|
1
|
Patel RK, Parappilly M, Farley HC, Latour EJ, Wang LG, Nair AM, Lu ES, Sims Z, Park B, Nelson K, Mayo SC, Mills GB, Sheppard BC, Chang YH, Gibbs SL, Kardosh A, Lopez CD, Wong MH. Circulating Neoplastic-Immune Hybrid Cells Are Biomarkers of Occult Metastasis and Treatment Response in Pancreatic Cancer. Cancers (Basel) 2024; 16:3650. [PMID: 39518088 PMCID: PMC11545756 DOI: 10.3390/cancers16213650] [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: 09/25/2024] [Revised: 10/21/2024] [Accepted: 10/24/2024] [Indexed: 11/16/2024] Open
Abstract
BACKGROUND/OBJECTIVES Pancreatic ductal adenocarcinoma (PDAC) presents significant diagnostic and prognostic challenges, as current biomarkers frequently fail to accurately stage disease, predict rapid metastatic recurrence (rPDAC), or assess response to neoadjuvant therapy (NAT). We investigated the potential for circulating neoplastic-immune hybrid cells (CHCs) as a non-invasive, multifunctional biomarker for PDAC. METHODS Peripheral blood specimens were obtained from patients diagnosed with PDAC. CHCs were detected by co-expression of pan-cytokeratin and CD45, normalized to 50,000 peripheral blood mononuclear cells. rPDAC was defined as metastatic recurrence within six months of margin-negative pancreatectomy. Cyclic immunofluorescence (CyCIF) analyses compared hybrid phenotypes in blood and tumors. RESULTS Blood samples were collected from 42 patients with PDAC prior to resection. Those with radiographically occult metastatic disease and rPDAC had higher preoperative CHC numbers compared to patients who did not (65.0 and 74.4, vs. 11.52 CHCs; p < 0.001). Patients with complete or near-complete pathologic responses to NAT had lower preoperative CHC numbers than partial and/or non-responders (1.7 vs. 13.1 CHCs; p = 0.008). When assessed longitudinally, those with partial pathologic response saw CHC levels become undetectable while on treatment but increase in the interval between NAT completion and resection. In contrast, patients with poor responses or development of metastatic disease experienced persistent CHC detection during therapy or rising levels prior to radiographic evidence of metastases. Further, in metastatic PDAC patients, treatment-induced phenotypic changes in hybrid cells mirrored those in paired metastatic tumor samples. CONCLUSIONS CHC enumeration and phenotyping display promise as a real-time indicator of disease burden, recurrence risk, and treatment response in PDAC. CHCs have great potential as tumor-derived biomarkers to optimize therapeutic strategies and improve survival in patients with PDAC.
Collapse
Affiliation(s)
- Ranish K. Patel
- Department of Surgery, Division of Surgical Oncology, Oregon Health & Science University (OHSU), Portland, OR 97239, USA; (R.K.P.)
| | - Michael Parappilly
- Department of Cell, Developmental and Cancer Biology, OHSU, Portland, OR 97201, USA
| | - Hannah C. Farley
- Department of Cell, Developmental and Cancer Biology, OHSU, Portland, OR 97201, USA
| | - Emile J. Latour
- Biostatistics Shared Resource, Knight Cancer Institute, OHSU, Portland, OR 97239, USA
| | - Lei G. Wang
- Department of Biomedical Engineering, OHSU, Portland, OR 97201, USA
| | - Ashvin M. Nair
- Department of Cell, Developmental and Cancer Biology, OHSU, Portland, OR 97201, USA
| | - Ethan S. Lu
- Department of Cell, Developmental and Cancer Biology, OHSU, Portland, OR 97201, USA
| | - Zachary Sims
- Department of Biomedical Engineering, OHSU, Portland, OR 97201, USA
| | - Byung Park
- Biostatistics Shared Resource, Knight Cancer Institute, OHSU, Portland, OR 97239, USA
- Knight Cancer Institute, OHSU, Portland, OR 97201, USA
| | - Katherine Nelson
- Gastrointestinal Clinical Trials, Knight Cancer Institute, OHSU, Portland, OR 97239, USA
| | - Skye C. Mayo
- Department of Surgery, Division of Surgical Oncology, Oregon Health & Science University (OHSU), Portland, OR 97239, USA; (R.K.P.)
- Knight Cancer Institute, OHSU, Portland, OR 97201, USA
| | - Gordon B. Mills
- Knight Cancer Institute, OHSU, Portland, OR 97201, USA
- Division of Oncological Sciences, Knight Cancer Institute, OHSU, Portland, OR 97239, USA
| | - Brett C. Sheppard
- Knight Cancer Institute, OHSU, Portland, OR 97201, USA
- Department of Surgery, Division of General Surgery, OHSU, Portland, OR 97239, USA
| | - Young Hwan Chang
- Department of Biomedical Engineering, OHSU, Portland, OR 97201, USA
- Knight Cancer Institute, OHSU, Portland, OR 97201, USA
| | - Summer L. Gibbs
- Department of Biomedical Engineering, OHSU, Portland, OR 97201, USA
- Knight Cancer Institute, OHSU, Portland, OR 97201, USA
| | - Adel Kardosh
- Knight Cancer Institute, OHSU, Portland, OR 97201, USA
- Department of Medicine, Division of Medical Oncology, OHSU, Portland, OR 97239, USA
| | - Charles D. Lopez
- Knight Cancer Institute, OHSU, Portland, OR 97201, USA
- Department of Medicine, Division of Medical Oncology, OHSU, Portland, OR 97239, USA
| | - Melissa H. Wong
- Department of Cell, Developmental and Cancer Biology, OHSU, Portland, OR 97201, USA
- Knight Cancer Institute, OHSU, Portland, OR 97201, USA
| |
Collapse
|
|
2
|
Liu W, Zhang B, Liu T, Jiang J, Liu Y. Artificial Intelligence in Pancreatic Image Analysis: A Review. SENSORS (BASEL, SWITZERLAND) 2024; 24:4749. [PMID: 39066145 PMCID: PMC11280964 DOI: 10.3390/s24144749] [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: 06/05/2024] [Revised: 07/15/2024] [Accepted: 07/16/2024] [Indexed: 07/28/2024]
Abstract
Pancreatic cancer is a highly lethal disease with a poor prognosis. Its early diagnosis and accurate treatment mainly rely on medical imaging, so accurate medical image analysis is especially vital for pancreatic cancer patients. However, medical image analysis of pancreatic cancer is facing challenges due to ambiguous symptoms, high misdiagnosis rates, and significant financial costs. Artificial intelligence (AI) offers a promising solution by relieving medical personnel's workload, improving clinical decision-making, and reducing patient costs. This study focuses on AI applications such as segmentation, classification, object detection, and prognosis prediction across five types of medical imaging: CT, MRI, EUS, PET, and pathological images, as well as integrating these imaging modalities to boost diagnostic accuracy and treatment efficiency. In addition, this study discusses current hot topics and future directions aimed at overcoming the challenges in AI-enabled automated pancreatic cancer diagnosis algorithms.
Collapse
Affiliation(s)
- Weixuan Liu
- Sydney Smart Technology College, Northeastern University at Qinhuangdao, Qinhuangdao 066004, China; (W.L.); (B.Z.)
| | - Bairui Zhang
- Sydney Smart Technology College, Northeastern University at Qinhuangdao, Qinhuangdao 066004, China; (W.L.); (B.Z.)
| | - Tao Liu
- School of Mathematics and Statistics, Northeastern University at Qinhuangdao, Qinhuangdao 066004, China;
| | - Juntao Jiang
- College of Control Science and Engineering, Zhejiang University, Hangzhou 310058, China
| | - Yong Liu
- College of Control Science and Engineering, Zhejiang University, Hangzhou 310058, China
| |
Collapse
|
|
3
|
Femel J, Hill C, Illa Bochaca I, Booth JL, Asnaashari TG, Steele MM, Moshiri AS, Do H, Zhong J, Osman I, Leachman SA, Tsujikawa T, White KP, Chang YH, Lund AW. Quantitative multiplex immunohistochemistry reveals inter-patient lymphovascular and immune heterogeneity in primary cutaneous melanoma. Front Immunol 2024; 15:1328602. [PMID: 38361951 PMCID: PMC10867179 DOI: 10.3389/fimmu.2024.1328602] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/27/2023] [Accepted: 01/15/2024] [Indexed: 02/17/2024] Open
Abstract
Introduction Quantitative, multiplexed imaging is revealing complex spatial relationships between phenotypically diverse tumor infiltrating leukocyte populations and their prognostic implications. The underlying mechanisms and tissue structures that determine leukocyte distribution within and around tumor nests, however, remain poorly understood. While presumed players in metastatic dissemination, new preclinical data demonstrates that blood and lymphatic vessels (lymphovasculature) also dictate leukocyte trafficking within tumor microenvironments and thereby impact anti-tumor immunity. Here we interrogate these relationships in primary human cutaneous melanoma. Methods We established a quantitative, multiplexed imaging platform to simultaneously detect immune infiltrates and tumor-associated vessels in formalin-fixed paraffin embedded patient samples. We performed a discovery, retrospective analysis of 28 treatment-naïve, primary cutaneous melanomas. Results Here we find that the lymphvasculature and immune infiltrate is heterogenous across patients in treatment naïve, primary melanoma. We categorized five lymphovascular subtypes that differ by functionality and morphology and mapped their localization in and around primary tumors. Interestingly, the localization of specific vessel subtypes, but not overall vessel density, significantly associated with the presence of lymphoid aggregates, regional progression, and intratumoral T cell infiltrates. Discussion We describe a quantitative platform to enable simultaneous lymphovascular and immune infiltrate analysis and map their spatial relationships in primary melanoma. Our data indicate that tumor-associated vessels exist in different states and that their localization may determine potential for metastasis or immune infiltration. This platform will support future efforts to map tumor-associated lymphovascular evolution across stage, assess its prognostic value, and stratify patients for adjuvant therapy.
Collapse
Affiliation(s)
- Julia Femel
- Department of Cell, Developmental, & Cancer Biology, Oregon Health & Science University, Portland, OR, United States
| | - Cameron Hill
- Ronald O. Perelman Department of Dermatology, New York University (NYU) Grossman School of Medicine, New York, NY, United States
| | - Irineu Illa Bochaca
- Ronald O. Perelman Department of Dermatology, New York University (NYU) Grossman School of Medicine, New York, NY, United States
| | - Jamie L. Booth
- Department of Cell, Developmental, & Cancer Biology, Oregon Health & Science University, Portland, OR, United States
| | - Tina G. Asnaashari
- Department of Biomedical Engineering and Computational Biology Program, Oregon Health & Science University, Portland, OR, United States
| | - Maria M. Steele
- Ronald O. Perelman Department of Dermatology, New York University (NYU) Grossman School of Medicine, New York, NY, United States
| | - Ata S. Moshiri
- Ronald O. Perelman Department of Dermatology, New York University (NYU) Grossman School of Medicine, New York, NY, United States
| | - Hyungrok Do
- Department of Population Health, New York University (NYU) Grossman School of Medicine, New York, NY, United States
| | - Judy Zhong
- Department of Population Health, New York University (NYU) Grossman School of Medicine, New York, NY, United States
- Laura and Isaac Perlmutter Cancer Center, New York University (NYU) Langone Health, New York, NY, United States
| | - Iman Osman
- Ronald O. Perelman Department of Dermatology, New York University (NYU) Grossman School of Medicine, New York, NY, United States
- Laura and Isaac Perlmutter Cancer Center, New York University (NYU) Langone Health, New York, NY, United States
| | - Sancy A. Leachman
- Department of Dermatology, Oregon Health & Science University, Portland, OR, United States
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR, United States
| | - Takahiro Tsujikawa
- Department of Cell, Developmental, & Cancer Biology, Oregon Health & Science University, Portland, OR, United States
- Department of Otolaryngology-Head and Neck Surgery, Kyoto Prefectural University of Medicine, Kyoto, Japan
| | - Kevin P. White
- Department of Dermatology, Oregon Health & Science University, Portland, OR, United States
| | - Young H. Chang
- Department of Biomedical Engineering and Computational Biology Program, Oregon Health & Science University, Portland, OR, United States
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR, United States
| | - Amanda W. Lund
- Department of Cell, Developmental, & Cancer Biology, Oregon Health & Science University, Portland, OR, United States
- Ronald O. Perelman Department of Dermatology, New York University (NYU) Grossman School of Medicine, New York, NY, United States
- Department of Biomedical Engineering and Computational Biology Program, Oregon Health & Science University, Portland, OR, United States
- Laura and Isaac Perlmutter Cancer Center, New York University (NYU) Langone Health, New York, NY, United States
- Department of Dermatology, Oregon Health & Science University, Portland, OR, United States
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR, United States
- Department of Pathology, New York University (NYU) Grossman School of Medicine, New York, NY, United States
| |
Collapse
|
|
4
|
Kaur H, Saini SK, Thakur N, Juneja M. Survey of Denoising, Segmentation and Classification of Pancreatic Cancer Imaging. Curr Med Imaging 2024; 20:e150523216892. [PMID: 37189279 DOI: 10.2174/1573405620666230515090523] [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: 12/17/2022] [Revised: 03/10/2023] [Accepted: 04/03/2023] [Indexed: 05/17/2023]
Abstract
BACKGROUND Pancreatic cancer is one of the most serious problems that has taken many lives worldwide. The diagnostic procedure using the traditional approaches was manual by visually analyzing the large volumes of the dataset, making it time-consuming and prone to subjective errors. Hence the need for the computer-aided diagnosis system (CADs) emerged that comprises the machine and deep learning approaches for denoising, segmentation and classification of pancreatic cancer. INTRODUCTION There are different modalities used for the diagnosis of pancreatic cancer, such as Positron Emission Tomography/Computed Tomography (PET/CT), Magnetic Resonance Imaging (MRI), Multiparametric-MRI (Mp-MRI), Radiomics and Radio-genomics. Although these modalities gave remarkable results in diagnosis on the basis of different criteria. CT is the most commonly used modality that produces detailed and fine contrast images of internal organs of the body. However, it may also contain a certain amount of gaussian and rician noise that is necessary to be preprocessed before segmentation of the required region of interest (ROI) from the images and classification of cancer. METHOD This paper analyzes different methodologies used for the complete diagnosis of pancreatic cancer, including the denoising, segmentation and classification, along with the challenges and future scope for the diagnosis of pancreatic cancer. RESULT Various filters are used for denoising and image smoothening and filters as gaussian scale mixture process, non-local means, median filter, adaptive filter and average filter have been used more for better results. CONCLUSION In terms of segmentation, atlas based region-growing method proved to give better results as compared to the state of the art whereas, for the classification, deep learning approaches outperformed other methodologies to classify the images as cancerous and non- cancerous. These methodologies have proved that CAD systems have become a better solution to the ongoing research proposals for the detection of pancreatic cancer worldwide.
Collapse
Affiliation(s)
- Harjinder Kaur
- Department of UIET, University of Punjab, Chandigarh, 160014, India
| | | | - Niharika Thakur
- Department of UIET, University of Punjab, Chandigarh, 160014, India
| | - Mamta Juneja
- Department of UIET, University of Punjab, Chandigarh, 160014, India
| |
Collapse
|
|
5
|
Burlingame E, Ternes L, Lin JR, Chen YA, Kim EN, Gray JW, Chang YH. 3D multiplexed tissue imaging reconstruction and optimized region of interest (ROI) selection through deep learning model of channels embedding. FRONTIERS IN BIOINFORMATICS 2023; 3:1275402. [PMID: 37928169 PMCID: PMC10620917 DOI: 10.3389/fbinf.2023.1275402] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2023] [Accepted: 10/05/2023] [Indexed: 11/07/2023] Open
Abstract
Introduction: Tissue-based sampling and diagnosis are defined as the extraction of information from certain limited spaces and its diagnostic significance of a certain object. Pathologists deal with issues related to tumor heterogeneity since analyzing a single sample does not necessarily capture a representative depiction of cancer, and a tissue biopsy usually only presents a small fraction of the tumor. Many multiplex tissue imaging platforms (MTIs) make the assumption that tissue microarrays (TMAs) containing small core samples of 2-dimensional (2D) tissue sections are a good approximation of bulk tumors although tumors are not 2D. However, emerging whole slide imaging (WSI) or 3D tumor atlases that use MTIs like cyclic immunofluorescence (CyCIF) strongly challenge this assumption. In spite of the additional insight gathered by measuring the tumor microenvironment in WSI or 3D, it can be prohibitively expensive and time-consuming to process tens or hundreds of tissue sections with CyCIF. Even when resources are not limited, the criteria for region of interest (ROI) selection in tissues for downstream analysis remain largely qualitative and subjective as stratified sampling requires the knowledge of objects and evaluates their features. Despite the fact TMAs fail to adequately approximate whole tissue features, a theoretical subsampling of tissue exists that can best represent the tumor in the whole slide image. Methods: To address these challenges, we propose deep learning approaches to learn multi-modal image translation tasks from two aspects: 1) generative modeling approach to reconstruct 3D CyCIF representation and 2) co-embedding CyCIF image and Hematoxylin and Eosin (H&E) section to learn multi-modal mappings by a cross-domain translation for minimum representative ROI selection. Results and discussion: We demonstrate that generative modeling enables a 3D virtual CyCIF reconstruction of a colorectal cancer specimen given a small subset of the imaging data at training time. By co-embedding histology and MTI features, we propose a simple convex optimization for objective ROI selection. We demonstrate the potential application of ROI selection and the efficiency of its performance with respect to cellular heterogeneity.
Collapse
Affiliation(s)
- Erik Burlingame
- Department of Biomedical Engineering and Computational Biology Program, Oregon Health and Science University, Portland, OR, United States
| | - Luke Ternes
- Department of Biomedical Engineering and Computational Biology Program, Oregon Health and Science University, Portland, OR, United States
| | - Jia-Ren Lin
- Ludwig Center for Cancer Research at Harvard, Harvard Medical School, Boston, MA, United States
- Laboratory of Systems Pharmacology, Harvard Medical School, Boston, MA, United States
| | - Yu-An Chen
- Ludwig Center for Cancer Research at Harvard, Harvard Medical School, Boston, MA, United States
- Laboratory of Systems Pharmacology, Harvard Medical School, Boston, MA, United States
| | - Eun Na Kim
- Department of Biomedical Engineering and Computational Biology Program, Oregon Health and Science University, Portland, OR, United States
| | - Joe W. Gray
- Department of Biomedical Engineering and Computational Biology Program, Oregon Health and Science University, Portland, OR, United States
- Knight Cancer Institute, Oregon Health and Science University, Portland, OR, United States
| | - Young Hwan Chang
- Department of Biomedical Engineering and Computational Biology Program, Oregon Health and Science University, Portland, OR, United States
- Knight Cancer Institute, Oregon Health and Science University, Portland, OR, United States
| |
Collapse
|
|
6
|
Abstract
Machine learning methods have been growing in prominence across all areas of medicine. In pathology, recent advances in deep learning (DL) have enabled computational analysis of histological samples, aiding in diagnosis and characterization in multiple disease areas. In cancer, and particularly endocrine cancer, DL approaches have been shown to be useful in tasks ranging from tumor grading to gene expression prediction. This review summarizes the current state of DL research in endocrine cancer histopathology with an emphasis on experimental design, significant findings, and key limitations.
Collapse
Affiliation(s)
- Siddhi Ramesh
- Department of Medicine, Section of Hematology/Oncology, University of Chicago Medical Center, 5841 South Maryland Avenue, MC 2115, Chicago, IL 60637, USA; The University of Chicago Medicine & Biological Sciences, 5841 South Maryland Avenue, Chicago, IL, USA
| | - James M Dolezal
- Department of Medicine, Section of Hematology/Oncology, University of Chicago Medical Center, 5841 South Maryland Avenue, MC 2115, Chicago, IL 60637, USA; The University of Chicago Medicine & Biological Sciences, 5841 South Maryland Avenue, Chicago, IL, USA
| | - Alexander T Pearson
- Department of Medicine, Section of Hematology/Oncology, University of Chicago Medical Center, 5841 South Maryland Avenue, MC 2115, Chicago, IL 60637, USA; University of Chicago Comprehensive Cancer Center, Chicago, IL, USA; The University of Chicago Medicine & Biological Sciences, 5841 South Maryland Avenue, Chicago, IL, USA.
| |
Collapse
|
|
7
|
Sundaram S, Kim EN, Jones GM, Sivagnanam S, Tripathi M, Miremadi A, Di Pietro M, Coussens LM, Fitzgerald RC, Chang YH, Zhuang L. Deciphering the Immune Complexity in Esophageal Adenocarcinoma and Pre-Cancerous Lesions With Sequential Multiplex Immunohistochemistry and Sparse Subspace Clustering Approach. Front Immunol 2022; 13:874255. [PMID: 35663986 PMCID: PMC9161782 DOI: 10.3389/fimmu.2022.874255] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/11/2022] [Accepted: 04/19/2022] [Indexed: 02/05/2023] Open
Abstract
Esophageal adenocarcinoma (EAC) develops from a chronic inflammatory environment across four stages: intestinal metaplasia, known as Barrett's esophagus, low- and high-grade dysplasia, and adenocarcinoma. Although the genomic characteristics of this progression have been well defined via large-scale DNA sequencing, the dynamics of various immune cell subsets and their spatial interactions in their tumor microenvironment remain unclear. Here, we applied a sequential multiplex immunohistochemistry (mIHC) platform with computational image analysis pipelines that allow for the detection of 10 biomarkers in one formalin-fixed paraffin-embedded (FFPE) tissue section. Using this platform and quantitative image analytics, we studied changes in the immune landscape during disease progression based on 40 normal and diseased areas from endoscopic mucosal resection specimens of chemotherapy treatment- naïve patients, including normal esophagus, metaplasia, low- and high-grade dysplasia, and adenocarcinoma. The results revealed a steady increase of FOXP3+ T regulatory cells and a CD163+ myelomonocytic cell subset. In parallel to the manual gating strategy applied for cell phenotyping, we also adopted a sparse subspace clustering (SSC) algorithm allowing the automated cell phenotyping of mIHC-based single-cell data. The algorithm successfully identified comparable cell types, along with significantly enriched FOXP3 T regulatory cells and CD163+ myelomonocytic cells as found in manual gating. In addition, SCC identified a new CSF1R+CD1C+ myeloid lineage, which not only was previously unknown in this disease but also increases with advancing disease stages. This study revealed immune dynamics in EAC progression and highlighted the potential application of a new multiplex imaging platform, combined with computational image analysis on routine clinical FFPE sections, to investigate complex immune populations in tumor ecosystems.
Collapse
Affiliation(s)
- Srinand Sundaram
- Medical Research Council (MRC) Cancer Unit, Hutchison-Medical Research Council (MRC) Research Centre, University of Cambridge, Cambridge, United Kingdom
| | - Eun Na Kim
- Department of Biomedical Engineering, Oregon Health and Science University, Portland, OR, United States
| | - Georgina M. Jones
- Medical Research Council (MRC) Cancer Unit, Hutchison-Medical Research Council (MRC) Research Centre, University of Cambridge, Cambridge, United Kingdom
| | - Shamilene Sivagnanam
- Department of Cell, Developmental & Cancer Biology, Oregon Health and Science University, Portland, OR, United States
| | - Monika Tripathi
- Medical Research Council (MRC) Cancer Unit, Hutchison-Medical Research Council (MRC) Research Centre, University of Cambridge, Cambridge, United Kingdom
| | - Ahmad Miremadi
- Medical Research Council (MRC) Cancer Unit, Hutchison-Medical Research Council (MRC) Research Centre, University of Cambridge, Cambridge, United Kingdom
| | - Massimiliano Di Pietro
- Medical Research Council (MRC) Cancer Unit, Hutchison-Medical Research Council (MRC) Research Centre, University of Cambridge, Cambridge, United Kingdom
| | - Lisa M. Coussens
- Department of Cell, Developmental & Cancer Biology, Oregon Health and Science University, Portland, OR, United States
- Knight Cancer Institute, Oregon Health and Science University, Portland, OR, United States
| | - Rebecca C. Fitzgerald
- Medical Research Council (MRC) Cancer Unit, Hutchison-Medical Research Council (MRC) Research Centre, University of Cambridge, Cambridge, United Kingdom
| | - Young Hwan Chang
- Department of Biomedical Engineering, Oregon Health and Science University, Portland, OR, United States
- Knight Cancer Institute, Oregon Health and Science University, Portland, OR, United States
| | - Lizhe Zhuang
- Medical Research Council (MRC) Cancer Unit, Hutchison-Medical Research Council (MRC) Research Centre, University of Cambridge, Cambridge, United Kingdom
| |
Collapse
|
|
8
|
Budak C, Mençik V. Detection of ring cell cancer in histopathological images with region of interest determined by SLIC superpixels method. Neural Comput Appl 2022. [DOI: 10.1007/s00521-022-07183-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
|
9
|
A new lightweight convolutional neural network for radiation-induced liver disease classification. Biomed Signal Process Control 2022. [DOI: 10.1016/j.bspc.2021.103463] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
|
|
10
|
Johnson BE, Creason AL, Stommel JM, Keck JM, Parmar S, Betts CB, Blucher A, Boniface C, Bucher E, Burlingame E, Camp T, Chin K, Eng J, Estabrook J, Feiler HS, Heskett MB, Hu Z, Kolodzie A, Kong BL, Labrie M, Lee J, Leyshock P, Mitri S, Patterson J, Riesterer JL, Sivagnanam S, Somers J, Sudar D, Thibault G, Weeder BR, Zheng C, Nan X, Thompson RF, Heiser LM, Spellman PT, Thomas G, Demir E, Chang YH, Coussens LM, Guimaraes AR, Corless C, Goecks J, Bergan R, Mitri Z, Mills GB, Gray JW. An omic and multidimensional spatial atlas from serial biopsies of an evolving metastatic breast cancer. Cell Rep Med 2022; 3:100525. [PMID: 35243422 PMCID: PMC8861971 DOI: 10.1016/j.xcrm.2022.100525] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2021] [Revised: 11/15/2021] [Accepted: 01/19/2022] [Indexed: 12/15/2022]
Abstract
Mechanisms of therapeutic resistance and vulnerability evolve in metastatic cancers as tumor cells and extrinsic microenvironmental influences change during treatment. To support the development of methods for identifying these mechanisms in individual people, here we present an omic and multidimensional spatial (OMS) atlas generated from four serial biopsies of an individual with metastatic breast cancer during 3.5 years of therapy. This resource links detailed, longitudinal clinical metadata that includes treatment times and doses, anatomic imaging, and blood-based response measurements to clinical and exploratory analyses, which includes comprehensive DNA, RNA, and protein profiles; images of multiplexed immunostaining; and 2- and 3-dimensional scanning electron micrographs. These data report aspects of heterogeneity and evolution of the cancer genome, signaling pathways, immune microenvironment, cellular composition and organization, and ultrastructure. We present illustrative examples of how integrative analyses of these data reveal potential mechanisms of response and resistance and suggest novel therapeutic vulnerabilities.
Collapse
Affiliation(s)
- Brett E. Johnson
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
| | - Allison L. Creason
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
| | - Jayne M. Stommel
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
| | - Jamie M. Keck
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
| | - Swapnil Parmar
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
| | - Courtney B. Betts
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Cell, Developmental & Cancer Biology, Oregon Health & Science University, Portland, OR 97239, USA
| | - Aurora Blucher
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Cell, Developmental & Cancer Biology, Oregon Health & Science University, Portland, OR 97239, USA
| | - Christopher Boniface
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
- Cancer Early Detection Advanced Research Center, Oregon Health & Science University, Portland, OR 97239, USA
| | - Elmar Bucher
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
| | - Erik Burlingame
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
- Computational Biology Program, Oregon Health & Science University, Portland, OR 97239, USA
| | - Todd Camp
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
| | - Koei Chin
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
| | - Jennifer Eng
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
| | - Joseph Estabrook
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Molecular and Medical Genetics, Oregon Health & Science University, Portland, OR 97239, USA
| | - Heidi S. Feiler
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
| | - Michael B. Heskett
- Department of Molecular and Medical Genetics, Oregon Health & Science University, Portland, OR 97239, USA
| | - Zhi Hu
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
| | - Annette Kolodzie
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
| | - Ben L. Kong
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Pharmacy Services, Oregon Health & Science University, Portland, OR 97239, USA
| | - Marilyne Labrie
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Cell, Developmental & Cancer Biology, Oregon Health & Science University, Portland, OR 97239, USA
| | - Jinho Lee
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
| | - Patrick Leyshock
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
| | - Souraya Mitri
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
| | - Janice Patterson
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Knight Diagnostic Laboratories, Oregon Health & Science University, Portland, OR 97239, USA
| | - Jessica L. Riesterer
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
- Multiscale Microscopy Core, Oregon Health & Science University, Portland, OR 97239, USA
| | - Shamilene Sivagnanam
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Cell, Developmental & Cancer Biology, Oregon Health & Science University, Portland, OR 97239, USA
- Computational Biology Program, Oregon Health & Science University, Portland, OR 97239, USA
| | - Julia Somers
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Molecular and Medical Genetics, Oregon Health & Science University, Portland, OR 97239, USA
| | - Damir Sudar
- Quantitative Imaging Systems LLC, Portland, OR 97239, USA
| | - Guillaume Thibault
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
| | - Benjamin R. Weeder
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
| | - Christina Zheng
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
| | - Xiaolin Nan
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
- Cancer Early Detection Advanced Research Center, Oregon Health & Science University, Portland, OR 97239, USA
| | - Reid F. Thompson
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
- Division of Hospital and Specialty Medicine, VA Portland Healthcare System, Portland, OR 97239, USA
| | - Laura M. Heiser
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
| | - Paul T. Spellman
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Molecular and Medical Genetics, Oregon Health & Science University, Portland, OR 97239, USA
| | - George Thomas
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Pathology & Laboratory Medicine, Oregon Health & Science University, Portland, OR 97239, USA
| | - Emek Demir
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Molecular and Medical Genetics, Oregon Health & Science University, Portland, OR 97239, USA
| | - Young Hwan Chang
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
- Computational Biology Program, Oregon Health & Science University, Portland, OR 97239, USA
| | - Lisa M. Coussens
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Cell, Developmental & Cancer Biology, Oregon Health & Science University, Portland, OR 97239, USA
| | - Alexander R. Guimaraes
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Diagnostic Radiology, Oregon Health & Science University, Portland, OR 97239, USA
| | - Christopher Corless
- Department of Pharmacy Services, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Pathology & Laboratory Medicine, Oregon Health & Science University, Portland, OR 97239, USA
| | - Jeremy Goecks
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
| | - Raymond Bergan
- Fred & Pamela Buffett Cancer Center, University of Nebraska Medical Center, Omaha, NE 68198, USA
| | - Zahi Mitri
- Division of Hematology & Medical Oncology, Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Medicine, Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
| | - Gordon B. Mills
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Cell, Developmental & Cancer Biology, Oregon Health & Science University, Portland, OR 97239, USA
| | - Joe W. Gray
- Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97239, USA
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA
| |
Collapse
|
|
11
|
Eksi SE, Chitsazan A, Sayar Z, Thomas GV, Fields AJ, Kopp RP, Spellman PT, Adey AC. Epigenetic loss of heterogeneity from low to high grade localized prostate tumours. Nat Commun 2021; 12:7292. [PMID: 34911933 PMCID: PMC8674326 DOI: 10.1038/s41467-021-27615-8] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2021] [Accepted: 11/30/2021] [Indexed: 12/13/2022] Open
Abstract
Identifying precise molecular subtypes attributable to specific stages of localized prostate cancer has proven difficult due to high levels of heterogeneity. Bulk assays represent a population-average, which mask the heterogeneity that exists at the single-cell level. In this work, we sequence the accessible chromatin regions of 14,424 single-cells from 18 flash-frozen prostate tumours. We observe shared chromatin features among low-grade prostate cancer cells are lost in high-grade tumours. Despite this loss, high-grade tumours exhibit an enrichment for FOXA1, HOXB13 and CDX2 transcription factor binding sites, indicating a shared trans-regulatory programme. We identify two unique genes encoding neuronal adhesion molecules that are highly accessible in high-grade prostate tumours. We show NRXN1 and NLGN1 expression in epithelial, endothelial, immune and neuronal cells in prostate cancer using cyclic immunofluorescence. Our results provide a deeper understanding of the active gene regulatory networks in primary prostate tumours, critical for molecular stratification of the disease.
Collapse
Affiliation(s)
- Sebnem Ece Eksi
- Cancer Early Detection Advanced Research (CEDAR), Knight Cancer Institute, OHSU, Portland, OR, 97239, USA.
- Department of Biomedical Engineering, School of Medicine, OHSU, Portland, OR, 97209, USA.
| | - Alex Chitsazan
- Cancer Early Detection Advanced Research (CEDAR), Knight Cancer Institute, OHSU, Portland, OR, 97239, USA
| | - Zeynep Sayar
- Cancer Early Detection Advanced Research (CEDAR), Knight Cancer Institute, OHSU, Portland, OR, 97239, USA
- Department of Biomedical Engineering, School of Medicine, OHSU, Portland, OR, 97209, USA
| | - George V Thomas
- Cancer Early Detection Advanced Research (CEDAR), Knight Cancer Institute, OHSU, Portland, OR, 97239, USA
- Department of Pathology & Laboratory Medicine, School of Medicine, OHSU, Portland, OR, 97239, USA
| | - Andrew J Fields
- Department of Molecular and Medical Genetics, School of Medicine, OHSU, Portland, OR, 97239, USA
| | - Ryan P Kopp
- Department of Urology, School of Medicine, OHSU, Portland, OR, 97239, USA
| | - Paul T Spellman
- Cancer Early Detection Advanced Research (CEDAR), Knight Cancer Institute, OHSU, Portland, OR, 97239, USA
- Department of Molecular and Medical Genetics, School of Medicine, OHSU, Portland, OR, 97239, USA
| | - Andrew C Adey
- Cancer Early Detection Advanced Research (CEDAR), Knight Cancer Institute, OHSU, Portland, OR, 97239, USA.
- Department of Molecular and Medical Genetics, School of Medicine, OHSU, Portland, OR, 97239, USA.
| |
Collapse
|
|
12
|
Dietz MS, Sutton TL, Walker BS, Gast CE, Zarour L, Sengupta SK, Swain JR, Eng J, Parappilly M, Limbach K, Sattler A, Burlingame E, Chin Y, Gower A, Mira JLM, Sapre A, Chiu YJ, Clayburgh DR, Pommier SJ, Cetnar JP, Fischer JM, Jaboin JJ, Pommier RF, Sheppard BC, Tsikitis VL, Skalet AH, Mayo SC, Lopez CD, Gray JW, Mills GB, Mitri Z, Chang YH, Chin K, Wong MH. Relevance of circulating hybrid cells as a non-invasive biomarker for myriad solid tumors. Sci Rep 2021; 11:13630. [PMID: 34211050 PMCID: PMC8249418 DOI: 10.1038/s41598-021-93053-7] [Citation(s) in RCA: 30] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2021] [Accepted: 06/09/2021] [Indexed: 02/06/2023] Open
Abstract
Metastatic progression defines the final stages of tumor evolution and underlies the majority of cancer-related deaths. The heterogeneity in disseminated tumor cell populations capable of seeding and growing in distant organ sites contributes to the development of treatment resistant disease. We recently reported the identification of a novel tumor-derived cell population, circulating hybrid cells (CHCs), harboring attributes from both macrophages and neoplastic cells, including functional characteristics important to metastatic spread. These disseminated hybrids outnumber conventionally defined circulating tumor cells (CTCs) in cancer patients. It is unknown if CHCs represent a generalized cancer mechanism for cell dissemination, or if this population is relevant to the metastatic cascade. Herein, we detect CHCs in the peripheral blood of patients with cancer in myriad disease sites encompassing epithelial and non-epithelial malignancies. Further, we demonstrate that in vivo-derived hybrid cells harbor tumor-initiating capacity in murine cancer models and that CHCs from human breast cancer patients express stem cell antigens, features consistent with the potential to seed and grow at metastatic sites. Finally, we reveal heterogeneity of CHC phenotypes reflect key tumor features, including oncogenic mutations and functional protein expression. Importantly, this novel population of disseminated neoplastic cells opens a new area in cancer biology and renewed opportunity for battling metastatic disease.
Collapse
Affiliation(s)
- Matthew S Dietz
- Department of Pediatrics, Oregon Health & Science University (OHSU), Portland, OR, 97239, USA.,Department of Pediatrics, University of Utah, Salt Lake City, UT, 84113, USA
| | | | | | - Charles E Gast
- Department of Cell, Developmental and Cancer Biology, Oregon Health & Science University, 2720 S. Moody Ave., Mailcode KC-CDCB, Portland, OR, 97201, USA
| | - Luai Zarour
- Department of Surgery, OHSU, Portland, OR, 97239, USA.,Department of General Surgery, Legacy Medical Group, Gresham, OR, 97030, USA
| | - Sidharth K Sengupta
- Department of Cell, Developmental and Cancer Biology, Oregon Health & Science University, 2720 S. Moody Ave., Mailcode KC-CDCB, Portland, OR, 97201, USA
| | - John R Swain
- Department of Cell, Developmental and Cancer Biology, Oregon Health & Science University, 2720 S. Moody Ave., Mailcode KC-CDCB, Portland, OR, 97201, USA
| | - Jennifer Eng
- Department of Biomedical Engineering, OHSU, Portland, OR, 97239, USA
| | - Michael Parappilly
- Department of Cell, Developmental and Cancer Biology, Oregon Health & Science University, 2720 S. Moody Ave., Mailcode KC-CDCB, Portland, OR, 97201, USA
| | | | - Ariana Sattler
- Department of Cell, Developmental and Cancer Biology, Oregon Health & Science University, 2720 S. Moody Ave., Mailcode KC-CDCB, Portland, OR, 97201, USA
| | - Erik Burlingame
- Department of Biomedical Engineering, OHSU, Portland, OR, 97239, USA.,Computational Biology Program, OHSU, Portland, OR, 97239, USA
| | - Yuki Chin
- Department of Cell, Developmental and Cancer Biology, Oregon Health & Science University, 2720 S. Moody Ave., Mailcode KC-CDCB, Portland, OR, 97201, USA
| | - Austin Gower
- Cancer Early Detection Advanced Research Center, OHSU, Portland, OR, 97201, USA
| | - Jose L Montoya Mira
- Department of Biomedical Engineering, OHSU, Portland, OR, 97239, USA.,Cancer Early Detection Advanced Research Center, OHSU, Portland, OR, 97201, USA
| | - Ajay Sapre
- Cancer Early Detection Advanced Research Center, OHSU, Portland, OR, 97201, USA
| | - Yu-Jui Chiu
- Cancer Early Detection Advanced Research Center, OHSU, Portland, OR, 97201, USA
| | - Daniel R Clayburgh
- Department of Otolaryngology, OHSU, Portland, OR, 97239, USA.,Operative Care Division, Portland Veterans Affairs Medical Center, Portland, OR, 97239, USA.,The Knight Cancer Institute, OHSU, Portland, OR, 97201, USA
| | | | - Jeremy P Cetnar
- The Knight Cancer Institute, OHSU, Portland, OR, 97201, USA.,Department of Medicine, OHSU, Portland, OR, 97239, USA
| | - Jared M Fischer
- Cancer Early Detection Advanced Research Center, OHSU, Portland, OR, 97201, USA.,The Knight Cancer Institute, OHSU, Portland, OR, 97201, USA.,Department of Molecule and Medical Genetics, OHSU, Portland, OR, 97239, USA
| | - Jerry J Jaboin
- The Knight Cancer Institute, OHSU, Portland, OR, 97201, USA.,Department of Radiation Medicine, OHSU, Portland, OR, 97239, USA
| | - Rodney F Pommier
- Department of Surgery, OHSU, Portland, OR, 97239, USA.,The Knight Cancer Institute, OHSU, Portland, OR, 97201, USA
| | - Brett C Sheppard
- Department of Surgery, OHSU, Portland, OR, 97239, USA.,The Knight Cancer Institute, OHSU, Portland, OR, 97201, USA
| | | | - Alison H Skalet
- The Knight Cancer Institute, OHSU, Portland, OR, 97201, USA.,Casey Eye Institute, OHSU, Portland, OR, 97239, USA
| | - Skye C Mayo
- Department of Surgery, OHSU, Portland, OR, 97239, USA.,The Knight Cancer Institute, OHSU, Portland, OR, 97201, USA
| | - Charles D Lopez
- The Knight Cancer Institute, OHSU, Portland, OR, 97201, USA.,Department of Medicine, OHSU, Portland, OR, 97239, USA
| | - Joe W Gray
- Department of Biomedical Engineering, OHSU, Portland, OR, 97239, USA.,The Knight Cancer Institute, OHSU, Portland, OR, 97201, USA
| | - Gordon B Mills
- Department of Cell, Developmental and Cancer Biology, Oregon Health & Science University, 2720 S. Moody Ave., Mailcode KC-CDCB, Portland, OR, 97201, USA.,The Knight Cancer Institute, OHSU, Portland, OR, 97201, USA
| | - Zahi Mitri
- The Knight Cancer Institute, OHSU, Portland, OR, 97201, USA.,Department of Medicine, OHSU, Portland, OR, 97239, USA
| | - Young Hwan Chang
- Department of Biomedical Engineering, OHSU, Portland, OR, 97239, USA.,Computational Biology Program, OHSU, Portland, OR, 97239, USA.,The Knight Cancer Institute, OHSU, Portland, OR, 97201, USA
| | - Koei Chin
- Department of Biomedical Engineering, OHSU, Portland, OR, 97239, USA.,The Knight Cancer Institute, OHSU, Portland, OR, 97201, USA
| | - Melissa H Wong
- Department of Cell, Developmental and Cancer Biology, Oregon Health & Science University, 2720 S. Moody Ave., Mailcode KC-CDCB, Portland, OR, 97201, USA. .,The Knight Cancer Institute, OHSU, Portland, OR, 97201, USA.
| |
Collapse
|
|
13
|
Kobayashi S, Saltz JH, Yang VW. State of machine and deep learning in histopathological applications in digestive diseases. World J Gastroenterol 2021; 27:2545-2575. [PMID: 34092975 PMCID: PMC8160628 DOI: 10.3748/wjg.v27.i20.2545] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/28/2021] [Revised: 03/27/2021] [Accepted: 04/29/2021] [Indexed: 02/06/2023] Open
Abstract
Machine learning (ML)- and deep learning (DL)-based imaging modalities have exhibited the capacity to handle extremely high dimensional data for a number of computer vision tasks. While these approaches have been applied to numerous data types, this capacity can be especially leveraged by application on histopathological images, which capture cellular and structural features with their high-resolution, microscopic perspectives. Already, these methodologies have demonstrated promising performance in a variety of applications like disease classification, cancer grading, structure and cellular localizations, and prognostic predictions. A wide range of pathologies requiring histopathological evaluation exist in gastroenterology and hepatology, indicating these as disciplines highly targetable for integration of these technologies. Gastroenterologists have also already been primed to consider the impact of these algorithms, as development of real-time endoscopic video analysis software has been an active and popular field of research. This heightened clinical awareness will likely be important for future integration of these methods and to drive interdisciplinary collaborations on emerging studies. To provide an overview on the application of these methodologies for gastrointestinal and hepatological histopathological slides, this review will discuss general ML and DL concepts, introduce recent and emerging literature using these methods, and cover challenges moving forward to further advance the field.
Collapse
Affiliation(s)
- Soma Kobayashi
- Department of Biomedical Informatics, Renaissance School of Medicine, Stony Brook University, Stony Brook, NY 11794, United States
| | - Joel H Saltz
- Department of Biomedical Informatics, Renaissance School of Medicine, Stony Brook University, Stony Brook, NY 11794, United States
| | - Vincent W Yang
- Department of Medicine, Renaissance School of Medicine, Stony Brook University, Stony Brook, NY 11794, United States
- Department of Physiology and Biophysics, Renaissance School of Medicine, Stony Brook University, Stony Brook , NY 11794, United States
| |
Collapse
|
|
14
|
Fu H, Mi W, Pan B, Guo Y, Li J, Xu R, Zheng J, Zou C, Zhang T, Liang Z, Zou J, Zou H. Automatic Pancreatic Ductal Adenocarcinoma Detection in Whole Slide Images Using Deep Convolutional Neural Networks. Front Oncol 2021; 11:665929. [PMID: 34249702 PMCID: PMC8267174 DOI: 10.3389/fonc.2021.665929] [Citation(s) in RCA: 21] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2021] [Accepted: 06/10/2021] [Indexed: 01/11/2023] Open
Abstract
Pancreatic ductal adenocarcinoma (PDAC) is one of the deadliest cancer types worldwide, with the lowest 5-year survival rate among all kinds of cancers. Histopathology image analysis is considered a gold standard for PDAC detection and diagnosis. However, the manual diagnosis used in current clinical practice is a tedious and time-consuming task and diagnosis concordance can be low. With the development of digital imaging and machine learning, several scholars have proposed PDAC analysis approaches based on feature extraction methods that rely on field knowledge. However, feature-based classification methods are applicable only to a specific problem and lack versatility, so that the deep-learning method is becoming a vital alternative to feature extraction. This paper proposes the first deep convolutional neural network architecture for classifying and segmenting pancreatic histopathological images on a relatively large WSI dataset. Our automatic patch-level approach achieved 95.3% classification accuracy and the WSI-level approach achieved 100%. Additionally, we visualized the classification and segmentation outcomes of histopathological images to determine which areas of an image are more important for PDAC identification. Experimental results demonstrate that our proposed model can effectively diagnose PDAC using histopathological images, which illustrates the potential of this practical application.
Collapse
Affiliation(s)
- Hao Fu
- Department of Automation, School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China
| | - Weiming Mi
- Department of Automation, School of Information Science and Technology, Tsinghua University, Beijing, China
| | - Boju Pan
- Molecular Pathology Research Center, Department of Pathology, Peking Union Medical College Hospital (PUMCH), Peking Union Medical College and Chinese Academy of Medical Sciences, Beijing, China
| | - Yucheng Guo
- Yihai Center, Tsimage Medical Technology, Shenzhen, China
- Center for Intelligent Medical Imaging & Health, Research Institute of Tsinghua University in Shenzhen, Shenzhen, China
| | - Junjie Li
- Molecular Pathology Research Center, Department of Pathology, Peking Union Medical College Hospital (PUMCH), Peking Union Medical College and Chinese Academy of Medical Sciences, Beijing, China
| | - Rongyan Xu
- Shanghai Chenshan Plant Science Research Center, Chinese Academy of Sciences, Shanghai, China
| | - Jie Zheng
- Yihai Center, Tsimage Medical Technology, Shenzhen, China
- Center for Intelligent Medical Imaging & Health, Research Institute of Tsinghua University in Shenzhen, Shenzhen, China
| | - Chunli Zou
- Yihai Center, Tsimage Medical Technology, Shenzhen, China
- Center for Intelligent Medical Imaging & Health, Research Institute of Tsinghua University in Shenzhen, Shenzhen, China
| | - Tao Zhang
- Department of Automation, School of Information Science and Technology, Tsinghua University, Beijing, China
| | - Zhiyong Liang
- Molecular Pathology Research Center, Department of Pathology, Peking Union Medical College Hospital (PUMCH), Peking Union Medical College and Chinese Academy of Medical Sciences, Beijing, China
- *Correspondence: Zhiyong Liang, ; Hao Zou, ; Junzhong Zou,
| | - Junzhong Zou
- Department of Automation, School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China
- *Correspondence: Zhiyong Liang, ; Hao Zou, ; Junzhong Zou,
| | - Hao Zou
- Yihai Center, Tsimage Medical Technology, Shenzhen, China
- Center for Intelligent Medical Imaging & Health, Research Institute of Tsinghua University in Shenzhen, Shenzhen, China
- *Correspondence: Zhiyong Liang, ; Hao Zou, ; Junzhong Zou,
| |
Collapse
|
|
15
|
Burlingame EA, McDonnell M, Schau GF, Thibault G, Lanciault C, Morgan T, Johnson BE, Corless C, Gray JW, Chang YH. SHIFT: speedy histological-to-immunofluorescent translation of a tumor signature enabled by deep learning. Sci Rep 2020; 10:17507. [PMID: 33060677 PMCID: PMC7566625 DOI: 10.1038/s41598-020-74500-3] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2020] [Accepted: 09/28/2020] [Indexed: 02/07/2023] Open
Abstract
Spatially-resolved molecular profiling by immunostaining tissue sections is a key feature in cancer diagnosis, subtyping, and treatment, where it complements routine histopathological evaluation by clarifying tumor phenotypes. In this work, we present a deep learning-based method called speedy histological-to-immunofluorescent translation (SHIFT) which takes histologic images of hematoxylin and eosin (H&E)-stained tissue as input, then in near-real time returns inferred virtual immunofluorescence (IF) images that estimate the underlying distribution of the tumor cell marker pan-cytokeratin (panCK). To build a dataset suitable for learning this task, we developed a serial staining protocol which allows IF and H&E images from the same tissue to be spatially registered. We show that deep learning-extracted morphological feature representations of histological images can guide representative sample selection, which improved SHIFT generalizability in a small but heterogenous set of human pancreatic cancer samples. With validation in larger cohorts, SHIFT could serve as an efficient preliminary, auxiliary, or substitute for panCK IF by delivering virtual panCK IF images for a fraction of the cost and in a fraction of the time required by traditional IF.
Collapse
Affiliation(s)
- Erik A Burlingame
- Computational Biology Program, Department of Biomedical Engineering, Oregon Health and Science University, Portland, OR, USA
- OHSU Center for Spatial Systems Biomedicine, Department of Biomedical Engineering, Oregon Health and Science University, Portland, OR, USA
| | - Mary McDonnell
- OHSU Center for Spatial Systems Biomedicine, Department of Biomedical Engineering, Oregon Health and Science University, Portland, OR, USA
| | - Geoffrey F Schau
- Computational Biology Program, Department of Biomedical Engineering, Oregon Health and Science University, Portland, OR, USA
- OHSU Center for Spatial Systems Biomedicine, Department of Biomedical Engineering, Oregon Health and Science University, Portland, OR, USA
| | - Guillaume Thibault
- OHSU Center for Spatial Systems Biomedicine, Department of Biomedical Engineering, Oregon Health and Science University, Portland, OR, USA
| | - Christian Lanciault
- Department of Pathology, Oregon Health and Science University, Portland, OR, USA
| | - Terry Morgan
- Department of Pathology, Oregon Health and Science University, Portland, OR, USA
| | - Brett E Johnson
- OHSU Center for Spatial Systems Biomedicine, Department of Biomedical Engineering, Oregon Health and Science University, Portland, OR, USA
| | - Christopher Corless
- Knight Diagnostic Laboratories, Oregon Health and Science University, Portland, OR, USA
- Knight Cancer Institute, Oregon Health and Science University, Portland, OR, USA
| | - Joe W Gray
- OHSU Center for Spatial Systems Biomedicine, Department of Biomedical Engineering, Oregon Health and Science University, Portland, OR, USA
- Knight Cancer Institute, Oregon Health and Science University, Portland, OR, USA
- Brenden-Colson Center for Pancreatic Care, Oregon Health and Science University, Portland, OR, USA
| | - Young Hwan Chang
- Computational Biology Program, Department of Biomedical Engineering, Oregon Health and Science University, Portland, OR, USA.
- OHSU Center for Spatial Systems Biomedicine, Department of Biomedical Engineering, Oregon Health and Science University, Portland, OR, USA.
- Brenden-Colson Center for Pancreatic Care, Oregon Health and Science University, Portland, OR, USA.
| |
Collapse
|
|
16
|
Jackson CR, Sriharan A, Vaickus LJ. A machine learning algorithm for simulating immunohistochemistry: development of SOX10 virtual IHC and evaluation on primarily melanocytic neoplasms. Mod Pathol 2020; 33:1638-1648. [PMID: 32238879 PMCID: PMC10811656 DOI: 10.1038/s41379-020-0526-z] [Citation(s) in RCA: 21] [Impact Index Per Article: 4.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2020] [Revised: 03/08/2020] [Accepted: 03/09/2020] [Indexed: 11/08/2022]
Abstract
Immunohistochemistry (IHC) is a diagnostic technique used throughout pathology. A machine learning algorithm that could predict individual cell immunophenotype based on hematoxylin and eosin (H&E) staining would save money, time, and reduce tissue consumed. Prior approaches have lacked the spatial accuracy needed for cell-specific analytical tasks. Here IHC performed on destained H&E slides is used to create a neural network that is potentially capable of predicting individual cell immunophenotype. Twelve slides were stained with H&E and scanned to create digital whole slide images. The H&E slides were then destained, and stained with SOX10 IHC. The SOX10 IHC slides were scanned, and corresponding H&E and IHC digital images were registered. Color-thresholding and machine learning techniques were applied to the registered H&E and IHC images to segment 3,396,668 SOX10-negative cells and 306,166 SOX10-positive cells. The resulting segmentation was used to annotate the original H&E images, and a convolutional neural network was trained to predict SOX10 nuclear staining. Sixteen thousand three hundred and nine image patches were used to train the virtual IHC (vIHC) neural network, and 1,813 image patches were used to quantitatively evaluate it. The resulting vIHC neural network achieved an area under the curve of 0.9422 in a receiver operator characteristics analysis when sorting individual nuclei. The vIHC network was applied to additional images from clinical practice, and was evaluated qualitatively by a board-certified dermatopathologist. Further work is needed to make the process more efficient and accurate for clinical use. This proof-of-concept demonstrates the feasibility of creating neural network-driven vIHC assays.
Collapse
Affiliation(s)
- Christopher R Jackson
- Department of Pathology and Laboratory Medicine, Dartmouth-Hitchcock Medical Center, Lebanon, NH, USA.
| | - Aravindhan Sriharan
- Department of Pathology and Laboratory Medicine, Dartmouth-Hitchcock Medical Center, Lebanon, NH, USA
| | - Louis J Vaickus
- Department of Pathology and Laboratory Medicine, Dartmouth-Hitchcock Medical Center, Lebanon, NH, USA
| |
Collapse
|
|
17
|
Mitchell E, Jindal S, Chan T, Narasimhan J, Sivagnanam S, Gray E, Chang YH, Weinmann S, Schedin P. Loss of myoepithelial calponin-1 characterizes high-risk ductal carcinoma in situ cases, which are further stratified by T cell composition. Mol Carcinog 2020; 59:701-712. [PMID: 32134153 PMCID: PMC7317523 DOI: 10.1002/mc.23171] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2020] [Revised: 02/14/2020] [Accepted: 02/15/2020] [Indexed: 12/15/2022]
Abstract
A hallmark of ductal carcinoma in situ (DCIS) progression is a loss of the surrounding ductal myoepithelium. However, whether compromise in myoepithelial differentiation, rather than overt cellular loss, can be used to predict the risk of DCIS progression is unknown. Here we address this question utilizing pure and mixed DCIS cases (N = 30) as surrogates for DCIS at low and high risk for progression, respectively. We used multiplex immunohistochemical staining to evaluate the relationship between myoepithelial cell differentiation and lymphoid immune cell types associated with poor prognostic DCIS. Our results show that myoepithelial calponin-1 discriminates between pure and mixed DCIS lesions better than histological subtype, presence of necrosis, or nuclear grade. Additionally, focal loss of myoepithelial cells associated with increased PD-1+CD8+ T cells, which suggests a link between the myoepithelium and immune surveillance. To identify associations between calponin-1 expression and immune response, we performed unsupervised hierarchical clustering of myoepithelial and immune cell biomarkers on 219 DCIS lesions from 30 cases. Notably, the majority of pure (low-risk) DCIS lesions clustered in a high calponin-1, T cell low group, whereas the majority of mixed (high-risk) DCIS lesions clustered in a low calponin-1, T cell high group, specifically with CD8+ and PD-1+CD8+ T cells. However, a subset of pure DCIS lesions had a similar calponin-1 and immune signature as the majority of mixed DCIS lesions, which have low calponin-1 and T cell enrichment-raising the possibility that these pure DCIS lesions might be at a high risk for progression.
Collapse
Affiliation(s)
- Elizabeth Mitchell
- Department of Cell, Developmental, and Cancer BiologyOregon Health and Science UniversityPortlandOregon
| | - Sonali Jindal
- Department of Cell, Developmental, and Cancer BiologyOregon Health and Science UniversityPortlandOregon
- Cancer Prevention and Control, Knight Cancer InstituteOregon Health and Science UniversityPortlandOregon
| | - Tiffany Chan
- Department of Cell, Developmental, and Cancer BiologyOregon Health and Science UniversityPortlandOregon
| | - Jayasri Narasimhan
- Department of Cell, Developmental, and Cancer BiologyOregon Health and Science UniversityPortlandOregon
| | - Shamilene Sivagnanam
- Computational Biology Program, Department of Cell, Developmental, and Cancer BiologyOregon Health and Science UniversityPortlandOregon
| | - Elliot Gray
- Department of Biomedical Engineering, Oregon Center for Spatial Systems BiomedicineOregon Health and Science UniversityPortlandOregon
| | - Young Hwan Chang
- Department of Biomedical Engineering, Oregon Center for Spatial Systems BiomedicineOregon Health and Science UniversityPortlandOregon
| | - Sheila Weinmann
- Center for Health ResearchKaiser Permanente NorthwestPortlandOregon
| | - Pepper Schedin
- Department of Cell, Developmental, and Cancer BiologyOregon Health and Science UniversityPortlandOregon
- Cancer Prevention and Control, Knight Cancer InstituteOregon Health and Science UniversityPortlandOregon
| |
Collapse
|
|
18
|
RESTORE: Robust intEnSiTy nORmalization mEthod for multiplexed imaging. Commun Biol 2020; 3:111. [PMID: 32152447 PMCID: PMC7062831 DOI: 10.1038/s42003-020-0828-1] [Citation(s) in RCA: 29] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/11/2019] [Accepted: 02/12/2020] [Indexed: 12/29/2022] Open
Abstract
Recent advances in multiplexed imaging technologies promise to improve the understanding of the functional states of individual cells and the interactions between the cells in tissues. This often requires compilation of results from multiple samples. However, quantitative integration of information between samples is complicated by variations in staining intensity and background fluorescence that obscure biological variations. Failure to remove these unwanted artifacts will complicate downstream analysis and diminish the value of multiplexed imaging for clinical applications. Here, to compensate for unwanted variations, we automatically identify negative control cells for each marker within the same tissue and use their expression levels to infer background signal level. The intensity profile is normalized by the inferred level of the negative control cells to remove between-sample variation. Using a tissue microarray data and a pair of longitudinal biopsy samples, we demonstrated that the proposed approach can remove unwanted variations effectively and shows robust performance. Chang et al. develop an analytical method called RESTORE to control for variations due to technical artifacts in multiplexed imaging. They test their method on a CycIF stained tissue microarray dataset and biopsies processed at different times. Their method can improve the applicability of imaging techniques in diagnostics and inference using unbiased clustering methods.
Collapse
|
|
19
|
Tsujikawa T, Thibault G, Azimi V, Sivagnanam S, Banik G, Means C, Kawashima R, Clayburgh DR, Gray JW, Coussens LM, Chang YH. Robust Cell Detection and Segmentation for Image Cytometry Reveal Th17 Cell Heterogeneity. Cytometry A 2019; 95:389-398. [PMID: 30714674 DOI: 10.1002/cyto.a.23726] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/23/2018] [Revised: 10/30/2018] [Accepted: 01/14/2019] [Indexed: 01/04/2023]
Abstract
Image cytometry enables quantitative cell characterization with preserved tissue architecture; thus, it has been highlighted in the advancement of multiplex immunohistochemistry (IHC) and digital image analysis in the context of immune-based biomarker monitoring associated with cancer immunotherapy. However, one of the challenges in the current image cytometry methodology is a technical limitation in the segmentation of nuclei and cellular components particularly in heterogeneously stained cancer tissue images. To improve the detection and specificity of single-cell segmentation in hematoxylin-stained images (which can be utilized for recently reported 12-biomarker chromogenic sequential multiplex IHC), we adapted a segmentation algorithm previously developed for hematoxlin and eosin-stained images, where morphological features are extracted based on Gabor-filtering, followed by stacking of image pixels into n-dimensional feature space and unsupervised clustering of individual pixels. Our proposed method showed improved sensitivity and specificity in comparison with standard segmentation methods. Replacing previously proposed methods with our method in multiplex IHC/image cytometry analysis, we observed higher detection of cell lineages including relatively rare TH 17 cells, further enabling sub-population analysis into TH 1-like and TH 2-like phenotypes based on T-bet and GATA3 expression. Interestingly, predominance of TH 2-like TH 17 cells was associated with human papilloma virus (HPV)-negative status of oropharyngeal squamous cell carcinoma of head and neck, known as a poor-prognostic subtype in comparison with HPV-positive status. Furthermore, TH 2-like TH 17 cells in HPV-negative head and neck cancer tissues were spatiotemporally correlated with CD66b+ granulocytes, presumably associated with an immunosuppressive microenvironment. Our cell segmentation method for multiplex IHC/image cytometry potentially contributes to in-depth immune profiling and spatial association, leading to further tissue-based biomarker exploration. © 2019 International Society for Advancement of Cytometry.
Collapse
Affiliation(s)
- Takahiro Tsujikawa
- Department of Cell, Developmental, and Cancer Biology, Oregon Health & Science University, Portland, Oregon, USA.,Department of Otolaryngology-Head & Neck Surgery, Oregon Health & Science University, Portland, Oregon, USA.,Department of Otolaryngology-Head and Neck Surgery, Kyoto Prefectural University of Medicine, Kyoto, Japan
| | - Guillaume Thibault
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, Oregon, USA
| | - Vahid Azimi
- Computational Biology Program, Oregon Health & Science University, Portland, Oregon, USA
| | - Sam Sivagnanam
- Computational Biology Program, Oregon Health & Science University, Portland, Oregon, USA
| | - Grace Banik
- Department of Otolaryngology-Head & Neck Surgery, Oregon Health & Science University, Portland, Oregon, USA
| | - Casey Means
- Department of Otolaryngology-Head & Neck Surgery, Oregon Health & Science University, Portland, Oregon, USA
| | - Rie Kawashima
- Department of Cell, Developmental, and Cancer Biology, Oregon Health & Science University, Portland, Oregon, USA
| | - Daniel R Clayburgh
- Department of Otolaryngology-Head & Neck Surgery, Oregon Health & Science University, Portland, Oregon, USA.,Department of Knight Cancer Institute, Oregon Health & Science University, Portland, Oregon, USA
| | - Joe W Gray
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, Oregon, USA.,Department of Knight Cancer Institute, Oregon Health & Science University, Portland, Oregon, USA
| | - Lisa M Coussens
- Department of Cell, Developmental, and Cancer Biology, Oregon Health & Science University, Portland, Oregon, USA.,Department of Knight Cancer Institute, Oregon Health & Science University, Portland, Oregon, USA
| | - Young Hwan Chang
- Department of Biomedical Engineering, Oregon Health & Science University, Portland, Oregon, USA.,Computational Biology Program, Oregon Health & Science University, Portland, Oregon, USA
| |
Collapse
|
|
20
|
Burlingame EA, Margolin AA, Gray JW, Chang YH. SHIFT: speedy histopathological-to-immunofluorescent translation of whole slide images using conditional generative adversarial networks. PROCEEDINGS OF SPIE--THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING 2018; 10581. [PMID: 30283195 DOI: 10.1117/12.2293249] [Citation(s) in RCA: 15] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/16/2023]
Abstract
Multiplexed imaging such as multicolor immunofluorescence staining, multiplexed immunohistochemistry (mIHC) or cyclic immunofluorescence (cycIF) enables deep assessment of cellular complexity in situ and, in conjunction with standard histology stains like hematoxylin and eosin (H&E), can help to unravel the complex molecular relationships and spatial interdependencies that undergird disease states. However, these multiplexed imaging methods are costly and can degrade both tissue quality and antigenicity with each successive cycle of staining. In addition, computationally intensive image processing such as image registration across multiple channels is required. We have developed a novel method, speedy histopathological-to-immunofluorescent translation (SHIFT) of whole slide images (WSIs) using conditional generative adversarial networks (cGANs). This approach is rooted in the assumption that specific patterns captured in IF images by stains like DAPI, pan-cytokeratin (panCK), or α-smooth muscle actin ( α-SMA) are encoded in H&E images, such that a SHIFT model can learn useful feature representations or architectural patterns in the H&E stain that help generate relevant IF stain patterns. We demonstrate that the proposed method is capable of generating realistic tumor marker IF WSIs conditioned on corresponding H&E-stained WSIs with up to 94.5% accuracy in a matter of seconds. Thus, this method has the potential to not only improve our understanding of the mapping of histological and morphological profiles into protein expression profiles, but also greatly increase the e ciency of diagnostic and prognostic decision-making.
Collapse
Affiliation(s)
| | | | - Joe W Gray
- Oregon Health and Science University, Portland, OR, USA
| | | |
Collapse
|