77% for selected and random fields of view, respectively. This method enabled the model to fully and correctly identify the tissue structures characteristic of F4 stages, previously misclassified. The study also highlighted a moderate to strong correlation between ChatGPT-4's fibrosis staging and collagen proportionate area. CONCLUSIONS ChatGPT-4 showed remarkable results with a diagnostic accuracy overlapping those of expert liver pathologists. The in-context learning analysis, applied here for the first time to assess fibrosis deposition in metabolic dysfunction-associated steatohepatitis samples, was crucial in accurately identifying the key features of F4 cases, critical for early therapeutic decision-making. These findings suggest the potential for integrating large language models as supportive tools in diagnostic pathology.
Collapse
Affiliation(s)
- Davide Panzeri
- Department of Physics, University of Milano-Bicocca, Milan, Italy
| | - Thiyaphat Laohawetwanit
- Division of Pathology, Chulabhorn International College of Medicine, Thammasat University, Pathum Thani, Thailand
| | - Reha Akpinar
- Department of Biomedical Sciences, Humanitas University, Milan, Italy
- Department of Pathology, IRCCS Humanitas Research Hospital, Milan, Italy
| | - Camilla De Carlo
- Department of Biomedical Sciences, Humanitas University, Milan, Italy
- Department of Pathology, IRCCS Humanitas Research Hospital, Milan, Italy
| | - Vincenzo Belsito
- Department of Pathology, IRCCS Humanitas Research Hospital, Milan, Italy
| | - Luigi Terracciano
- Department of Biomedical Sciences, Humanitas University, Milan, Italy
- Department of Pathology, IRCCS Humanitas Research Hospital, Milan, Italy
| | - Alessio Aghemo
- Department of Biomedical Sciences, Humanitas University, Milan, Italy
- Department of Gastroenterology, Division of Internal Medicine and Hepatology, IRCCS Humanitas Research Hospital, Milan, Italy
| | - Nicola Pugliese
- Department of Biomedical Sciences, Humanitas University, Milan, Italy
- Department of Gastroenterology, Division of Internal Medicine and Hepatology, IRCCS Humanitas Research Hospital, Milan, Italy
| | - Giuseppe Chirico
- Department of Physics, University of Milano-Bicocca, Milan, Italy
| | - Donato Inverso
- Division of Immunology, Transplantation and Infectious Diseases IRCCS San Raffaele Scientific Institute, Milan, Italy
- Vita-Salute San Raffaele University, Milan, Italy
| | - Julien Calderaro
- Team «Viruses, Hepatology, Cancer», Institut Mondor de Recherche Biomédicale, INSERM U955, Hôpital, Henri Mondor (AP-HP), Université Paris-Est, Créteil, France
- Department of Pathology, AP-HP, Henri Mondor University Hospital, Créteil, France
| | - Laura Sironi
- Department of Physics, University of Milano-Bicocca, Milan, Italy
| | - Luca Di Tommaso
- Department of Biomedical Sciences, Humanitas University, Milan, Italy
- Department of Pathology, IRCCS Humanitas Research Hospital, Milan, Italy
| |
Collapse
|
19
|
Li T, Zhou X, Xue J, Zeng L, Zhu Q, Wang R, Yu H, Xia J. Cross-modal alignment and contrastive learning for enhanced cancer survival prediction. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2025; 263:108633. [PMID: 39961170 DOI: 10.1016/j.cmpb.2025.108633] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/05/2024] [Revised: 12/28/2024] [Accepted: 01/30/2025] [Indexed: 03/14/2025]
Abstract
BACKGROUND AND OBJECTIVE Integrating multimodal data, such as pathology images and genomics, is crucial for understanding cancer heterogeneity, personalized treatment complexity, and enhancing survival prediction. However, most current prognostic methods are limited to a single domain of histopathology or genomics, inevitably reducing their potential for accurate patient outcome prediction. Despite advancements in the concurrent analysis of pathology and genomic data, existing approaches inadequately address the intricate intermodal relationships. METHODS This paper introduces the CPathomic method for multimodal data-based survival prediction. By leveraging whole slide pathology images to guide local pathological features, the method effectively mitigates significant intermodal differences through a cross-modal representational contrastive learning module. Furthermore, it facilitates interactive learning between different modalities through cross-modal and gated attention modules. RESULTS The extensive experiments on five public TCGA datasets demonstrate that CPathomic framework effectively bridges modality gaps, consistently outperforming alternative multimodal survival prediction methods. CONCLUSION The model we propose, CPathomic, unveils the potential of contrastive learning and cross-modal attention in the representation and fusion of multimodal data, enhancing the performance of patient survival prediction.
Collapse
Affiliation(s)
- Tengfei Li
- School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China
| | - Xuezhong Zhou
- School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China
| | - Jingyan Xue
- School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China
| | - Lili Zeng
- School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China
| | - Qiang Zhu
- School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China
| | - Ruiping Wang
- School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China
| | - Haibin Yu
- The First Affiliated Hospital, Henan University of Chinese Medicine, Henan, 450000, China
| | - Jianan Xia
- School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China.
| |
Collapse
|
20
|
Park S, Kang H, Choi Y, Yoon SG, Park HJ, Jin H, Kim H, Jeong Y, Shim JS, Noh TI, Kang SH, Lee KH. Precision screening with sequential multi-algorithm reclassification technique (SMART): Saving bladders from unnecessary cystectomy. Comput Biol Med 2025; 189:109980. [PMID: 40064121 DOI: 10.1016/j.compbiomed.2025.109980] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2024] [Revised: 02/28/2025] [Accepted: 03/03/2025] [Indexed: 04/01/2025]
Abstract
Bladder cancer, when diagnosed at an advanced stage, often necessitates inevitable invasive intervention. Consequently, non-invasive biosensor-based cancer detection and AI-based precision screening are being actively employed. However, the misclassification of cancer patients as normal-referred to as false negatives-remains a significant concern, as it could lead to fatal outcomes in lifespan. Moreover, while ensemble techniques such as soft voting and other methods can improve model accuracy and reduce misclassification, their effectiveness is limited and not applicable to all diagnostic tasks. Here, we developed a double stage cancer screening system that utilizes a sensitive urinary electrical biosensor implemented with an AI model and XAI interpretation tools. This system is designed for screening bladder cancer, well-known for its notable recurrence and high tendency to advance from non-invasive muscle tumors to muscle-invasive tumors. Four urinary biomarkers (CK8, CK18, PD-1, PD-L1) were measured by a field-effect transistor biosensor, and along with gender and age information, patients underwent initial screening by the CatBoost classification model. Patients initially classified as normal were reclassified using local explanations from neural networks offering a different perspective than CatBoost. After the second-stage screening, all of the false negatives from the initial screening could be correctly reclassified as cancer patients. Furthermore, global explanation guides the improvement of the AI model to be trained on an appropriate set of biomarker features to achieve high accuracy.
Collapse
Affiliation(s)
- Sungwook Park
- Center for Advanced Biomolecular Recognition, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul, 02792, Republic of Korea
| | - Heeseok Kang
- Center for Advanced Biomolecular Recognition, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul, 02792, Republic of Korea
| | - Yukyoung Choi
- Center for Advanced Biomolecular Recognition, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul, 02792, Republic of Korea; KU-KIST Graduate School of Converging Science and Technology, Korea University, Seoul, 02481, Republic of Korea
| | - Sung Goo Yoon
- Department of Urology, Korea University, School of Medicine, Seoul, 02841, Republic of Korea
| | - Hyung Joon Park
- Center for Advanced Biomolecular Recognition, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul, 02792, Republic of Korea; KU-KIST Graduate School of Converging Science and Technology, Korea University, Seoul, 02481, Republic of Korea
| | - Harin Jin
- Center for Advanced Biomolecular Recognition, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul, 02792, Republic of Korea; Division of Bio-Medical Science and Technology, KIST School, University of Science and Technology (UST), Seoul, Republic of Korea
| | - Hojun Kim
- Center for Advanced Biomolecular Recognition, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul, 02792, Republic of Korea; Division of Bio-Medical Science and Technology, KIST School, University of Science and Technology (UST), Seoul, Republic of Korea
| | - Youngdo Jeong
- Center for Advanced Biomolecular Recognition, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul, 02792, Republic of Korea; Division of Bio-Medical Science and Technology, KIST School, University of Science and Technology (UST), Seoul, Republic of Korea; Department of HY-KIST Bio-convergence, Hanyang University, Seoul, 04763, Republic of Korea
| | - Ji Sung Shim
- Department of Urology, Korea University, School of Medicine, Seoul, 02841, Republic of Korea
| | - Tae Il Noh
- Department of Urology, Korea University, School of Medicine, Seoul, 02841, Republic of Korea
| | - Seok Ho Kang
- Department of Urology, Korea University, School of Medicine, Seoul, 02841, Republic of Korea
| | - Kwan Hyi Lee
- Center for Advanced Biomolecular Recognition, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul, 02792, Republic of Korea; KU-KIST Graduate School of Converging Science and Technology, Korea University, Seoul, 02481, Republic of Korea; Division of Bio-Medical Science and Technology, KIST School, University of Science and Technology (UST), Seoul, Republic of Korea.
| |
Collapse
|
21
|
Liu X, Yao J, Wang D, Xiao W, Zhou W, Li L, He F, Luo Y, Xiao M, Yang Z, Yang G, Qin X. Machine Learning Model for Risk Stratification of Papillary Thyroid Carcinoma Based on Radiopathomics. Acad Radiol 2025; 32:2545-2553. [PMID: 39870562 DOI: 10.1016/j.acra.2024.12.062] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2024] [Revised: 12/18/2024] [Accepted: 12/27/2024] [Indexed: 01/29/2025]
Abstract
RATIONALE AND OBJECTIVES This study aims to develop a radiopathomics model based on preoperative ultrasound and fine-needle aspiration cytology (FNAC) images to enable accurate, non-invasive preoperative risk stratification for patients with papillary thyroid carcinoma (PTC). The model seeks to enhance clinical decision-making by optimizing preoperative treatment strategies. METHODS A retrospective analysis was conducted on data from PTC patients who underwent thyroidectomy between October 2022 and May 2024 across six centers. Based on lymph node dissection outcomes, patients were categorized into high-risk and low-risk groups. Initially, a clinical predictive model was established based on the maximum diameter of the thyroid nodules. Radiomics features were extracted from preoperative two-dimensional ultrasound images, and pathomics features were extracted from 400x magnification H&E-stained tumor cell images from FNAC. The most predictive radiomics and pathomics features were identified through univariate analysis, Pearson correlation analysis and LASSO algorithm. The most valuable radiopathomics features were then selected by combining these predictive features. Finally, machine learning with the XGBoost algorithm was employed to construct radiomics, pathomics, and radiopathomics models. The performance of the models was evaluated using the area under the curve (AUC), decision curve analysis, accuracy, specificity, sensitivity, positive predictive value, and negative predictive value. RESULTS A total of 688 PTC patients were included, with 344 classified as intermediate/high-risk and 344 as low-risk. The multimodal radiopathomics model demonstrated excellent predictive performance, with AUCs of 0.886 (95% CI: 0.829-0.924) and 0.828 (95% CI: 0.751-0.879) in two external validation cohorts, significantly outperforming the clinical model (AUCs of 0.662 and 0.601), radiomics model (AUCs of 0.702 and 0.697), and pathomics model (AUCs of 0.741 and 0.712). CONCLUSION The radiopathomics model exhibits significant advantages in accurately predicting preoperative risk stratification in PTC patients. Its application is expected to reduce unnecessary lymph node dissection surgeries, optimize treatment strategies, and improve therapeutic outcomes.
Collapse
Affiliation(s)
- Xiaoling Liu
- Department of Ultrasound, Beijing Anzhen Nanchong Hospital, Capital Medical University (Nanchong Central Hospital), Second Clinical Medical College of North Sichuan Medical College, Nanchong 637000, China (X.L.); Department of Ultrasound, Chengdu Second People's Hospital, Chengdu 610000, China (X.L., X.Q.)
| | - Jiao Yao
- North Sichuan Medical College, Nanchong 637000, China (J.Y., D.W., W.X., M.X., Z.Y., G.Y.)
| | - Di Wang
- North Sichuan Medical College, Nanchong 637000, China (J.Y., D.W., W.X., M.X., Z.Y., G.Y.)
| | - Weihan Xiao
- North Sichuan Medical College, Nanchong 637000, China (J.Y., D.W., W.X., M.X., Z.Y., G.Y.)
| | - Wang Zhou
- Department of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei 230022, China (W.Z.)
| | - Lin Li
- Department of Ultrasound, Suining Central Hospital, Suining 629000, China (L.L.)
| | - Fanding He
- Department of Medical Ultrasound, Sichuan Provincial People's Hospital, School of Medicine, University of Electronic Science and Technology of China, Chengdu 610072, China (F.H.)
| | - Yujie Luo
- Department of Ultrasound, West China School of Public Health and West China Fourth Hospital, Sichuan University, Chengdu 610000, China (Y.L.)
| | - Mengyao Xiao
- North Sichuan Medical College, Nanchong 637000, China (J.Y., D.W., W.X., M.X., Z.Y., G.Y.)
| | - Ziqing Yang
- North Sichuan Medical College, Nanchong 637000, China (J.Y., D.W., W.X., M.X., Z.Y., G.Y.)
| | - Guixiang Yang
- North Sichuan Medical College, Nanchong 637000, China (J.Y., D.W., W.X., M.X., Z.Y., G.Y.)
| | - Xiachuan Qin
- Department of Ultrasound, Chengdu Second People's Hospital, Chengdu 610000, China (X.L., X.Q.).
| |
Collapse
|
22
|
Allaume P, Bourgade R, Uguen A, Pécot T, Prevot S, Guettier C, Selves J, Bertheau P, Franchet C, Svrcek M, Sabourin JC, Brevet M, Calderaro J, Rioux-Leclercq N, Loussouarn D, Kammerer-Jacquet SF. [A national survey from the French Society of Pathology on research and application of artificial intelligence in pathology]. Ann Pathol 2025; 45:224-232. [PMID: 39743406 DOI: 10.1016/j.annpat.2024.12.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2024] [Revised: 12/03/2024] [Accepted: 12/07/2024] [Indexed: 01/04/2025]
Abstract
The 2030 French Innovation Healthcare national plan defined "Digital Healthcare" as one of its priority. The deployment of digital pathology and artificial intelligence fits perfectly into this framework. Therefore we evaluated the pathologist's interest in those fields by conducting an online survey among members of the French Society of Pathology, mainly composed of senior pathologists and trainees (n=2301). We collected 123 answers originating nationwide and representative of all status of practice. A heavy majority of participants (83%) declared themselves "interested or very interested" in digital transition and AI. Twenty-six percent of participants took part in academic research projects and 20% in industrial research projects. With digital pathology becoming increasingly common nationwide, there is a growing interest of pathologists in the development and validation of AI algorithms. In order to support this dynamic, a commission for research on artificial intelligence has been created under the authority of the French Society of Pathology.
Collapse
Affiliation(s)
- Pierre Allaume
- Service d'anatomie et cytologie pathologique, hôpital Pontchaillou, CHU de Rennes, université de Rennes 1, 2, rue Henri-Le-Guilloux, 35033 Rennes cedex, France.
| | - Raphaël Bourgade
- Service d'anatomie et cytologie pathologiques, CHU de Nantes, 9, quai Moncousu - plateau technique 1, 44093 Nantes cedex, France
| | - Arnaud Uguen
- Service d'anatomie et cytologie pathologiques, hôpital Morvan, CHRU de Brest, 5, avenue Foch, 29609 Brest, France; LBAI, UMR1227, CHU de Brest, université de Brest, Inserm, Brest, France
| | - Thierry Pécot
- Facility for Artificial Intelligence and Image Analysis (FAIIA), Biosit UAR 3480 CNRS-US18 Inserm, université de Rennes, 2, avenue du Professeur-Léon-Bernard, 35042 Rennes, France
| | - Sophie Prevot
- Service d'anatomie et cytologie pathologiques, hôpitaux universitaires Paris Sud, AP-HP, université Paris Saclay, 78, rue du Général-Leclerc, 94270 Le Kremlin-Bicêtre, France
| | - Catherine Guettier
- Service d'anatomie et cytologie pathologiques, hôpitaux universitaires Paris Sud, AP-HP, université Paris Saclay, 78, rue du Général-Leclerc, 94270 Le Kremlin-Bicêtre, France
| | - Janick Selves
- Département d'anatomie et cytologie pathologiques, institut universitaire du cancer Toulouse, 1, avenue Irène-Joliot-Curie, 31059 Toulouse cedex, France
| | - Philippe Bertheau
- Service d'anatomie et cytologie pathologiques, hôpital Saint-Louis, AP-HP, université de Paris, Sorbonne université, Paris, France
| | - Camille Franchet
- Service d'anatomie et cytologie pathologiques, hôpital Saint-Louis, AP-HP, université de Paris, Sorbonne université, Paris, France
| | - Magali Svrcek
- Service d'anatomie et cytologie pathologique, hôpital Saint-Antoine, 184, rue du Faubourg Saint-Antoine, 75012 Paris, France
| | - Jean-Christophe Sabourin
- Service d'anatomie et cytologie pathologique, CHU de Rouen, 1, rue de Germont, 76031 Rouen cedex, France
| | - Marie Brevet
- Biwako & Technipath, 1305, route de Lozanne, Dommartin, 69380 Auvergne-Rhône-Alpes, France
| | - Julien Calderaro
- Service d'anatomie et cytologie pathologiques, Inserm U955 Team 18, faculté de médecine, hôpital universitaire Henri-Mondor, Assistance publique-Hôpitaux de Paris, université Paris-Est-Créteil, Créteil, France
| | - Nathalie Rioux-Leclercq
- Service d'anatomie et cytologie pathologique, hôpital Pontchaillou, CHU de Rennes, université de Rennes 1, 2, rue Henri-Le-Guilloux, 35033 Rennes cedex, France
| | - Delphine Loussouarn
- Service d'anatomie et cytologie pathologiques, CHU de Nantes, 9, quai Moncousu - plateau technique 1, 44093 Nantes cedex, France
| | - Solène-Florence Kammerer-Jacquet
- Service d'anatomie et cytologie pathologique, hôpital Pontchaillou, CHU de Rennes, université de Rennes 1, 2, rue Henri-Le-Guilloux, 35033 Rennes cedex, France; Équipe IMPACT, laboratoire traitement du signal et de l'image (LTSI) Inserm, hôpital Pontchaillou, CHU de Rennes, université Rennes 1, 35033 Rennes, France
| |
Collapse
|
23
|
Salvi M, Seoni S, Campagner A, Gertych A, Acharya UR, Molinari F, Cabitza F. Explainability and uncertainty: Two sides of the same coin for enhancing the interpretability of deep learning models in healthcare. Int J Med Inform 2025; 197:105846. [PMID: 39993336 DOI: 10.1016/j.ijmedinf.2025.105846] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2024] [Revised: 02/19/2025] [Accepted: 02/19/2025] [Indexed: 02/26/2025]
Abstract
BACKGROUND The increasing use of Deep Learning (DL) in healthcare has highlighted the critical need for improved transparency and interpretability. While Explainable Artificial Intelligence (XAI) methods provide insights into model predictions, reliability cannot be guaranteed by simply relying on explanations. OBJECTIVES This position paper proposes the integration of Uncertainty Quantification (UQ) with XAI methods to improve model reliability and trustworthiness in healthcare applications. METHODS We examine state-of-the-art XAI and UQ techniques, discuss implementation challenges, and suggest solutions to combine UQ with XAI methods. We propose a framework for estimating both aleatoric and epistemic uncertainty in the XAI context, providing illustrative examples of their potential application. RESULTS Our analysis indicates that integrating UQ with XAI could significantly enhance the reliability of DL models in practice. This approach has the potential to reduce interpretation biases and over-reliance, leading to more cautious and conscious use of AI in healthcare.
Collapse
Affiliation(s)
- Massimo Salvi
- Biolab, PoliToBIOMed Lab, Department of Electronics and Telecommunications, Politecnico di Torino, Corso Duca degli Abruzzi 24, 10129 Turin, Italy.
| | - Silvia Seoni
- Biolab, PoliToBIOMed Lab, Department of Electronics and Telecommunications, Politecnico di Torino, Corso Duca degli Abruzzi 24, 10129 Turin, Italy
| | | | - Arkadiusz Gertych
- Faculty of Biomedical Engineering, Silesian University of Technology, Zabrze, Poland; Department of Surgery, Cedars-Sinai Medical Center, Los Angeles, CA, United States; Department of Pathology and Laboratory Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, United States
| | - U Rajendra Acharya
- School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, Australia; Centre for Health Research, University of Southern Queensland, Springfield, QLD 4300, Australia
| | - Filippo Molinari
- Biolab, PoliToBIOMed Lab, Department of Electronics and Telecommunications, Politecnico di Torino, Corso Duca degli Abruzzi 24, 10129 Turin, Italy
| | - Federico Cabitza
- IRCCS Ospedale Galeazzi - Sant'Ambrogio, Milan, Italy; Department of Computer Science, Systems and Communication, University of Milano-Bicocca, Milan, Italy
| |
Collapse
|
24
|
Yang T, Wang X, Jin Y, Yao X, Sun Z, Chen P, Zhou S, Zhu W, Chen W. Deep learning radiopathomics predicts targeted therapy sensitivity in EGFR-mutant lung adenocarcinoma. J Transl Med 2025; 23:482. [PMID: 40301933 PMCID: PMC12039126 DOI: 10.1186/s12967-025-06480-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2024] [Accepted: 04/11/2025] [Indexed: 05/01/2025] Open
Abstract
BACKGROUND Ttyrosine kinase inhibitors (TKIs) represent the standard first-line treatment for patients with epidermal growth factor receptor (EGFR)-mutant lung adenocarcinoma. However, not all patients with EGFR mutations respond to TKIs. This study aims to develop a deep learning radiological-pathological-clinical (DLRPC) model that integrates computed tomography (CT) images, hematoxylin and eosin (H&E)-stained aspiration biopsy samples, and clinical data to predict the response in EGFR-mutant lung adenocarcinoma patients undergoing TKIs treatment. METHODS We retrospectively analyzed data from 214 lung adenocarcinoma patients who received TKIs treatment from two medical centers between September 2013 and June 2023. The DLRPC model leverages paired CT, pathological images and clinical data, incorporating a clinical-based attention mask to further explore the cross-modality associations. To evaluate its diagnostic performance, we compared the DLRPC model against single-modality models and a decision level fusion model based on Dempster-Shafer theory. Model performances metrics, including area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), were used for evaluation. The Delong test assessed statistically significantly differences in AUC among models. RESULTS The DLRPC model demonstrated strong performance, achieving an AUC value of 0.8424. It outperformed the single-modality models (AUC = 0.6894, 0.7753, 0.8052 for CT model, pathology model and clinical model, respectively. P < 0.05). Additionally, the DLRPC model surpassed the decision level fusion model (AUC = 0.8132, P < 0.05). CONCLUSION The DLRPC model effectively predicts the response of EGFR-mutant lung adenocarcinoma patients to TKIs, providing a promising tool for personalized treatment decisions in lung cancer management.
Collapse
Affiliation(s)
- Taotao Yang
- Department of Radiology, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing, 400038, China
- Yu-Yue Pathology Scientific Research Center, Chongqing, 400039, China
| | - Xianqi Wang
- Department of Radiology, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing, 400038, China
- Yu-Yue Pathology Scientific Research Center, Chongqing, 400039, China
| | - Yuan Jin
- Zhejiang Lab, Hangzhou, 311121, China
| | - Xiaohong Yao
- Institute of Pathology and Southwest Cancer Center, Southwest Hospital, Army Medical University, (Third Military Medical University), Chongqing, 400038, China
| | - Zhiyuan Sun
- Department of Radiology, Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, China
| | - Pinzhen Chen
- Department of Radiology, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing, 400038, China
| | - Suyi Zhou
- Department of Radiology, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing, 400038, China
| | | | - Wei Chen
- Department of Radiology, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing, 400038, China.
- Yu-Yue Pathology Scientific Research Center, Chongqing, 400039, China.
| |
Collapse
|
25
|
Marra A, Morganti S, Pareja F, Campanella G, Bibeau F, Fuchs T, Loda M, Parwani A, Scarpa A, Reis-Filho JS, Curigliano G, Marchiò C, Kather JN. Artificial intelligence entering the pathology arena in oncology: current applications and future perspectives. Ann Oncol 2025:S0923-7534(25)00112-7. [PMID: 40307127 DOI: 10.1016/j.annonc.2025.03.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2024] [Revised: 02/19/2025] [Accepted: 03/07/2025] [Indexed: 05/02/2025] Open
Abstract
BACKGROUND Artificial intelligence (AI) is rapidly transforming the fields of pathology and oncology, offering novel opportunities for advancing diagnosis, prognosis, and treatment of cancer. METHODS Through a systematic review-based approach, the representatives from the European Society for Medical Oncology (ESMO) Precision Oncology Working Group (POWG) and international experts identified studies in pathology and oncology that applied AI-based algorithms for tumour diagnosis, molecular biomarker detection, and cancer prognosis assessment. These findings were synthesised to provide a comprehensive overview of current AI applications and future directions in cancer pathology. RESULTS The integration of AI tools in digital pathology is markedly improving the accuracy and efficiency of image analysis, allowing for automated tumour detection and classification, identification of prognostic molecular biomarkers, and prediction of treatment response and patient outcomes. Several barriers for the adoption of AI in clinical workflows, such as data availability, explainability, and regulatory considerations, still persist. There are currently no prognostic or predictive AI-based biomarkers supported by level IA or IB evidence. The ongoing advancements in AI algorithms, particularly foundation models, generalist models and transformer-based deep learning, offer immense promise for the future of cancer research and care. AI is also facilitating the integration of multi-omics data, leading to more precise patient stratification and personalised treatment strategies. CONCLUSIONS The application of AI in pathology is poised to not only enhance the accuracy and efficiency of cancer diagnosis and prognosis but also facilitate the development of personalised treatment strategies. Although barriers to implementation remain, ongoing research and development in this field coupled with addressing ethical and regulatory considerations will likely lead to a future where AI plays an integral role in cancer management and precision medicine. The continued evolution and adoption of AI in pathology and oncology are anticipated to reshape the landscape of cancer care, heralding a new era of precision medicine and improved patient outcomes.
Collapse
Affiliation(s)
- A Marra
- Division of Early Drug Development for Innovative Therapies, European Institute of Oncology IRCCS, Milan, Italy
| | - S Morganti
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, USA; Department of Medicine, Harvard Medical School, Boston, USA; Gerstner Center for Cancer Diagnostics, Broad Institute of MIT and Harvard, Boston, USA
| | - F Pareja
- Department of Pathology and Laboratory Medicine, Memorial Sloan Kettering Cancer Center, New York, USA
| | - G Campanella
- Hasso Plattner Institute for Digital Health, Mount Sinai Medical School, New York, USA; Department of AI and Human Health, Icahn School of Medicine at Mount Sinai, New York, USA
| | - F Bibeau
- Department of Pathology, University Hospital of Besançon, Besancon, France
| | - T Fuchs
- Hasso Plattner Institute for Digital Health, Mount Sinai Medical School, New York, USA; Department of AI and Human Health, Icahn School of Medicine at Mount Sinai, New York, USA
| | - M Loda
- Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, USA; Nuffield Department of Surgical Sciences, University of Oxford, Oxford, UK; Department of Oncologic Pathology, Dana-Farber Cancer Institute and Harvard Medical School, Boston, USA
| | - A Parwani
- Department of Pathology, Wexner Medical Center, Ohio State University, Columbus, USA
| | - A Scarpa
- Department of Diagnostics and Public Health, Section of Pathology, University and Hospital Trust of Verona, Verona, Italy; ARC-Net Research Center, University of Verona, Verona, Italy
| | - J S Reis-Filho
- Department of Pathology and Laboratory Medicine, Memorial Sloan Kettering Cancer Center, New York, USA
| | - G Curigliano
- Division of Early Drug Development for Innovative Therapies, European Institute of Oncology IRCCS, Milan, Italy; Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
| | - C Marchiò
- Candiolo Cancer Institute, FPO IRCCS, Candiolo, Italy; Department of Medical Sciences, University of Turin, Turin, Italy
| | - J N Kather
- Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden, Dresden, Germany; Department of Medicine I, University Hospital and Faculty of Medicine Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany; Medical Oncology, National Center for Tumor Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany.
| |
Collapse
|
26
|
Dang C, Qi Z, Xu T, Gu M, Chen J, Wu J, Lin Y, Qi X. Deep Learning-Powered Whole Slide Image Analysis in Cancer Pathology. J Transl Med 2025; 105:104186. [PMID: 40306572 DOI: 10.1016/j.labinv.2025.104186] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2024] [Revised: 03/05/2025] [Accepted: 04/22/2025] [Indexed: 05/02/2025] Open
Abstract
Pathology is the cornerstone of modern cancer care. With the advancement of precision oncology, the demand for histopathologic diagnosis and stratification of patients is increasing as personalized cancer therapy relies on accurate biomarker assessment. Recently, rapid development of whole slide imaging technology has enabled digitalization of traditional histologic slides at high resolution, holding promise to improve both the precision and efficiency of histopathologic evaluation. In particular, deep learning approaches, such as Convolutional Neural Network, Graph Convolutional Network, and Transformer, have shown great promise in enhancing the sensitivity and accuracy of whole slide image (WSI) analysis in cancer pathology because of their ability to handle high-dimensional and complex image data. The integration of deep learning models with WSIs enables us to explore and mine morphologic features beyond the visual perception of pathologists, which can help automate clinical diagnosis, assess histopathologic grade, predict clinical outcomes, and even discover novel morphologic biomarkers. In this review, we present a comprehensive framework for incorporating deep learning with WSIs, highlighting how deep learning-driven WSI analysis advances clinical tasks in cancer care. Furthermore, we critically discuss the opportunities and challenges of translating deep learning-based digital pathology into clinical practice, which should be considered to support personalized treatment of cancer patients.
Collapse
Affiliation(s)
- Chengrun Dang
- School of Chemistry and Life Sciences, Suzhou University of Science and Technology, Suzhou, China
| | - Zhuang Qi
- School of Software, Shandong University, Jinan, China
| | - Tao Xu
- School of Chemistry and Life Sciences, Suzhou University of Science and Technology, Suzhou, China
| | - Mingkai Gu
- School of Chemistry and Life Sciences, Suzhou University of Science and Technology, Suzhou, China
| | - Jiajia Chen
- School of Chemistry and Life Sciences, Suzhou University of Science and Technology, Suzhou, China
| | - Jie Wu
- Department of Oncology, The First Affiliated Hospital of Soochow University, Suzhou, China.
| | - Yuxin Lin
- Department of Urology, The First Affiliated Hospital of Soochow University, Suzhou, China.
| | - Xin Qi
- School of Chemistry and Life Sciences, Suzhou University of Science and Technology, Suzhou, China.
| |
Collapse
|
27
|
Hernandez N, Carrillo-Perez F, Ortuño FM, Rojas I, Valenzuela O. Understanding the Impact of Deep Learning Model Parameters on Breast Cancer Histopathological Classification Using ANOVA. Cancers (Basel) 2025; 17:1425. [PMID: 40361352 PMCID: PMC12071027 DOI: 10.3390/cancers17091425] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2025] [Revised: 04/15/2025] [Accepted: 04/22/2025] [Indexed: 05/15/2025] Open
Abstract
Artificial intelligence (AI) has the potential to enhance clinical practice, particularly in the early and accurate diagnosis of diseases like breast cancer. However, for AI models to be effective in medical settings, they must not only be accurate but also interpretable and reliable. This study aims to analyze how variations in different model parameters affect the performance of a weakly supervised deep learning model used for breast cancer detection. METHODS In this work, we apply Analysis of Variance (ANOVA) to investigate how changes in different parameters impact the performance of the deep learning model. The model is built using attention mechanisms, which both perform classification and identify the most relevant regions in medical images, improving the interpretability of the model. ANOVA is used to determine the significance of each parameter in influencing the model's outcome, offering insights into the specific factors that drive its decision-making. RESULTS Our analysis reveals that certain parameters significantly affect the model's performance, with some configurations showing higher sensitivity and specificity than others. By using ANOVA, we identify the key factors that influence the model's ability to classify images correctly. This approach allows for a deeper understanding of how the model works and highlights areas where improvements can be made to enhance its reliability in clinical practice. CONCLUSIONS The study demonstrates that applying ANOVA to deep learning models in medical applications provides valuable insights into the parameters that influence performance. This analysis helps make AI models more interpretable and trustworthy, which is crucial for their adoption in real-world medical environments like breast cancer detection. Understanding these factors enables the development of more transparent and efficient AI tools for clinical use.
Collapse
Affiliation(s)
- Nerea Hernandez
- Department of Computer Engineering, Automation and Robotics, University of Granada, 18071 Granada, Spain
| | | | | | | | | |
Collapse
|
28
|
Adam KM, Ali EW, Elangeeb ME, Abuagla HA, Elamin BK, Ahmed EM, Edris AM, Ahmed AAEM, Eltieb EI. Intelligent Care: A Scientometric Analysis of Artificial Intelligence in Precision Medicine. Med Sci (Basel) 2025; 13:44. [PMID: 40265391 PMCID: PMC12015873 DOI: 10.3390/medsci13020044] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2025] [Revised: 03/24/2025] [Accepted: 04/17/2025] [Indexed: 04/24/2025] Open
Abstract
The integration of advanced computational methods into precision medicine represents a transformative advancement in healthcare, enabling highly personalized treatment strategies based on individual genetic, environmental, and lifestyle factors. These methodologies have significantly enhanced disease diagnostics, genomic analysis, and drug discovery. However, rapid expansion in this field has resulted in fragmented understandings of its evolution and persistent knowledge gaps. This study employs a scientometric approach to systematically map the research landscape, identify key contributors, and highlight emerging trends in precision medicine. Methods: A scientometric analysis was conducted using data retrieved from the Scopus database, covering publications from 2019 to 2024. Tools such as VOSviewer and R-bibliometrix package (version 4.3.0) were used to perform co-authorship analysis, co-citation mapping, and keyword evolution tracking. The study examined annual publication growth, citation impact, research productivity by country and institution, and thematic clustering to identify core research areas. Results: The analysis identified 4574 relevant publications, collectively amassing 70,474 citations. A rapid growth trajectory was observed, with a 34.3% increase in publications in 2024 alone. The United States, China, and Germany emerged as the top contributors, with Harvard Medical School, the Mayo Clinic, and Sichuan University leading in institutional productivity. Co-citation and keyword analysis revealed three primary research themes: diagnostics and medical imaging, genomic and multi-omics data integration, and personalized treatment strategies. Recent trends indicate a shift toward enhanced clinical decision support systems and precision drug discovery. Conclusions: Advanced computational methods are revolutionizing precision medicine, spurring increased global research collaboration and rapidly evolving methodologies. This study provides a comprehensive knowledge framework, highlighting key developments and future directions. The insights derived can inform policy decisions, funding allocations, and interdisciplinary collaborations, driving further advancements in healthcare solutions.
Collapse
Affiliation(s)
- Khalid M. Adam
- Department of Medical Laboratory Sciences, College of Applied Medical Sciences, University of Bisha, P.O. Box 255, Bisha 67714, Saudi Arabia; (E.W.A.); (M.E.E.); (H.A.A.); (E.M.A.); (A.M.E.); (A.A.E.M.A.); (E.I.E.)
| | - Elshazali W. Ali
- Department of Medical Laboratory Sciences, College of Applied Medical Sciences, University of Bisha, P.O. Box 255, Bisha 67714, Saudi Arabia; (E.W.A.); (M.E.E.); (H.A.A.); (E.M.A.); (A.M.E.); (A.A.E.M.A.); (E.I.E.)
| | - Mohamed E. Elangeeb
- Department of Medical Laboratory Sciences, College of Applied Medical Sciences, University of Bisha, P.O. Box 255, Bisha 67714, Saudi Arabia; (E.W.A.); (M.E.E.); (H.A.A.); (E.M.A.); (A.M.E.); (A.A.E.M.A.); (E.I.E.)
| | - Hytham A. Abuagla
- Department of Medical Laboratory Sciences, College of Applied Medical Sciences, University of Bisha, P.O. Box 255, Bisha 67714, Saudi Arabia; (E.W.A.); (M.E.E.); (H.A.A.); (E.M.A.); (A.M.E.); (A.A.E.M.A.); (E.I.E.)
| | - Bahaeldin K. Elamin
- Department of Microbiology and Clinical Parasitology, College of Medicine, University of Bisha, P.O. Box 1290, Bisha 67714, Saudi Arabia;
| | - Elsadig M. Ahmed
- Department of Medical Laboratory Sciences, College of Applied Medical Sciences, University of Bisha, P.O. Box 255, Bisha 67714, Saudi Arabia; (E.W.A.); (M.E.E.); (H.A.A.); (E.M.A.); (A.M.E.); (A.A.E.M.A.); (E.I.E.)
| | - Ali M. Edris
- Department of Medical Laboratory Sciences, College of Applied Medical Sciences, University of Bisha, P.O. Box 255, Bisha 67714, Saudi Arabia; (E.W.A.); (M.E.E.); (H.A.A.); (E.M.A.); (A.M.E.); (A.A.E.M.A.); (E.I.E.)
| | - Abubakr A. Elamin Mohamed Ahmed
- Department of Medical Laboratory Sciences, College of Applied Medical Sciences, University of Bisha, P.O. Box 255, Bisha 67714, Saudi Arabia; (E.W.A.); (M.E.E.); (H.A.A.); (E.M.A.); (A.M.E.); (A.A.E.M.A.); (E.I.E.)
| | - Elmoiz I. Eltieb
- Department of Medical Laboratory Sciences, College of Applied Medical Sciences, University of Bisha, P.O. Box 255, Bisha 67714, Saudi Arabia; (E.W.A.); (M.E.E.); (H.A.A.); (E.M.A.); (A.M.E.); (A.A.E.M.A.); (E.I.E.)
| |
Collapse
|
29
|
Gonzalez AD, Wadop YN, Danner B, Clarke KM, Dopler MB, Ghaseminejad-Bandpey A, Babu S, Parker-Garza J, Corbett C, Alhneif M, Keating M, Bieniek KF, Maestre GE, Seshadri S, Etemadmoghadam S, Fongang B, Flanagan ME. Digital pathology in tau research: A comparison of QuPath and HALO. J Neuropathol Exp Neurol 2025:nlaf026. [PMID: 40238207 DOI: 10.1093/jnen/nlaf026] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/18/2025] Open
Abstract
The application of digital pathology tools has expanded in recent years, but non-neoplastic human brain tissue presents unique challenges due to its complexity. This study evaluated HALO and QuPath tau quantification performance in the hippocampus and mid-frontal gyrus across various tauopathies. Percent positivity emerged as the most reliable measure, showing strong correlations with Braak stages and CERAD scores, outperforming object and optical densities. QuPath demonstrated superior correlations with Braak stages, while HALO excelled in aligning with CERAD scoring. However, HALO's optical density was less consistent. Paired t-tests revealed significant differences in object and optical densities between platforms, though percent positivity was consistent across both. QuPath's threshold-based object density showed similar agreement with manual counts compared to HALO's AI-dependent approach (all ρ > 0.70). Reanalysis of QuPath further improved its agreement with manual measurements and correlations with Braak and CERAD scores (all ρ > 0.70). HALO offers a user-friendly interface and excels in certain metrics but is hindered by frequent software malfunctions and more limited flexibility. In contrast, QuPath's customizable workflows and superior performance in Braak staging make it more suitable for advanced and larger-scale analyses. Overall, our study highlights the strengths and limitations of these platforms, helping guide their application in neuropathology.
Collapse
Affiliation(s)
- Angelique D Gonzalez
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| | - Yannick N Wadop
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| | - Benjamin Danner
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| | - Kyra M Clarke
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| | - Matthew B Dopler
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| | - Ali Ghaseminejad-Bandpey
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| | - Sahana Babu
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| | - Julie Parker-Garza
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| | - Cole Corbett
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| | - Mohammad Alhneif
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| | - Mallory Keating
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| | - Kevin F Bieniek
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
- Department of Pathology and Laboratory Medicine, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| | - Gladys E Maestre
- Institute of Neurosciences, School of Medicine, University of Texas Rio Grande Valley, Harlingen, TX, United States
- Rio Grande Valley Alzheimer's Disease Resource Center for Minority Aging Research (RGV AD-RCMAR), University of Texas Rio Grande Valley, Brownsville, TX, United States
- Department of Human Genetics, School of Medicine, University of Texas Rio Grande Valley, Brownsville, TX, United States
| | - Sudha Seshadri
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| | - Shahroo Etemadmoghadam
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| | - Bernard Fongang
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| | - Margaret E Flanagan
- Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
- Department of Pathology and Laboratory Medicine, University of Texas Health Science Center at San Antonio, San Antonio, TX, United States
| |
Collapse
|
30
|
Shin Y, Lee M, Lee Y, Kim K, Kim T. Artificial Intelligence-Powered Quality Assurance: Transforming Diagnostics, Surgery, and Patient Care-Innovations, Limitations, and Future Directions. Life (Basel) 2025; 15:654. [PMID: 40283208 PMCID: PMC12028931 DOI: 10.3390/life15040654] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2025] [Revised: 04/09/2025] [Accepted: 04/14/2025] [Indexed: 04/29/2025] Open
Abstract
Artificial intelligence is rapidly transforming quality assurance in healthcare, driving advancements in diagnostics, surgery, and patient care. This review presents a comprehensive analysis of artificial intelligence integration-particularly convolutional and recurrent neural networks-across key clinical domains, significantly enhancing diagnostic accuracy, surgical performance, and pathology evaluation. Artificial intelligence-based approaches have demonstrated clear superiority over conventional methods: convolutional neural networks achieved 91.56% accuracy in scanner fault detection, surpassing manual inspections; endoscopic lesion detection sensitivity rose from 2.3% to 6.1% with artificial intelligence assistance; and gastric cancer invasion depth classification reached 89.16% accuracy, outperforming human endoscopists by 17.25%. In pathology, artificial intelligence achieved 93.2% accuracy in identifying out-of-focus regions and an F1 score of 0.94 in lymphocyte quantification, promoting faster and more reliable diagnostics. Similarly, artificial intelligence improved surgical workflow recognition with over 81% accuracy and exceeded 95% accuracy in skill assessment classification. Beyond traditional diagnostics and surgical support, AI-powered wearable sensors, drug delivery systems, and biointegrated devices are advancing personalized treatment by optimizing physiological monitoring, automating care protocols, and enhancing therapeutic precision. Despite these achievements, challenges remain in areas such as data standardization, ethical governance, and model generalizability. Overall, the findings underscore artificial intelligence's potential to outperform traditional techniques across multiple parameters, emphasizing the need for continued development, rigorous clinical validation, and interdisciplinary collaboration to fully realize its role in precision medicine and patient safety.
Collapse
Affiliation(s)
- Yoojin Shin
- College of Medicine, The Catholic University of Korea, 222 Banpo-Daero, Seocho-gu, Seoul 06591, Republic of Korea; (Y.S.); (M.L.); (Y.L.)
| | - Mingyu Lee
- College of Medicine, The Catholic University of Korea, 222 Banpo-Daero, Seocho-gu, Seoul 06591, Republic of Korea; (Y.S.); (M.L.); (Y.L.)
| | - Yoonji Lee
- College of Medicine, The Catholic University of Korea, 222 Banpo-Daero, Seocho-gu, Seoul 06591, Republic of Korea; (Y.S.); (M.L.); (Y.L.)
| | - Kyuri Kim
- College of Medicine, Ewha Womans University, 25 Magokdong-ro 2-gil, Gangseo-gu, Seoul 07804, Republic of Korea;
| | - Taejung Kim
- Department of Hospital Pathology, Yeouido St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, 10, 63-ro, Yeongdeungpo-gu, Seoul 07345, Republic of Korea
| |
Collapse
|
31
|
Cao H, Wu X, Shi H, Chu B, He Y, Wang H, Dong F. AI-assisted SERS imaging method for label-free and rapid discrimination of clinical lymphoma. J Nanobiotechnology 2025; 23:295. [PMID: 40241186 PMCID: PMC12001690 DOI: 10.1186/s12951-025-03339-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/17/2024] [Accepted: 03/18/2025] [Indexed: 04/18/2025] Open
Abstract
BACKGROUND Lymphoma is a malignant tumor of the immune system and its incidence is increasing year after year, causing a major threat to people's health. Conventional diagnosis of lymphoma basically depends on histological images consuming long-time and tedious manipulations (e.g., 7-15 days) and large-field view (e.g., > 1000 × 1000 μm2). Artificial intelligence has recently revolutionized cancer diagnosis by training pathological image databases via deep learning. Current approaches, however, remain dependent on analyzing wide-field pathological images to detect distinct nuclear, cytologic, and histomorphologic traits for diagnostic categorization, limiting their applicability to minimally invasive lesion. RESULTS Herein, we develop a molecular imaging strategy for minimally invasive lymphoma diagnosis. By spreading lymphoma tissue sections tightly on a surface-enhanced Raman scattering (SERS) chip, label-free images of DNA double strand breaks (DSBs) in 30 × 30 μm2 tissue sections could be achieved in ~ 15 min. To establish a proof of concept, the Raman image datasets collected from clinical samples of normal lymphatic tissues and non-Hodgkin's lymphoma (NHL) tissues were well organized and trained in a deep convolutional neural network model, finally achieving a recognition rate of ~ 91.7 ± 2.1%. CONCLUSIONS The molecular imaging strategy for minimally invasive lymphoma diagnosis that can achieve a recognition rate of ~ 91.7 ± 2.1%. We anticipate that these results will catalyze the development of a series of histological SERS-AI technologies for diagnosing various diseases, including other types of cancer. In this work, we present a reliable tool to facilitate clinicians in the diagnosis of lymphoma.
Collapse
Affiliation(s)
- Haiting Cao
- Suzhou Key Laboratory of Nanotechnology and Biomedicine, Institute of Functional Nano & Soft Materials (FUNSOM), and Collaborative Innovation Center of Suzhou Nano Science and Technology (NANO-CIC), Soochow University, Suzhou, 215123, Jiangsu, China
| | - Xiaofeng Wu
- Department of Ultrasound, The First Affiliated Hospital of Soochow University, Suzhou, 215031, Jiangsu, China
| | - Huayi Shi
- Suzhou Key Laboratory of Nanotechnology and Biomedicine, Institute of Functional Nano & Soft Materials (FUNSOM), and Collaborative Innovation Center of Suzhou Nano Science and Technology (NANO-CIC), Soochow University, Suzhou, 215123, Jiangsu, China
| | - Binbin Chu
- Suzhou Key Laboratory of Nanotechnology and Biomedicine, Institute of Functional Nano & Soft Materials (FUNSOM), and Collaborative Innovation Center of Suzhou Nano Science and Technology (NANO-CIC), Soochow University, Suzhou, 215123, Jiangsu, China.
| | - Yao He
- Suzhou Key Laboratory of Nanotechnology and Biomedicine, Institute of Functional Nano & Soft Materials (FUNSOM), and Collaborative Innovation Center of Suzhou Nano Science and Technology (NANO-CIC), Soochow University, Suzhou, 215123, Jiangsu, China.
- Macao Translational Medicine Center, Macau University of Science and Technology, Taipa, 999078, Macau SAR, China.
- Macao Institute of Materials Science and Engineering, Macau University of Science and Technology, Taipa, 999078, Macau SAR, China.
| | - Houyu Wang
- Suzhou Key Laboratory of Nanotechnology and Biomedicine, Institute of Functional Nano & Soft Materials (FUNSOM), and Collaborative Innovation Center of Suzhou Nano Science and Technology (NANO-CIC), Soochow University, Suzhou, 215123, Jiangsu, China.
| | - Fenglin Dong
- Department of Ultrasound, The First Affiliated Hospital of Soochow University, Suzhou, 215031, Jiangsu, China.
| |
Collapse
|
32
|
Casals-Farre O, Baskaran R, Singh A, Kaur H, Ul Hoque T, de Almeida A, Coffey M, Hassoulas A. Assessing ChatGPT 4.0's Capabilities in the United Kingdom Medical Licensing Examination (UKMLA): A Robust Categorical Analysis. Sci Rep 2025; 15:13031. [PMID: 40234701 PMCID: PMC12000555 DOI: 10.1038/s41598-025-97327-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2024] [Accepted: 04/03/2025] [Indexed: 04/17/2025] Open
Abstract
Advances in the various applications of artificial intelligence will have important implications for medical training and practice. The advances in ChatGPT-4 alongside the introduction of the medical licensing assessment (MLA) provide an opportunity to compare GPT-4's medical competence against the expected level of a United Kingdom junior doctor and discuss its potential in clinical practice. Using 191 freely available questions in MLA style, we assessed GPT-4's accuracy with and without offering multiple-choice options. We compared single and multi-step questions, which targeted different points in the clinical process, from diagnosis to management. A chi-squared test was used to assess statistical significance. GPT-4 scored 86.3% and 89.6% in papers one-and-two respectively. Without the multiple-choice options, GPT's performance was 61.5% and 74.7% in papers one-and-two respectively. There was no significant difference between single and multistep questions, but GPT-4 answered 'management' questions significantly worse than 'diagnosis' questions with no multiple-choice options (p = 0.015). GPT-4's accuracy across categories and question structures suggest that LLMs are competently able to process clinical scenarios but remain incapable of understanding these clinical scenarios. Large-Language-Models incorporated into practice alongside a trained practitioner may balance risk and benefit as the necessary robust testing on evolving tools is conducted.
Collapse
Affiliation(s)
- Octavi Casals-Farre
- Centre for Medical Education (C4ME), School of Medicine, Cardiff University, Heath Park Campus, Cardiff, CF14 4YS, United Kingdom
- OSCEazy Research Collaborative, Heath Park Campus, Cardiff, CF14 4YS, United Kingdom
| | - Ravanth Baskaran
- Centre for Medical Education (C4ME), School of Medicine, Cardiff University, Heath Park Campus, Cardiff, CF14 4YS, United Kingdom
- OSCEazy Research Collaborative, Heath Park Campus, Cardiff, CF14 4YS, United Kingdom
- Department of Urology, Southampton General Hospital NHS Foundation Trust, Tremona Road, Southampton, SO16 6YD, United Kingdom
| | - Aditya Singh
- Centre for Medical Education (C4ME), School of Medicine, Cardiff University, Heath Park Campus, Cardiff, CF14 4YS, United Kingdom
- OSCEazy Research Collaborative, Heath Park Campus, Cardiff, CF14 4YS, United Kingdom
| | - Harmeena Kaur
- University of Southampton School of Medicine, 12 University Rd, Southampton, SO17 1BJ, United Kingdom
- OSCEazy Research Collaborative, Heath Park Campus, Cardiff, CF14 4YS, United Kingdom
| | - Tazim Ul Hoque
- Keele University School of Medicine, Keele University, University Road, Staffordshire, ST5 5BG, United Kingdom
- OSCEazy Research Collaborative, Heath Park Campus, Cardiff, CF14 4YS, United Kingdom
| | - Andreia de Almeida
- Centre for Medical Education (C4ME), School of Medicine, Cardiff University, Heath Park Campus, Cardiff, CF14 4YS, United Kingdom
- HIVE Digital & Teaching Innovation Unit, University Hospital of Wales, 2nd Floor Office F-24 Heath Park, Cardiff, CF14 4XW, United Kingdom
| | - Marcus Coffey
- Centre for Medical Education (C4ME), School of Medicine, Cardiff University, Heath Park Campus, Cardiff, CF14 4YS, United Kingdom
- HIVE Digital & Teaching Innovation Unit, University Hospital of Wales, 2nd Floor Office F-24 Heath Park, Cardiff, CF14 4XW, United Kingdom
| | - Athanasios Hassoulas
- Centre for Medical Education (C4ME), School of Medicine, Cardiff University, Heath Park Campus, Cardiff, CF14 4YS, United Kingdom.
- HIVE Digital & Teaching Innovation Unit, University Hospital of Wales, 2nd Floor Office F-24 Heath Park, Cardiff, CF14 4XW, United Kingdom.
| |
Collapse
|
33
|
Da Z, Yang H, Zhaxi B, Sun K, Bai G, Wang C, Wang F, Pan W, Du R. Multiple instance learning-based prediction of programmed death-ligand 1 (PD-L1) expression from hematoxylin and eosin (H&E)-stained histopathological images in breast cancer. PeerJ 2025; 13:e19201. [PMID: 40256728 PMCID: PMC12007500 DOI: 10.7717/peerj.19201] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2024] [Accepted: 03/03/2025] [Indexed: 04/22/2025] Open
Abstract
Programmed death-ligand 1 (PD-L1) is an important biomarker increasingly used as a predictive marker in breast cancer immunotherapy. Immunohistochemical quantification remains the standard method for assessment. However, it presents challenges related to time, cost, and reliability. Hematoxylin and eosin (H&E) staining is a routine method in cancer pathology, known for its accessibility and consistently reliability. Deep learning has shown the potential in predicting biomarkers in cancer histopathology. This study employs a weakly supervised multiple instance learning (MIL) approach to predict PD-L1 expression from H&E-stained images using deep learning techniques. In the internal test set, the TransMIL method achieved an area under the curve (AUC) of 0.833, and in an independent external test set, it achieved an AUC of 0.799. Additionally, since RNA sequencing results indicate a threshold that allows for the separation of H&E pathology images, we further validated our approach using the public TCGA-TNBC dataset, achieving an AUC of 0.721. These findings demonstrates that the Transformer-based TransMIL model can effectively capture highly heterogeneous features within the MIL framework, exhibiting strong cross-center generalization capabilities. Our study highlights that appropriate deep learning techniques can enable effective PD-L1 prediction even with limited data, and across diverse regions and centers. This not only underscores the significant potential of deep learning in pathological artificial intelligence (AI) but also provides valuable insights for the rational and efficient allocation of medical resources.
Collapse
Affiliation(s)
- Zhen Da
- Department of Pathology, People’s Hospital of Xizang Autonomous Region, Lhasa, Xizang, China
- Department of Pathology, Guangdong Women and Children Hospital, Guangzhou, Guangdong, China
| | - Heng Yang
- Kunyuan Fangqing Medical Technology Co., LTD, Guangzhou, Guangdong, China
- Jinfeng Laboratory, Chongqing, China
| | - Bianba Zhaxi
- Department of General Surgery, People’s Hospital of Xizang Autonomous Region, Lhasa, Xizang, China
| | - Kaixiang Sun
- Kunyuan Fangqing Medical Technology Co., LTD, Guangzhou, Guangdong, China
- Jinfeng Laboratory, Chongqing, China
| | - Guohui Bai
- Department of General Surgery, People’s Hospital of Xizang Autonomous Region, Lhasa, Xizang, China
| | - Chao Wang
- Department of Pathology, Nanfang Hospital and Basic Medical College, Southern Medical University, Guangzhou, Guangdong, China
| | - Feiyan Wang
- Kunyuan Fangqing Medical Technology Co., LTD, Guangzhou, Guangdong, China
- Jinfeng Laboratory, Chongqing, China
| | - Weijun Pan
- Jinfeng Laboratory, Chongqing, China
- Department of Pathology, Nanfang Hospital and Basic Medical College, Southern Medical University, Guangzhou, Guangdong, China
| | - Rui Du
- Department of Pathology, People’s Hospital of Xizang Autonomous Region, Lhasa, Xizang, China
- Department of Pathology, Guangdong Women and Children Hospital, Guangzhou, Guangdong, China
| |
Collapse
|
34
|
Barroso VM, Weng Z, Glamann L, Bauer M, Wickenhauser C, Zander T, Büttner R, Quaas A, Tolkach Y. Artificial Intelligence-Based Single-Cell Analysis as a Next-Generation Histologic Grading Approach in Colorectal Cancer: Prognostic Role and Tumor Biology Assessment. Mod Pathol 2025; 38:100771. [PMID: 40222652 DOI: 10.1016/j.modpat.2025.100771] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2024] [Revised: 03/16/2025] [Accepted: 04/01/2025] [Indexed: 04/15/2025]
Abstract
The management of colorectal carcinoma (CRC) relies on pathological interpretation. Digital pathology approaches allow for development of new potent artificial intelligence-based prognostic parameters. The study aimed to develop an artificial intelligence-based image analysis platform allowing fully automatized, quantitative, and explainable tumor microenvironment analysis and extraction of prognostic information from hematoxylin and eosin-stained whole-slide images of CRC patients. Three well--characterized, multi-institutional patient cohorts were included (patient n = 1438, whole-slide image n > 2400). The developed image analysis platform implements quality control and established algorithms to segment tissue and detect cell types. It enabled systematic analysis of immune infiltrate, assessing its prognostic relevance, intratumoral heterogeneity, and biological concepts across multiple survival end points. Analyzing single-cell types and their combinations reveals independent, prognostic parameters, highlighting significant intratumoral heterogeneity, especially in the biopsy setting, which must be accounted for. A key morphologic concept related to tumor control by the immune system is described, resulting in a capable, independent prognostic parameter (tumor "out of control"). Our findings have direct clinical implications and can be used as a foundation for updating the existing CRC grading systems.
Collapse
Affiliation(s)
- Vincenzo Mitchell Barroso
- Medical Faculty, University of Cologne, Cologne, Germany; Insitute of Pathology, University Hospital Cologne, Cologne, Germany
| | - Zhilong Weng
- Insitute of Pathology, University Hospital Cologne, Cologne, Germany
| | - Lennert Glamann
- Institute of Pathology, University Hospital Halle, Martin Luther University Halle-Wittenberg, Halle (Salle), Germany
| | - Marcus Bauer
- Institute of Pathology, University Hospital Halle, Martin Luther University Halle-Wittenberg, Halle (Salle), Germany
| | - Claudia Wickenhauser
- Institute of Pathology, University Hospital Halle, Martin Luther University Halle-Wittenberg, Halle (Salle), Germany
| | - Thomas Zander
- Clinic of Internal Medicine, Oncology, University Hospital Cologne, Cologne, Germany
| | - Reinhard Büttner
- Insitute of Pathology, University Hospital Cologne, Cologne, Germany
| | - Alexander Quaas
- Insitute of Pathology, University Hospital Cologne, Cologne, Germany
| | - Yuri Tolkach
- Insitute of Pathology, University Hospital Cologne, Cologne, Germany.
| |
Collapse
|
35
|
Markey M, Kim J, Goldstein Z, Gerardin Y, Brosnan-Cashman J, Javed SA, Juyal D, Pagidela H, Yu L, Rahsepar B, Abel J, Hennek S, Khosla A, Taylor-Weiner A, Parmar C. Spatial Mapping of Gene Signatures in Hematoxylin and Eosin-Stained Images: A Proof of Concept for Interpretable Predictions Using Additive Multiple Instance Learning. Mod Pathol 2025; 38:100772. [PMID: 40222651 DOI: 10.1016/j.modpat.2025.100772] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2024] [Revised: 03/06/2025] [Accepted: 04/06/2025] [Indexed: 04/15/2025]
Abstract
The relative abundance of cancer-associated fibroblast (CAF) subtypes influences a tumor's response to treatment, especially immunotherapy. However, the gene expression signatures associated with these CAF subtypes have yet to realize their potential as clinical biomarkers. Here, we describe an interpretable machine learning approach, additive multiple instance learning (aMIL), to predict bulk gene expression signatures from hematoxylin and eosin-stained whole-slide images, focusing on an immunosuppressive LRRC15+ CAF-enriched TGFβ-CAF signature. aMIL models accurately predicted TGFβ-CAF across various cancer types. Tissue regions contributing most highly to slide-level predictions of TGFβ-CAF were evaluated by machine learning models characterizing spatial distributions of diverse cell and tissue types, stromal subtypes, and nuclear morphology. In breast cancer, regions contributing most to TGFβ-CAF-high predictions ("excitatory") were localized to cancer stroma with high fibroblast density and mature collagen fibers. Regions contributing most to TGFβ-CAF-low predictions ("inhibitory") were localized to cancer epithelium and densely inflamed stroma. Fibroblast and lymphocyte nuclear morphology also differed between excitatory and inhibitory regions. Thus, aMIL enables a data-driven link between histologic features and transcription, offering biological interpretability beyond typical black-box models.
Collapse
|
36
|
Aggarwal A, Bharadwaj S, Corredor G, Pathak T, Badve S, Madabhushi A. Artificial intelligence in digital pathology - time for a reality check. Nat Rev Clin Oncol 2025; 22:283-291. [PMID: 39934323 DOI: 10.1038/s41571-025-00991-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 01/24/2025] [Indexed: 02/13/2025]
Abstract
The past decade has seen the introduction of artificial intelligence (AI)-based approaches aimed at optimizing several workflows across many medical specialties. In clinical oncology, the most promising applications include those involving image analysis, such as digital pathology. In this Perspective, we provide a comprehensive examination of the developments in AI in digital pathology between 2019 and 2024. We evaluate the current landscape from the lens of technological innovations, regulatory trends, deployment and implementation, reimbursement and commercial implications. We assess the technological advances that have driven improvements in AI, enabling more robust and scalable solutions for digital pathology. We also examine regulatory developments, in particular those affecting in-house devices and laboratory-developed tests, which are shaping the landscape of AI-based tools in digital pathology. Finally, we discuss the role of reimbursement frameworks and commercial investment in the clinical adoption of AI-based technologies. In this Perspective, we highlight both the progress and challenges in AI-driven digital pathology over the past 5 years, outlining the path forward for its adoption into routine practice in clinical oncology.
Collapse
Affiliation(s)
- Arpit Aggarwal
- Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA
| | - Satvika Bharadwaj
- Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA
| | - Germán Corredor
- Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA
- Atlanta Veterans Affairs Medical Center, Atlanta, GA, USA
| | - Tilak Pathak
- Department of Biomedical Engineering, Emory University, Atlanta, GA, USA
| | - Sunil Badve
- Department of Pathology and Laboratory Medicine, Emory University School of Medicine, Atlanta, GA, USA
| | - Anant Madabhushi
- Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA.
- Atlanta Veterans Affairs Medical Center, Atlanta, GA, USA.
| |
Collapse
|
37
|
Cheng C, Li B, Li J, Wang Y, Xiao H, Lian X, Chen L, Wang J, Wang H, Qin S, Yu L, Wu T, Peng S, Tan W, Ye Q, Chen W, Jiang X. Multi-stain deep learning prediction model of treatment response in lupus nephritis based on renal histopathology. Kidney Int 2025; 107:714-727. [PMID: 39733792 DOI: 10.1016/j.kint.2024.12.007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2024] [Revised: 10/03/2024] [Accepted: 12/16/2024] [Indexed: 12/31/2024]
Abstract
The response of the kidney after induction treatment is one of the determinants of prognosis in lupus nephritis, but effective predictive tools are lacking. Here, we sought to apply deep learning approaches on kidney biopsies for treatment response prediction in lupus nephritis. Patients who received cyclophosphamide or mycophenolate mofetil as induction treatment were included, and the primary outcome was 12-month treatment response, complete response defined as 24-h urinary protein under 0.5 g with normal estimated glomerular filtration rate or within 10% of normal range. The model development cohort included 245 patients (880 digital slides), and the external test cohort had 71 patients (258 digital slides). Deep learning models were trained independently on hematoxylin and eosin-, periodic acid-Schiff-, periodic Schiff-methenamine silver- and Masson's trichrome-stained slides at multiple magnifications and integrated to predict the primary outcome of complete response to therapy at 12 months. Single-stain models showed area under the curves of 0.813, 0.841, 0.823, and 0.862, respectively. Further, integration of the four models into a multi-stain model achieved area under the curves of 0.901 and 0.840 on internal validation and external testing, respectively, which outperformed conventional clinicopathologic parameters including estimated glomerular filtration rate, chronicity index and reduction in proteinuria at three months. Decisive features uncovered by visualization for model prediction included tertiary lymphoid structures, glomerulosclerosis, interstitial fibrosis and tubular atrophy. Our study demonstrated the feasibility of utilizing deep learning on kidney pathology to predict treatment response for lupus patients. Further validation is required before the model could be implemented for risk stratification and to aid in making therapeutic decisions in clinical practice.
Collapse
Affiliation(s)
- Cheng Cheng
- Department of Pediatrics, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Bin Li
- Clinical Trials Unit, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Jie Li
- Department of Pediatrics, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Yiqin Wang
- Department of Nephrology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, Guangdong, China; National Health Commission Key Laboratory of Clinical Nephrology (Sun Yat-sen University) and Guangdong Provincial Key Laboratory of Nephrology, Guangzhou, Guangdong, China
| | - Han Xiao
- Department of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Xingji Lian
- Department of Nephrology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, Guangdong, China; National Health Commission Key Laboratory of Clinical Nephrology (Sun Yat-sen University) and Guangdong Provincial Key Laboratory of Nephrology, Guangzhou, Guangdong, China
| | - Lizhi Chen
- Department of Pediatrics, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Junxian Wang
- Department of Nephrology, Zhongshan City People's Hospital, Zhongshan, Guangdong, China
| | - Haiyan Wang
- Department of Pediatrics, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Shuguang Qin
- Department of Nephrology, Guangzhou First People's Hospital, Guangzhou, Guangdong, China
| | - Li Yu
- Department of Pediatrics, Guangzhou First People's Hospital, Guangzhou, Guangdong, China
| | - Tingbo Wu
- Department of Pediatrics, Zhongshan City People's Hospital, Zhongshan, Guangdong, China
| | - Sui Peng
- Clinical Trials Unit, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China; Institute of Precision Medicine, the First Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China; Department of Gastroenterology and Hepatology, the First Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China
| | - Weiping Tan
- Department of Pediatrics, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China.
| | - Qing Ye
- Department of Nephrology, Zhongshan City People's Hospital, Zhongshan, Guangdong, China.
| | - Wei Chen
- Department of Nephrology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, Guangdong, China; National Health Commission Key Laboratory of Clinical Nephrology (Sun Yat-sen University) and Guangdong Provincial Key Laboratory of Nephrology, Guangzhou, Guangdong, China.
| | - Xiaoyun Jiang
- Department of Pediatrics, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China.
| |
Collapse
|
38
|
Toro P, Bakhshwin A, Zein-Sabatto B, Khaitan N, Duckworth L, Bennett A, Elsoukkary SS, Zhang X, Govande S, Zabor EC, Liska D, Balagamwala E, Allende DS. Computational Pathology-Enabled Residual Tumor Estimation Is a Prognostic Factor for Overall Survival in Anal Squamous Cell Carcinoma. Mod Pathol 2025; 38:100692. [PMID: 39709147 DOI: 10.1016/j.modpat.2024.100692] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/07/2024] [Revised: 11/12/2024] [Accepted: 12/10/2024] [Indexed: 12/23/2024]
Abstract
The incidence of anal squamous cell carcinoma (SCC) has increased, and treatment has shifted from surgery to chemoradiotherapy (CRT), with salvage abdominoperineal resection being reserved for persistent/recurrent cases. This study evaluates the utility of different tumor regression scoring systems in predicting survival in anal SCC patients, using pathologists' observations and digital pathology. Data of cases managed surgically from 2005 to 2019 were collected. Residual tumor was assessed by multiple methods (gross tumor size, largest focus of tumor on hematoxylin and eosin (H&E) slide, average of residual tumor in all submitted H&E slides, Japanese Esophageal Society, Chirieac, Schneider, Hermann, and College of American Pathologists scoring system). Three expert pathologists individually estimated ("eyeballed") the residual tumor percentage based on residual tumor/tumor bed (single representative H&E slide). The QuPath software was used to measure tumor volume on the same slide. The American Joint Committee on Cancer eighth staging and outcome data were retrieved from electronic medical records. The study involved 48 participants, predominantly female (56%), with a median age of 57 years. Most were Caucasian. Human papillomavirus-positive was present in 77% of those assessed (17/22). Initial treatment included CRT, followed by abdominoperineal resection (79%) or pelvic exenteration (21%). Complications (13%), persistent disease (33%), and recurrence (54%) led to surgical interventions. Fifty-one percent had moderately differentiated SCC, whereas 42% were poorly differentiated. Lymphovascular invasion (44%), perineural invasion (38%), and lymph node metastasis (13%) were present. Distant metastasis was rare (2%). Median overall survival was 3.2 years. Positive margins (hazard ratio, 4.12; 95% CI, 1.83-9.28) and larger tumor size (hazard ratio, 1.02; 95% CI, 1.01-1.03) were associated with an increased hazard of death. Most residual tumor measurement methods were not significantly associated with overall survival. Interobserver agreement (based on "eyeballing") was moderate (kappa, 0.4). Computational pathology-based residual tumor percentage was the only method significantly associated with outcome, with each 10% increase in the residual tumor percentage corresponding to a 1.23-fold higher hazard death (95% CI, 1.03; 1.46; P = .024). This study highlights computational pathology's important role in predicting outcomes in anal SCC treated with CRT and surgery. Specifically, the computational assessment of the residual tumor percentage proves to be a strong predictor of overall survival, outperforming other established tumor regression scoring systems methods.
Collapse
Affiliation(s)
- Paula Toro
- Department of Pathology, Cleveland Clinic, Cleveland, Ohio
| | - Ahmed Bakhshwin
- Department of Pathology, Faculty of Medicine, King Abdulaziz University, Jeddah, Saudi Arabia
| | | | - Neha Khaitan
- Department of Pathology, Cleveland Clinic, Cleveland, Ohio
| | | | - Ana Bennett
- Department of Pathology, Cleveland Clinic, Cleveland, Ohio
| | | | - Xuefeng Zhang
- Department of Pathology, Cleveland Clinic, Cleveland, Ohio
| | - Sneha Govande
- Department of Quantitative Health Sciences & Taussig Cancer Center, Cleveland Clinic, Cleveland, Ohio
| | - Emily C Zabor
- Department of Quantitative Health Sciences & Taussig Cancer Center, Cleveland Clinic, Cleveland, Ohio
| | - David Liska
- Department of Colorectal Surgery, Digestive Disease Institute, Cleveland Clinic, Cleveland, Ohio
| | | | | |
Collapse
|
39
|
Feng K, Yi Z, Xu B. Artificial Intelligence and Breast Cancer Management: From Data to the Clinic. CANCER INNOVATION 2025; 4:e159. [PMID: 39981497 PMCID: PMC11840326 DOI: 10.1002/cai2.159] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/07/2024] [Revised: 10/10/2024] [Accepted: 10/22/2024] [Indexed: 02/22/2025]
Abstract
Breast cancer (BC) remains a significant threat to women's health worldwide. The oncology field had an exponential growth in the abundance of medical images, clinical information, and genomic data. With its continuous advancement and refinement, artificial intelligence (AI) has demonstrated exceptional capabilities in processing intricate multidimensional BC-related data. AI has proven advantageous in various facets of BC management, encompassing efficient screening and diagnosis, precise prognosis assessment, and personalized treatment planning. However, the implementation of AI into precision medicine and clinical practice presents ongoing challenges that necessitate enhanced regulation, transparency, fairness, and integration of multiple clinical pathways. In this review, we provide a comprehensive overview of the current research related to AI in BC, highlighting its extensive applications throughout the whole BC cycle management and its potential for innovative impact. Furthermore, this article emphasizes the significance of constructing patient-oriented AI algorithms. Additionally, we explore the opportunities and potential research directions within this burgeoning field.
Collapse
Affiliation(s)
- Kaixiang Feng
- Department of Breast and Thyroid Surgery, Hubei Key Laboratory of Tumor Biological Behaviors, Hubei Cancer Clinical Study CenterZhongnan Hospital of Wuhan UniversityWuhanHubeiChina
- Department of Radiation and Medical Oncology, Hubei Key Laboratory of Tumor Biological Behaviors, Hubei Cancer Clinical Study CenterZhongnan Hospital of Wuhan UniversityWuhanHubeiChina
| | - Zongbi Yi
- Department of Radiation and Medical Oncology, Hubei Key Laboratory of Tumor Biological Behaviors, Hubei Cancer Clinical Study CenterZhongnan Hospital of Wuhan UniversityWuhanHubeiChina
| | - Binghe Xu
- Department of Medical Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer HospitalChinese Academy of Medical Sciences and Peking Union Medical CollegeBeijingChina
| |
Collapse
|
40
|
Grothey B, Odenkirchen J, Brkic A, Schömig-Markiefka B, Quaas A, Büttner R, Tolkach Y. Comprehensive testing of large language models for extraction of structured data in pathology. COMMUNICATIONS MEDICINE 2025; 5:96. [PMID: 40164789 PMCID: PMC11958830 DOI: 10.1038/s43856-025-00808-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/09/2024] [Accepted: 03/13/2025] [Indexed: 04/02/2025] Open
Abstract
BACKGROUND Pathology departments generate large volumes of unstructured data as free-text diagnostic reports. Converting these reports into structured formats for analytics or artificial intelligence projects requires substantial manual effort by specialized personnel. While recent studies show promise in using advanced language models for structuring pathology data, they primarily rely on proprietary models, raising cost and privacy concerns. Additionally, important aspects such as prompt engineering and model quantization for deployment on consumer-grade hardware remain unaddressed. METHODS We created a dataset of 579 annotated pathology reports in German and English versions. Six language models (proprietary: GPT-4; open-source: Llama2 13B, Llama2 70B, Llama3 8B, Llama3 70B, and Qwen2.5 7B) were evaluated for their ability to extract eleven key parameters from these reports. Additionally, we investigated model performance across different prompt engineering strategies and model quantization techniques to assess practical deployment scenarios. RESULTS Here we show that open-source language models extract structured data from pathology reports with high precision, matching the accuracy of proprietary GPT-4 model. The precision varies significantly across different models and configurations. These variations depend on specific prompt engineering strategies and quantization methods used during model deployment. CONCLUSIONS Open-source language models demonstrate comparable performance to proprietary solutions in structuring pathology report data. This finding has significant implications for healthcare institutions seeking cost-effective, privacy-preserving data structuring solutions. The variations in model performance across different configurations provide valuable insights for practical deployment in pathology departments. Our publicly available bilingual dataset serves as both a benchmark and a resource for future research.
Collapse
Affiliation(s)
- Bastian Grothey
- Institute of Pathology, University Hospital Cologne, Cologne, Germany.
| | | | - Adnan Brkic
- Institute of Pathology, University Hospital Cologne, Cologne, Germany
| | | | - Alexander Quaas
- Institute of Pathology, University Hospital Cologne, Cologne, Germany
| | - Reinhard Büttner
- Institute of Pathology, University Hospital Cologne, Cologne, Germany
| | - Yuri Tolkach
- Institute of Pathology, University Hospital Cologne, Cologne, Germany.
| |
Collapse
|
41
|
Zhang X, Wang T, Yan C, Najdawi F, Zhou K, Ma Y, Cheung YM, Malin BA. Implementing Trust in Non-Small Cell Lung Cancer Diagnosis with a Conformalized Uncertainty-Aware AI Framework in Whole-Slide Images. RESEARCH SQUARE 2025:rs.3.rs-5723270. [PMID: 40195980 PMCID: PMC11975025 DOI: 10.21203/rs.3.rs-5723270/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/09/2025]
Abstract
Ensuring trustworthiness is fundamental to the development of artificial intelligence (AI) that is considered societally responsible, particularly in cancer diagnostics, where a misdiagnosis can have dire consequences. Current digital pathology AI models lack systematic solutions to address trustworthiness concerns arising from model limitations and data discrepancies between model deployment and development environments. To address this issue, we developed TRUECAM, a framework designed to ensure both data and model trustworthiness in non-small cell lung cancer subtyping with whole-slide images. TRUECAM integrates 1) a spectral-normalized neural Gaussian process for identifying out-of-scope inputs and 2) an ambiguity-guided elimination of tiles to filter out highly ambiguous regions, addressing data trustworthiness, as well as 3) conformal prediction to ensure controlled error rates. We systematically evaluated the framework across multiple large-scale cancer datasets, leveraging both task-specific and foundation models, illustrate that an AI model wrapped with TRUECAM significantly outperforms models that lack such guidance, in terms of classification accuracy, robustness, interpretability, and data efficiency, while also achieving improvements in fairness. These findings highlight TRUECAM as a versatile wrapper framework for digital pathology AI models with diverse architectural designs, promoting their responsible and effective applications in real-world settings.
Collapse
Affiliation(s)
- Xiaoge Zhang
- Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong
| | - Tao Wang
- Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong
| | - Chao Yan
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Fedaa Najdawi
- Department of Pathology, Microbiology and Immunology, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Kai Zhou
- Department of Computing, The Hong Kong Polytechnic University, Kowloon, Hong Kong
| | - Yuan Ma
- Department of Mechanical Engineering and Research Institute for Intelligent Wearable Systems, The Hong Kong Polytechnic University, Kowloon, Hong Kong
| | - Yiu-Ming Cheung
- Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Kowloon, Hong Kong
| | - Bradley A Malin
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, USA
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
- Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, USA
| |
Collapse
|
42
|
Griffith JL, Joseph J, Jensen A, Banks S, Allen KD. Using deep-learning based segmentation to enable spatial evaluation of knee osteoarthritis (SEKO) in rodent models. Osteoarthritis Cartilage 2025:S1063-4584(25)00867-2. [PMID: 40139644 DOI: 10.1016/j.joca.2025.02.787] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/25/2024] [Revised: 01/21/2025] [Accepted: 02/20/2025] [Indexed: 03/29/2025]
Abstract
OBJECTIVE In preclinical models of osteoarthritis (OA), histology is commonly used to evaluate joint remodeling. The current study introduces a deep learning driven histological analysis pipeline for the spatial evaluation of knee osteoarthritis (SEKO) focused on quantifying and visualizing joint remodeling in the medial compartment of rodent knees. METHODS The SEKO pipeline contains both segmentation and visualization tools. For segmentation, two separate convolutional neural network architectures, HRNet and U-Net, were considered for identifying multiple regions of interest. Following segmentation, SEKO calculates multiple morphometric and location dependent measures to summarize joint-level changes. Additionally, SEKO generates probabilistic heat maps for visualization of the spatial aspects of joint remodeling. RESULTS SEKO incorporated the U-NET architecture - due to its higher prediction accuracy - and identified similar cartilage loss changes that were reported using by-hand segmentation in prior work. Additionally, SEKO enabled the detection of changes in subchondral bone area and location dependent bone remodeling. SEKO also enabled visualization of spatial changes in cartilage thinning and bone remodeling using probabilistic heat maps. CONCLUSION The SEKO pipeline offers the potential for objective comparison of OA progression and therapeutic interventions through visualization of spatial and morphometric changes. SEKO is provided as an open-source tool for the OA research community, facilitating collaborative research efforts and comprehensive analysis of knee joint histology.
Collapse
Affiliation(s)
- Jacob L Griffith
- J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA; Pain Research & Intervention Center of Excellence (PRICE), University of Florida, Gainesville, FL, USA
| | - Justin Joseph
- J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA
| | - Andrew Jensen
- Department of Mechanical and Aerospace Engineering at the University of Florida, Gainesville, FL, USA
| | - Scott Banks
- Department of Mechanical and Aerospace Engineering at the University of Florida, Gainesville, FL, USA; Department of Orthopaedic Surgery and Sports Medicine, University of Florida, Gainesville, FL, USA
| | - Kyle D Allen
- J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA; Pain Research & Intervention Center of Excellence (PRICE), University of Florida, Gainesville, FL, USA; Department of Mechanical and Aerospace Engineering at the University of Florida, Gainesville, FL, USA; Department of Orthopaedic Surgery and Sports Medicine, University of Florida, Gainesville, FL, USA.
| |
Collapse
|
43
|
Wekenborg MK, Gilbert S, Kather JN. Examining human-AI interaction in real-world healthcare beyond the laboratory. NPJ Digit Med 2025; 8:169. [PMID: 40108434 PMCID: PMC11923224 DOI: 10.1038/s41746-025-01559-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/04/2025] [Accepted: 03/10/2025] [Indexed: 03/22/2025] Open
Abstract
Artificial Intelligence (AI) is revolutionizing healthcare, but its true impact depends on seamless human interaction. While most research focuses on technical metrics, we lack frameworks to measure the compatibility or synergy of real-world human-AI interactions in healthcare settings. We propose a multimodal toolkit combining ecological momentary assessment, quantitative observations, and baseline measurements to optimize AI implementation.
Collapse
Affiliation(s)
- Magdalena Katharina Wekenborg
- Else Kroener Fresenius Center for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany
| | - Stephen Gilbert
- Else Kroener Fresenius Center for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany
| | - Jakob Nikolas Kather
- Else Kroener Fresenius Center for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany.
- Department of Medicine I, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany.
- Medical Oncology, National Center for Tumor Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany.
| |
Collapse
|
44
|
Grinberg N, Whitefield S, Kleinman S, Ianculovici C, Wasserman G, Peleg O. Assessing the performance of an artificial intelligence based chatbot in the differential diagnosis of oral mucosal lesions: clinical validation study. Clin Oral Investig 2025; 29:188. [PMID: 40097790 DOI: 10.1007/s00784-025-06268-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2024] [Accepted: 03/07/2025] [Indexed: 03/19/2025]
Abstract
OBJECTIVES Artificial intelligence (AI) is becoming more popular in medicine. The current study aims to investigate, primarily, if an AI-based chatbot, such as ChatGPT, could be a valid tool for assisting in establishing a differential diagnosis of oral mucosal lesions. METHODS Data was gathered from patients who were referred to our clinic for an oral mucosal biopsy by one oral medicine specialist. Clinical description, differential diagnoses, and final histopathologic diagnoses were retrospectively extracted from patient records. The lesion description was inputted into ChatGPT version 4.0 under a uniform script to generate three differential diagnoses. ChatGPT and an oral medicine specialist's differential diagnosis were compared to the final histopathologic diagnosis. RESULTS 100 oral soft tissue lesions were evaluated. A statistically significant correlation was found between the ability of the Chatbot and the Specialist to accurately diagnose the cases (P < 0.001). ChatGPT demonstrated remarkable sensitivity for diagnosing urgent cases, as none of the malignant lesions were missed by the chatbot. At the same time, the specificity of the specialist was higher in cases of malignant lesion diagnosis (p < 0.05). The chatbot performance was reliable in two different events (p < 0.01). CONCLUSION ChatGPT-4 has shown the ability to pinpoint suspicious malignant lesions and suggest an adequate differential diagnosis for soft tissue lesions, in a consistent and repetitive manner. CLINICAL RELEVANCE This study serves as a primary insight into the role of AI chatbots, as assisting tools in oral medicine and assesses their clinical capabilities.
Collapse
Affiliation(s)
- Nadav Grinberg
- Department of Otolaryngology, Head and Neck Surgery and Maxillofacial Surgery, Tel-Aviv Sourasky Medical Center, 64239, Tel Aviv, Israel.
- , Mevasseret Zion, Israel.
| | - Sara Whitefield
- Oral Medicine Unit, Head and Neck Surgery and Maxillofacial Surgery, Tel-Aviv Sourasky Medical Center, 64239, Tel Aviv, Israel
| | - Shlomi Kleinman
- Department of Otolaryngology, Head and Neck Surgery and Maxillofacial Surgery, Tel-Aviv Sourasky Medical Center, 64239, Tel Aviv, Israel
| | - Clariel Ianculovici
- Department of Otolaryngology, Head and Neck Surgery and Maxillofacial Surgery, Tel-Aviv Sourasky Medical Center, 64239, Tel Aviv, Israel
| | - Gilad Wasserman
- Oral Medicine Unit, Head and Neck Surgery and Maxillofacial Surgery, Tel-Aviv Sourasky Medical Center, 64239, Tel Aviv, Israel
| | - Oren Peleg
- Department of Otolaryngology, Head and Neck Surgery and Maxillofacial Surgery, Tel-Aviv Sourasky Medical Center, 64239, Tel Aviv, Israel
| |
Collapse
|
45
|
Santacroce G, Zammarchi I, Nardone OM, Capobianco I, Puga-Tejada M, Majumder S, Ghosh S, Iacucci M. Rediscovering histology - the application of artificial intelligence in inflammatory bowel disease histologic assessment. Therap Adv Gastroenterol 2025; 18:17562848251325525. [PMID: 40098604 PMCID: PMC11912177 DOI: 10.1177/17562848251325525] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/11/2024] [Accepted: 02/10/2025] [Indexed: 03/19/2025] Open
Abstract
Integrating artificial intelligence (AI) into histologic disease assessment is transforming the management of inflammatory bowel disease (IBD). AI-aided histology enables precise, objective evaluations of disease activity by analysing whole-slide images, facilitating accurate predictions of histologic remission (HR) in ulcerative colitis and Crohn's disease. Additionally, AI shows promise in predicting adverse outcomes and therapeutic responses, making it a promising tool for clinical practice and clinical trials. By leveraging advanced algorithms, AI enhances diagnostic accuracy, reduces assessment variability and streamlines histological workflows in clinical settings. In clinical trials, AI aids in assessing histological endpoints, enabling real-time analysis, standardising evaluations and supporting adaptive trial designs. Recent advancements are further refining AI-aided digital pathology in IBD. New developments in multimodal AI models integrating clinical, endoscopic, histologic and molecular data pave the way for a comprehensive approach to precision medicine in IBD. Automated assessment of intestinal barrier healing - a deeper level of healing beyond endoscopic and HR - shows promise for improved outcome prediction and patient management. Preliminary evidence also suggests that AI applied to colitis-associated neoplasia can aid in the detection, characterisation and molecular profiling of lesions, holding potential for enhanced dysplasia management and organ-sparing approaches. Although challenges remain in standardisation, validation through randomised controlled trials and ethical considerations. AI is poised to revolutionise IBD management by advancing towards a more personalised and efficient care model, while the path to full clinical implementation may be lengthy. However, the transformative impact of AI on IBD care is already shining through.
Collapse
Affiliation(s)
- Giovanni Santacroce
- APC Microbiome Ireland, College of Medicine and Health, University College Cork, Cork, Ireland
| | - Irene Zammarchi
- APC Microbiome Ireland, College of Medicine and Health, University College Cork, Cork, Ireland
| | - Olga Maria Nardone
- APC Microbiome Ireland, College of Medicine and Health, University College Cork, Cork, Ireland
| | - Ivan Capobianco
- APC Microbiome Ireland, College of Medicine and Health, University College Cork, Cork, Ireland
| | - Miguel Puga-Tejada
- APC Microbiome Ireland, College of Medicine and Health, University College Cork, Cork, Ireland
| | - Snehali Majumder
- APC Microbiome Ireland, College of Medicine and Health, University College Cork, Cork, Ireland
| | - Subrata Ghosh
- APC Microbiome Ireland, College of Medicine and Health, University College Cork, Cork, Ireland
| | - Marietta Iacucci
- APC Microbiome Ireland, College of Medicine and Health, University College Cork
- Cork, Ireland – Biosciences Institute, College Rd, University College Cork, T12 YT20, Cork, Ireland
| |
Collapse
|
46
|
Stagno F, Russo S, Murdaca G, Mirabile G, Alvaro ME, Nasso ME, Zemzem M, Gangemi S, Allegra A. Utilization of Machine Learning in the Prediction, Diagnosis, Prognosis, and Management of Chronic Myeloid Leukemia. Int J Mol Sci 2025; 26:2535. [PMID: 40141176 PMCID: PMC11942435 DOI: 10.3390/ijms26062535] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2025] [Revised: 03/07/2025] [Accepted: 03/11/2025] [Indexed: 03/28/2025] Open
Abstract
Chronic myeloid leukemia is a clonal hematologic disease characterized by the presence of the Philadelphia chromosome and the BCR::ABL1 fusion protein. Integrating different molecular, genetic, clinical, and laboratory data would improve the diagnostic, prognostic, and predictive sensitivity of chronic myeloid leukemia. However, without artificial intelligence support, managing such a vast volume of data would be impossible. Considering the advancements and growth in machine learning throughout the years, several models and algorithms have been proposed for the management of chronic myeloid leukemia. Here, we provide an overview of recent research that used specific algorithms on patients with chronic myeloid leukemia, highlighting the potential benefits of adopting machine learning in therapeutic contexts as well as its drawbacks. Our analysis demonstrated the great potential for advancing precision treatment in CML through the combination of clinical and genetic data, laboratory testing, and machine learning. We can use these powerful research instruments to unravel the molecular and spatial puzzles of CML by overcoming the current obstacles. A new age of patient-centered hematology care will be ushered in by this, opening the door for improved diagnosis accuracy, sophisticated risk assessment, and customized treatment plans.
Collapse
MESH Headings
- Humans
- Leukemia, Myelogenous, Chronic, BCR-ABL Positive/diagnosis
- Leukemia, Myelogenous, Chronic, BCR-ABL Positive/therapy
- Leukemia, Myelogenous, Chronic, BCR-ABL Positive/genetics
- Machine Learning
- Prognosis
- Fusion Proteins, bcr-abl/genetics
- Disease Management
- Algorithms
Collapse
Affiliation(s)
- Fabio Stagno
- Division of Hematology, Department of Human Pathology in Adulthood and Childhood “Gaetano Barresi”, University of Messina, Via Consolare Valeria, 98125 Messina, Italy; (F.S.); (S.R.); (G.M.); (M.E.A.); (M.E.N.); (M.Z.); (A.A.)
| | - Sabina Russo
- Division of Hematology, Department of Human Pathology in Adulthood and Childhood “Gaetano Barresi”, University of Messina, Via Consolare Valeria, 98125 Messina, Italy; (F.S.); (S.R.); (G.M.); (M.E.A.); (M.E.N.); (M.Z.); (A.A.)
| | - Giuseppe Murdaca
- Department of Internal Medicine, University of Genova, 16126 Genova, Italy
- Allergology and Clinical Immunology, San Bartolomeo Hospital, 19038 Sarzana, Italy
| | - Giuseppe Mirabile
- Division of Hematology, Department of Human Pathology in Adulthood and Childhood “Gaetano Barresi”, University of Messina, Via Consolare Valeria, 98125 Messina, Italy; (F.S.); (S.R.); (G.M.); (M.E.A.); (M.E.N.); (M.Z.); (A.A.)
| | - Maria Eugenia Alvaro
- Division of Hematology, Department of Human Pathology in Adulthood and Childhood “Gaetano Barresi”, University of Messina, Via Consolare Valeria, 98125 Messina, Italy; (F.S.); (S.R.); (G.M.); (M.E.A.); (M.E.N.); (M.Z.); (A.A.)
| | - Maria Elisa Nasso
- Division of Hematology, Department of Human Pathology in Adulthood and Childhood “Gaetano Barresi”, University of Messina, Via Consolare Valeria, 98125 Messina, Italy; (F.S.); (S.R.); (G.M.); (M.E.A.); (M.E.N.); (M.Z.); (A.A.)
| | - Mohamed Zemzem
- Division of Hematology, Department of Human Pathology in Adulthood and Childhood “Gaetano Barresi”, University of Messina, Via Consolare Valeria, 98125 Messina, Italy; (F.S.); (S.R.); (G.M.); (M.E.A.); (M.E.N.); (M.Z.); (A.A.)
| | - Sebastiano Gangemi
- Allergy and Clinical Immunology Unit, Department of Clinical and Experimental Medicine, University of Messina, Via Consolare Valeria, 98125 Messina, Italy;
| | - Alessandro Allegra
- Division of Hematology, Department of Human Pathology in Adulthood and Childhood “Gaetano Barresi”, University of Messina, Via Consolare Valeria, 98125 Messina, Italy; (F.S.); (S.R.); (G.M.); (M.E.A.); (M.E.N.); (M.Z.); (A.A.)
| |
Collapse
|
47
|
Zhang D, Zhao L, Guo B, Guo A, Ding J, Tong D, Wang B, Zhou Z. Integrated Machine Learning Algorithms-Enhanced Predication for Cervical Cancer from Mass Spectrometry-Based Proteomics Data. Bioengineering (Basel) 2025; 12:269. [PMID: 40150733 PMCID: PMC11939187 DOI: 10.3390/bioengineering12030269] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2025] [Revised: 03/04/2025] [Accepted: 03/07/2025] [Indexed: 03/29/2025] Open
Abstract
Early diagnosis is critical for improving outcomes in cancer patients; however, the application of diagnostic markers derived from serum proteomic screening remains challenging. Artificial intelligence (AI), encompassing deep learning and machine learning (ML), has gained increasing prominence across various scientific disciplines. In this study, we utilized cervical cancer (CC) as a model to develop an AI-driven pipeline for the identification and validation of serum biomarkers for early cancer diagnosis, leveraging mass spectrometry-based proteomics data. By processing and normalizing serum polypeptide differential peaks from 240 patients, we employed eight distinct ML algorithms to classify and analyze these differential polypeptide peaks, subsequently constructing receiver operating characteristic (ROC) curves and confusion matrices. Key performance metrics, including accuracy, precision, recall, and F1 score, were systematically evaluated. Furthermore, by integrating feature importance values, Shapley values, and local interpretable model-agnostic explanation (LIME) values, we demonstrated that the diagnostic area under the curve (AUC) achieved by our multi-dimensional learning models approached 1, significantly outperforming the diagnostic AUC of single markers derived from the PRIDE database. These findings underscore the potential of proteomics-driven integrated machine learning as a robust strategy to enhance early cancer diagnosis, offering a promising avenue for clinical translation.
Collapse
Affiliation(s)
- Da Zhang
- Department of Oncology, The Second Affiliated Hospital, Xi’an Jiaotong University, Xi’an 710000, China;
| | - Lihong Zhao
- Department of Dermatology, The Second Affiliated Hospital, Xi’an Jiaotong University, Xi’an 710000, China;
| | - Bo Guo
- Department of Cell Biology and Genetics, School of Basic Medical Sciences, Xi’an Jiaotong University Health Science Center, Xi’an 710000, China; (B.G.); (A.G.); (J.D.); (D.T.)
| | - Aihong Guo
- Department of Cell Biology and Genetics, School of Basic Medical Sciences, Xi’an Jiaotong University Health Science Center, Xi’an 710000, China; (B.G.); (A.G.); (J.D.); (D.T.)
- Department of Clinical Research, Xianyang Hospital of Yan’an University, Xianyang 712000, China
| | - Jiangbo Ding
- Department of Cell Biology and Genetics, School of Basic Medical Sciences, Xi’an Jiaotong University Health Science Center, Xi’an 710000, China; (B.G.); (A.G.); (J.D.); (D.T.)
- Department of Clinical Research, Xianyang Hospital of Yan’an University, Xianyang 712000, China
| | - Dongdong Tong
- Department of Cell Biology and Genetics, School of Basic Medical Sciences, Xi’an Jiaotong University Health Science Center, Xi’an 710000, China; (B.G.); (A.G.); (J.D.); (D.T.)
| | - Bingju Wang
- Department of Cell Biology and Genetics, School of Basic Medical Sciences, Xi’an Jiaotong University Health Science Center, Xi’an 710000, China; (B.G.); (A.G.); (J.D.); (D.T.)
- Department of Clinical Research, Xianyang Hospital of Yan’an University, Xianyang 712000, China
- Department of Clinical Research, Rugao Hospital of Shenzhen Jingcheng Medical Group, Rugao 226500, China
| | - Zhangjian Zhou
- Department of Oncology, The Second Affiliated Hospital, Xi’an Jiaotong University, Xi’an 710000, China;
| |
Collapse
|
48
|
Liu B, Polack M, Coudray N, Claudio Quiros A, Sakellaropoulos T, Le H, Karimkhan A, Crobach ASLP, van Krieken JHJM, Yuan K, Tollenaar RAEM, Mesker WE, Tsirigos A. Self-supervised learning reveals clinically relevant histomorphological patterns for therapeutic strategies in colon cancer. Nat Commun 2025; 16:2328. [PMID: 40057490 PMCID: PMC11890774 DOI: 10.1038/s41467-025-57541-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2024] [Accepted: 02/26/2025] [Indexed: 05/13/2025] Open
Abstract
Self-supervised learning (SSL) automates the extraction and interpretation of histopathology features on unannotated hematoxylin-eosin-stained whole slide images (WSIs). We train an SSL Barlow Twins encoder on 435 colon adenocarcinoma WSIs from The Cancer Genome Atlas to extract features from small image patches (tiles). Leiden community detection groups tiles into histomorphological phenotype clusters (HPCs). HPC reproducibility and predictive ability for overall survival are confirmed in an independent clinical trial (N = 1213 WSIs). This unbiased atlas results in 47 HPCs displaying unique and shared clinically significant histomorphological traits, highlighting tissue type, quantity, and architecture, especially in the context of tumor stroma. Through in-depth analyses of these HPCs, including immune landscape and gene set enrichment analyses, and associations to clinical outcomes, we shine light on the factors influencing survival and responses to treatments of standard adjuvant chemotherapy and experimental therapies. Further exploration of HPCs may unveil additional insights and aid decision-making and personalized treatments for colon cancer patients.
Collapse
Affiliation(s)
- Bojing Liu
- Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Karolinska, Sweden
- Applied Bioinformatics Laboratories, New York University Grossman School of Medicine, New York, NY, USA
| | - Meaghan Polack
- Department of Surgery, Leiden University Medical Center, Leiden, The Netherlands
| | - Nicolas Coudray
- Applied Bioinformatics Laboratories, New York University Grossman School of Medicine, New York, NY, USA
- Department of Cell Biology, New York University Grossman School of Medicine, New York, NY, USA
| | | | - Theodore Sakellaropoulos
- Applied Bioinformatics Laboratories, New York University Grossman School of Medicine, New York, NY, USA
| | - Hortense Le
- Applied Bioinformatics Laboratories, New York University Grossman School of Medicine, New York, NY, USA
| | - Afreen Karimkhan
- Department of Pathology, New York University Grossman School of Medicine, New York, NY, USA
| | | | - J Han J M van Krieken
- Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Ke Yuan
- Department of Computing Science, University of Glasgow, Glasgow, United Kingdom
- School of Cancer Sciences, University of Glasgow, Glasgow, Scotland, UK
| | - Rob A E M Tollenaar
- Department of Surgery, Leiden University Medical Center, Leiden, The Netherlands
| | - Wilma E Mesker
- Department of Surgery, Leiden University Medical Center, Leiden, The Netherlands
| | - Aristotelis Tsirigos
- Applied Bioinformatics Laboratories, New York University Grossman School of Medicine, New York, NY, USA.
- Department of Pathology, New York University Grossman School of Medicine, New York, NY, USA.
| |
Collapse
|
49
|
Obeagu EI, Ezeanya CU, Ogenyi FC, Ifu DD. Big data analytics and machine learning in hematology: Transformative insights, applications and challenges. Medicine (Baltimore) 2025; 104:e41766. [PMID: 40068020 PMCID: PMC11902945 DOI: 10.1097/md.0000000000041766] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/20/2023] [Revised: 12/14/2024] [Accepted: 02/17/2025] [Indexed: 03/14/2025] Open
Abstract
The integration of big data analytics and machine learning (ML) into hematology has ushered in a new era of precision medicine, offering transformative insights into disease management. By leveraging vast and diverse datasets, including genomic profiles, clinical laboratory results, and imaging data, these technologies enhance diagnostic accuracy, enable robust prognostic modeling, and support personalized therapeutic interventions. Advanced ML algorithms, such as neural networks and ensemble learning, facilitate the discovery of novel biomarkers and refine risk stratification for hematological disorders, including leukemias, lymphomas, and coagulopathies. Despite these advancements, significant challenges persist, particularly in the realms of data integration, algorithm validation, and ethical concerns. The heterogeneity of hematological datasets and the lack of standardized frameworks complicate their application, while the "black-box" nature of ML models raises issues of reliability and clinical trust. Moreover, safeguarding patient privacy in an era of data-driven medicine remains paramount, necessitating the development of secure and ethical analytical practices. Addressing these challenges is critical to ensuring equitable and effective implementation of these technologies. Collaborative efforts between hematologists, data scientists, and bioinformaticians are pivotal in translating these innovations into real-world clinical practice. Emphasis on developing explainable artificial intelligence models, integrating real-time analytics, and adopting federated learning approaches will further enhance the utility and adoption of these technologies. As big data analytics and ML continue to evolve, their potential to revolutionize hematology and improve patient outcomes remains immense.
Collapse
Affiliation(s)
| | | | - Fabian Chukwudi Ogenyi
- Department of Electrical, Telecommunication and Computer Engineering, Kampala International University, Kampala, Uganda
| | - Deborah Domini Ifu
- Department of Biomedical and Laboratory Science, Africa University, Mutare, Zimbabwe
| |
Collapse
|
50
|
Mill L, Aust O, Ackermann JA, Burger P, Pascual M, Palumbo-Zerr K, Krönke G, Uderhardt S, Schett G, Clemen CS, Holtzhausen C, Jabari S, Schröder R, Maier A, Grüneboom A. Deep learning-based image analysis in muscle histopathology using photo-realistic synthetic data. COMMUNICATIONS MEDICINE 2025; 5:64. [PMID: 40050400 PMCID: PMC11885816 DOI: 10.1038/s43856-025-00777-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2024] [Accepted: 02/20/2025] [Indexed: 03/09/2025] Open
Abstract
BACKGROUND Artificial intelligence (AI), specifically Deep learning (DL), has revolutionized biomedical image analysis, but its efficacy is limited by the need for representative, high-quality large datasets with manual annotations. While latest research on synthetic data using AI-based generative models has shown promising results to tackle this problem, several challenges such as lack of interpretability and need for vast amounts of real data remain. This study aims to introduce a new approach-SYNTA-for the generation of photo-realistic synthetic biomedical image data to address the challenges associated with state-of-the art generative models and DL-based image analysis. METHODS The SYNTA method employs a fully parametric approach to create photo-realistic synthetic training datasets tailored to specific biomedical tasks. Its applicability is tested in the context of muscle histopathology and skeletal muscle analysis. This new approach is evaluated for two real-world datasets to validate its applicability to solve complex image analysis tasks on real data. RESULTS Here we show that SYNTA enables expert-level segmentation of unseen real-world biomedical data using only synthetic training data. By addressing the lack of representative and high-quality real-world training data, SYNTA achieves robust performance in muscle histopathology image analysis, offering a scalable, controllable and interpretable alternative to generative models such as Generative Adversarial Networks (GANs) or Diffusion Models. CONCLUSIONS SYNTA demonstrates great potential to accelerate and improve biomedical image analysis. Its ability to generate high-quality photo-realistic synthetic data reduces reliance on extensive collection of data and manual annotations, paving the way for advancements in histopathology and medical research.
Collapse
Affiliation(s)
- Leonid Mill
- MIRA Vision Microscopy GmbH, 73037, Göppingen, Germany.
- Pattern Recognition Lab, Friedrich-Alexander University Erlangen-Nürnberg (FAU), 91058, Erlangen, Germany.
| | - Oliver Aust
- Department of Medicine 3 - Rheumatology and Immunology & Deutsches Zentrum für Immuntherapie, Friedrich-Alexander University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, 91054, Erlangen, Germany
| | - Jochen A Ackermann
- Department of Medicine 3 - Rheumatology and Immunology & Deutsches Zentrum für Immuntherapie, Friedrich-Alexander University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, 91054, Erlangen, Germany
| | - Philipp Burger
- Department of Medicine 3 - Rheumatology and Immunology & Deutsches Zentrum für Immuntherapie, Friedrich-Alexander University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, 91054, Erlangen, Germany
| | - Monica Pascual
- Department of Medicine 3 - Rheumatology and Immunology & Deutsches Zentrum für Immuntherapie, Friedrich-Alexander University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, 91054, Erlangen, Germany
| | - Katrin Palumbo-Zerr
- Department of Medicine 3 - Rheumatology and Immunology & Deutsches Zentrum für Immuntherapie, Friedrich-Alexander University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, 91054, Erlangen, Germany
| | - Gerhard Krönke
- Department of Medicine 3 - Rheumatology and Immunology & Deutsches Zentrum für Immuntherapie, Friedrich-Alexander University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, 91054, Erlangen, Germany
| | - Stefan Uderhardt
- Department of Medicine 3 - Rheumatology and Immunology & Deutsches Zentrum für Immuntherapie, Friedrich-Alexander University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, 91054, Erlangen, Germany
| | - Georg Schett
- Department of Medicine 3 - Rheumatology and Immunology & Deutsches Zentrum für Immuntherapie, Friedrich-Alexander University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, 91054, Erlangen, Germany
| | - Christoph S Clemen
- Institute of Aerospace Medicine, German Aerospace Center (DLR), Cologne, Germany
- Institute of Vegetative Physiology, Medical Faculty, University of Cologne, Cologne, Germany
| | - Christian Holtzhausen
- Department of Neuropathology, Universitätsklinikum Erlangen, Friedrich-Alexander University Erlangen-Nürnberg (FAU), 91054, Erlangen, Germany
| | - Samir Jabari
- Department of Neuropathology, Universitätsklinikum Erlangen, Friedrich-Alexander University Erlangen-Nürnberg (FAU), 91054, Erlangen, Germany
- Klinikum Nuremberg, Institute of Pathology, Paracelsus Medical University, 90419, Nuremberg, Germany
| | - Rolf Schröder
- Department of Neuropathology, Universitätsklinikum Erlangen, Friedrich-Alexander University Erlangen-Nürnberg (FAU), 91054, Erlangen, Germany
| | - Andreas Maier
- Pattern Recognition Lab, Friedrich-Alexander University Erlangen-Nürnberg (FAU), 91058, Erlangen, Germany
| | - Anika Grüneboom
- Leibniz-Institut für Analytische Wissenschaften - ISAS - e.V, 44139, Dortmund, Germany.
| |
Collapse
|