|
1
|
Duque CS, Builes-Montaño CE, Tobón-Ospina C, Velez Hoyos A, Sánchez JG, Londoño AF, Agudelo M, Valencia JA, Dueñas JP, Palacio MF, Sierra N. Thyroid Cancer Staging: Historical Evolution and Analysis From Macrocarcinoma to Microcarcinoma. Cureus 2025; 17:e81972. [PMID: 40352024 PMCID: PMC12064280 DOI: 10.7759/cureus.81972] [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] [Accepted: 04/08/2025] [Indexed: 05/14/2025] Open
Abstract
The classification of thyroid cancer diagnosis and treatment has evolved dramatically since the Union for International Cancer Control (UICC) published the first staging system in 1968. A careful review of the eight published editions of well-differentiated thyroid cancer (WDTC) staging by the UICC and the American Joint Committee on Cancer (AJCC) was performed. Each edition was analyzed to clearly understand which development published and accepted by specialists treating thyroid cancer justified considering a new updated edition. This study presents a comprehensive review of the remarkable evolution of thyroid cancer staging, highlighting the various changes in several areas throughout the years and editions. There were surprising changes within the eight publications: the tumor size was progressively reduced from 4 cm in the first AJCC volume to less than 1 cm in the seventh and eighth UICC and AJCC editions, classifying these small, WDTCs known up to now as "microcarcinomas." Extrathyroidal extension was accepted after the third edition; this description certainly plays a key role in today's decisions to manage this tumor as a prognostic factor. The age specification of 45 years prevailed for seven consecutive publications until it was raised to 55 years in the eighth thyroid cancer staging system. Without a doubt, this iconic change allowed physicians around the world to give their 45-year-old thyroid cancer patients a more encouraging panorama of the disease with the new classification. Over the course of nearly 57 years, thyroid cancer staging has undergone remarkable changes, reaching a level of certainty that not only provides recommendations for safer treatments with less surgery and adjunctive measures but also improves survival rates and patient safety.
Collapse
Affiliation(s)
- Carlos S Duque
- Department of Surgery, Clinica Intermedica, Medellin, COL
| | - Carlos E Builes-Montaño
- Department of Internal Medicine, Hospital Pablo Tobón Uribe, Medellin, COL
- Department of Endocrinology, Universidad de Antioquia, School of Medicine, Medellin, COL
| | | | - Alejandro Velez Hoyos
- School of Health Sciences, Universidad Pontificia Bolivariana, Medellin, COL
- Department of Pathology, Hospital Pablo Tobón Uribe, Medellin, COL
| | - Juan G Sánchez
- Department of Surgery, Clinica (Corporación de Estudios de la Salud) CES, Medellin, COL
| | - Andres F Londoño
- Department of Surgery, Hospital Pablo Tobón Uribe, Medellin, COL
| | - Miguel Agudelo
- Department of Hepatology, Temple University Hospital, Newark, USA
| | - Julio A Valencia
- Department of Surgery, Hospital Pablo Tobón Uribe, Medellin, COL
| | - Juan P Dueñas
- Department of Surgery, Clinica El Rosario El Tesoro, Medellin, COL
| | - Maria F Palacio
- Department of Surgery, Hospital Militar Central, Medellin, COL
| | - Natalia Sierra
- Department of General Medicine, Universidad Corporación de Estudios de la Salud (CES), Medellin, COL
| |
Collapse
|
|
2
|
Yang L, Wang X, Zhang S, Cao K, Yang J. Research progress on artificial intelligence technology-assisted diagnosis of thyroid diseases. Front Oncol 2025; 15:1536039. [PMID: 40052126 PMCID: PMC11882420 DOI: 10.3389/fonc.2025.1536039] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2024] [Accepted: 01/31/2025] [Indexed: 03/09/2025] Open
Abstract
With the rapid development of the "Internet + Medical" model, artificial intelligence technology has been widely used in the analysis of medical images. Among them, the technology of using deep learning algorithms to identify features of ultrasound and pathological images and realize intelligent diagnosis of diseases has entered the clinical verification stage. This study is based on the application research of artificial intelligence technology in medical diagnosis and reviews the early screening and diagnosis of thyroid diseases. The cure rate of thyroid disease is high in the early stage, but once it deteriorates into thyroid cancer, the risk of death and treatment costs of the patient increase. At present, the early diagnosis of the disease still depends on the examination equipment and the clinical experience of doctors, and there is a certain misdiagnosis rate. Based on the above background, it is particularly important to explore a technology that can achieve objective screening of thyroid lesions in the early stages. This paper provides a comprehensive review of recent research on the early diagnosis of thyroid diseases using artificial intelligence technology. It integrates the findings of multiple studies and that traditional machine learning algorithms are widely used as research objects. The convolutional neural network model has a high recognition accuracy for thyroid nodules and thyroid pathological cell lesions. U-Net network model can significantly improve the recognition accuracy of thyroid nodule ultrasound images when used as a segmentation algorithm. This article focuses on reviewing the intelligent recognition technology of thyroid ultrasound images and pathological sections, hoping to provide researchers with research ideas and help clinicians achieve intelligent early screening of thyroid cancer.
Collapse
Affiliation(s)
- Lina Yang
- Development Department of the Wisdom Hospital, Shandong Provincial Third Hospital, Jinan, China
| | - XinYuan Wang
- Information Department, Shandong First Rehabilitation Hospital, Linyi, China
| | - Shixia Zhang
- Development Department of the Wisdom Hospital, Shandong Provincial Third Hospital, Jinan, China
| | - Kun Cao
- Development Department of the Wisdom Hospital, Shandong Provincial Third Hospital, Jinan, China
| | - Jianjun Yang
- General Practice Medicine, Shandong Provincial Third Hospital, Jinan, China
| |
Collapse
|
|
3
|
Poursina O, Khayyat A, Maleki S, Amin A. Artificial Intelligence and Whole Slide Imaging Assist in Thyroid Indeterminate Cytology: A Systematic Review. Acta Cytol 2025; 69:161-170. [PMID: 39746329 DOI: 10.1159/000543344] [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: 08/14/2024] [Accepted: 12/20/2024] [Indexed: 01/04/2025]
Abstract
INTRODUCTION Thyroid cytopathology, particularly in cases of atypia of undetermined significance/follicular lesions of undetermined significance (AUS/FLUS), suffers from suboptimal sensitivity and specificity challenges. Recent advancements in digital pathology and artificial intelligence (AI) hold promise for enhancing diagnostic accuracy. This systematic review included studies that focused on diagnostic accuracy in AUS/FLUS cases using AI, whole slide imaging (WSI), or both. METHODS Of the 176 studies from 2000 to 2023, 13 met the inclusion criteria. The datasets range from 145 to 964 WSIs, with an overall number of 494 AUS cases ranging from eight to 254. Five studies used convolutional neural networks (CNNs), and two used artificial neural networks (ANNs). The preparation methods included Romanowsky-stained smears either alone or combined with Papanicolaou-stained or H&E and liquid-based cytology (ThinPrep). The scanner models that were used for scanning the slides varied, including Leica/Aperio, Alyuda Neurointelligence Cupertino, and PANNORAMIC™ Desk Scanner. Classifiers used include Feedforward Neural Networks (FFNNs), Two-Layer Feedforward Neural Networks (2L-FFNNs), Classifier Machine Learning Algorithm (MLA), Visual Geometry Group 11 (VGG11), Gradient Boosting Trees (GBT), Extra Trees Classifier (ETC), YOLOv4, EfficientNetV2-L, Back-Propagation Multi-Layer Perceptron (BP MLP), and MobileNetV2. RESULTS The available studies have shown promising results in differentiating between thyroid lesions, including AUS/FLUS. AI can be especially effective in removing sources of errors such as subjective assessment, variation in staining, and algorithms. CNN has been successful in processing WSI data and identifying diagnostic features with minimal human supervision. ANNs excelled in integrating structured clinical data with image-derived features, particularly when paired with WSI, enhancing diagnostic accuracy for indeterminate thyroid lesions. CONCLUSION A combined approach using both CNN and ANN can take advantage of their strengths. While AI and WSI integration shows promise in improving diagnostic accuracy and reducing uncertainty in indeterminate thyroid cytology, challenges such as the lack of standardization need to be addressed.
Collapse
Affiliation(s)
- Olia Poursina
- Department of Pathology and Laboratory Medicine, Brown University, Providence, Rhode Island, USA
| | - Azadeh Khayyat
- Department of Pathology and Laboratory Medicine, Medical College of Wisconsin, Milwaukee, Wisconsin, USA
| | - Sara Maleki
- Department of Pathology and Laboratory Medicine, Brown University, Providence, Rhode Island, USA
| | - Ali Amin
- Department of Pathology and Laboratory Medicine, Brown University, Providence, Rhode Island, USA
| |
Collapse
|
|
4
|
Zhang H, Li Z, Zhang F, Li H. CT-based radiomics features for the differential diagnosis of nodular goiter and papillary thyroid carcinoma: an analysis employing propensity score matching. Front Oncol 2024; 14:1465941. [PMID: 39726704 PMCID: PMC11669662 DOI: 10.3389/fonc.2024.1465941] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2024] [Accepted: 11/27/2024] [Indexed: 12/28/2024] Open
Abstract
Purpose This study aims to evaluate the effectiveness of CT-based radiomics features in discriminating between nodular goiter (NG) and papillary thyroid carcinoma (PTC). Methods A retrospective cohort comprising 228 patients with nodular goiter (NG) and 227 patients with papillary thyroid carcinoma (PTC) diagnosed between January 2018 and December 2022 was consecutively enrolled. Propensity score matching (PSM) was applied to align patients with NG and PTC. A total of 851 radiomics features were extracted from CT images acquired during the arterial phase for each individual. Feature selection was carried out utilizing the least absolute shrinkage and selection operator (LASSO) logistic regression algorithm to generate the radiomics score (Rad-score). Subsequently, the Rad-score was incorporated into a multivariate logistic regression analysis to construct a radiomics nomogram for visual representation. Results Following PSM implementation, 101 patients diagnosed with NG were matched with an equivalent number of patients diagnosed with PTC. The developed radiomics score exhibited excellent predictive performance in distinguishing between NG and PTC, with high values of AUC, sensitivity, and specificity in both the training cohort (AUC = 0.823, accuracy = 0.759, sensitivity = 0.794, specificity = 0.740) and validation cohort (AUC = 0.904, accuracy = 0.820, sensitivity = 0.758, specificity = 0.964). Conclusion The utilization of CT-based radiomics analysis following PMS offers a quantitative and data-driven approach to enhance the accuracy of distinguishing between nodular goiter (NG) and papillary thyroid carcinoma (PTC).
Collapse
Affiliation(s)
- Haiming Zhang
- Medical Imaging Center, The first Affiliated Hospital of Jinan University, Guangzhou, China
| | - Zhenyu Li
- Medical Imaging Center, The first Affiliated Hospital of Jinan University, Guangzhou, China
| | - Fengtao Zhang
- Invasive Technology Department, Huazhong University of Science and Technology Union Shenzhen Hospital, Shenzhen, China
| | - Hengguo Li
- Medical Imaging Center, The first Affiliated Hospital of Jinan University, Guangzhou, China
| |
Collapse
|
|
5
|
Oteri V, Piane S, Cocci E. The use of telecytology for the evaluation of thyroid nodules fine-needle aspiration biopsy specimens: a systematic review. J Endocrinol Invest 2024; 47:2397-2406. [PMID: 38704449 PMCID: PMC11393276 DOI: 10.1007/s40618-024-02378-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/01/2023] [Accepted: 04/18/2024] [Indexed: 05/06/2024]
Abstract
PURPOSE Fine needle aspiration biopsy (FNAB) is currently the gold standard for diagnosis and treatment of thyroid nodules, but the growing need for anatomic pathology services in small communities is becoming a challenge. Telecytology (TC) is defined as the electronic transmission of cytological digital images, and allows for the collection of samples, primary diagnosis, and other applications without the physical presence of a pathologist. Our aim is to systematically report, summarize, and critically analyze the most up to date applications of TC to thyroid nodules FNAB evaluation. METHODS We performed a systematic literature review by searching PubMed, Embase, and Cochrane Library databases. Only studies published in peer-reviewed scientific journals were included. Data were extracted using the PICO framework and critically analyzed. PRISMA guidelines were applied, and the risk of bias in the included studies was assessed using the ROBINS-I tools. The methodological quality was assessed following GRADE criteria. RESULTS We included 13 observational studies, resulting in a total of 3856 evaluated FNAB specimens. The majority of studies (63.6%) showed an excellent concordance rate of diagnosis via TC and conventional cytology. TC can be used to perform preliminary assessment of samples with a concordance rate ranging from 74 and 100%, showing a significant reduction of the non-diagnostic rate. Image quality was referred to as perfect or nearly perfect in most cases, regardless of telecytology technique. CONCLUSION Telecytology could be a valuable implementation for thyroid FNAB evaluation both for primary diagnosis and preliminary assessment of samples.
Collapse
Affiliation(s)
- V Oteri
- Endocrine Unit, Department of Clinical and Experimental Medicine, University of Catania, Garibaldi-Nesima Hospital, Catania, Italy.
| | - S Piane
- Department of Medicine and Surgery, University of Milano-Bicocca, Milan, Italy
| | - E Cocci
- Department of Clinical and Experimental Medicine, Marche Polytechnic University, Ancona, Italy
| |
Collapse
|
|
6
|
Kim CA, An HR, Yoo J, Lee YM, Sung TY, Kim WG, Song DE. Morphometric Analysis of Lateral Cervical Lymph Node Metastasis in Papillary Thyroid Carcinoma Using Digital Pathology. Endocr Pathol 2024; 35:113-121. [PMID: 38064165 DOI: 10.1007/s12022-023-09790-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 11/02/2023] [Indexed: 06/14/2024]
Abstract
Digital pathology uses digitized images for cancer research. We aimed to assess morphometric parameters using digital pathology for predicting recurrence in patients with papillary thyroid carcinoma (PTC) and lateral cervical lymph node (LN) metastasis. We analyzed 316 PTC patients and assessed the longest diameter and largest area of metastatic focus in LNs using a whole slide imaging scanner. In digital pathology assessment, the longest diameters and largest areas of metastatic foci in LNs were positively correlated with traditional optically measured diameters (R = 0.928 and R2 = 0.727, p < 0.001 and p < 0.001, respectively). The optimal cutoff diameter was 8.0 mm in both traditional microscopic (p = 0.009) and digital pathology (p = 0.016) evaluations, with significant differences in progression-free survival (PFS) observed at this cutoff (p = 0.006 and p = 0.002, respectively). The predictive area's cutoff was 35.6 mm2 (p = 0.005), which significantly affected PFS (p = 0.015). Using an 8.0-mm cutoff in traditional microscopic evaluation and a 35.6-mm2 cutoff in digital pathology showed comparable predictive results using the proportion of variation explained (PVE) methods (2.6% vs. 2.4%). Excluding cases with predominant cystic changes in LNs, the largest metastatic areas by digital pathology had the highest PVE at 3.9%. Furthermore, high volume of LN metastasis (p = 0.001), extranodal extension (p = 0.047), and high ratio of metastatic LNs (p = 0.006) were associated with poor prognosis. Both traditional microscopic and digital pathology evaluations effectively measured the longest diameter of metastatic foci in LNs. Moreover, digital pathology offers limited advantages in predicting PFS of patients with lateral cervical LN metastasis of PTC, especially those without predominant cystic changes in LNs.
Collapse
Affiliation(s)
- Chae A Kim
- Division of Endocrinology and Metabolism, Department of Internal Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Hyeong Rok An
- Department of Pathology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Jungmin Yoo
- Division of Endocrinology and Metabolism, Department of Internal Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Yu-Mi Lee
- Department of Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Tae-Yon Sung
- Department of Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Won Gu Kim
- Division of Endocrinology and Metabolism, Department of Internal Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
| | - Dong Eun Song
- Department of Pathology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
| |
Collapse
|
|
7
|
Rende PRF, Pires JM, Nakadaira KS, Lopes S, Vale J, Hecht F, Beltrão FEL, Machado GJR, Kimura ET, Eloy C, Ramos HE. Revisiting the utility of identifying nuclear grooves as unique nuclear changes by an object detector model. J Pathol Transl Med 2024; 58:117-126. [PMID: 38684222 PMCID: PMC11106606 DOI: 10.4132/jptm.2024.03.07] [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: 09/08/2023] [Revised: 02/12/2024] [Accepted: 03/06/2024] [Indexed: 05/02/2024] Open
Abstract
BACKGROUND Among other structures, nuclear grooves are vastly found in papillary thyroid carcinoma (PTC). Considering that the application of artificial intelligence in thyroid cytology has potential for diagnostic routine, our goal was to develop a new supervised convolutional neural network capable of identifying nuclear grooves in Diff-Quik stained whole-slide images (WSI) obtained from thyroid fineneedle aspiration. METHODS We selected 22 Diff-Quik stained cytological slides with cytological diagnosis of PTC and concordant histological diagnosis. Each of the slides was scanned, forming a WSI. Images that contained the region of interest were obtained, followed by pre-formatting, annotation of the nuclear grooves and data augmentation techniques. The final dataset was divided into training and validation groups in a 7:3 ratio. RESULTS This is the first artificial intelligence model based on object detection applied to nuclear structures in thyroid cytopathology. A total of 7,255 images were obtained from 22 WSI, totaling 7,242 annotated nuclear grooves. The best model was obtained after it was submitted 15 times with the train dataset (14th epoch), with 67% true positives, 49.8% for sensitivity and 43.1% for predictive positive value. CONCLUSIONS The model was able to develop a structure predictor rule, indicating that the application of an artificial intelligence model based on object detection in the identification of nuclear grooves is feasible. Associated with a reduction in interobserver variability and in time per slide, this demonstrates that nuclear evaluation constitutes one of the possibilities for refining the diagnosis through computational models.
Collapse
Affiliation(s)
- Pedro R. F. Rende
- Bioregulation Department, Health and Science Institute, Federal University of Bahia, Salvador, Brazil
| | | | | | - Sara Lopes
- Endocrinology Department, Hospital de Braga, Braga, Portugal
| | - João Vale
- Laboratory of Pathology of the Institute of Pathology and Molecular Immunology, University of Porto, Porto, Portugal
| | - Fabio Hecht
- Department of Biomedical Genetics, University of Rochester, Rochester, New York, USA
| | - Fabyan E. L. Beltrão
- Bioregulation Department, Health and Science Institute, Federal University of Bahia, Salvador, Brazil
| | - Gabriel J. R. Machado
- Bioregulation Department, Health and Science Institute, Federal University of Bahia, Salvador, Brazil
| | - Edna T. Kimura
- Institute of Biomedical Sciences, University of São Paulo, São Paulo, Brazil
| | - Catarina Eloy
- Laboratory of Pathology of the Institute of Pathology and Molecular Immunology, University of Porto, Porto, Portugal
- Faculty of Medicine, University of Porto, Porto, Portugal
| | - Helton E. Ramos
- Bioregulation Department, Health and Science Institute, Federal University of Bahia, Salvador, Brazil
- Postgraduate Program in Medicine and Health, Bahia Faculty of Medicine, Federal University of Bahia, Salvador, Brazil
| |
Collapse
|
|
8
|
Palomba G, Fernicola A, Corte MD, Capuano M, De Palma GD, Aprea G. Artificial intelligence in screening and diagnosis of surgical diseases: A narrative review. AIMS Public Health 2024; 11:557-576. [PMID: 39027395 PMCID: PMC11252578 DOI: 10.3934/publichealth.2024028] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2024] [Revised: 03/29/2024] [Accepted: 04/02/2024] [Indexed: 07/20/2024] Open
Abstract
Artificial intelligence (AI) is playing an increasing role in several fields of medicine. It is also gaining popularity among surgeons as a valuable screening and diagnostic tool for many conditions such as benign and malignant colorectal, gastric, thyroid, parathyroid, and breast disorders. In the literature, there is no review that groups together the various application domains of AI when it comes to the screening and diagnosis of main surgical diseases. The aim of this review is to describe the use of AI in these settings. We performed a literature review by searching PubMed, Web of Science, Scopus, and Embase for all studies investigating the role of AI in the surgical setting, published between January 01, 2000, and June 30, 2023. Our focus was on randomized controlled trials (RCTs), meta-analysis, systematic reviews, and observational studies, dealing with large cohorts of patients. We then gathered further relevant studies from the reference list of the selected publications. Based on the studies reviewed, it emerges that AI could strongly enhance the screening efficiency, clinical ability, and diagnostic accuracy for several surgical conditions. Some of the future advantages of this technology include implementing, speeding up, and improving the automaticity with which AI recognizes, differentiates, and classifies the various conditions.
Collapse
Affiliation(s)
- Giuseppe Palomba
- Department of Clinical Medicine and Surgery, University of Naples, “Federico II”, Sergio Pansini 5, 80131, Naples, Italy
| | - Agostino Fernicola
- Department of Clinical Medicine and Surgery, University of Naples, “Federico II”, Sergio Pansini 5, 80131, Naples, Italy
| | - Marcello Della Corte
- Azienda Ospedaliera Universitaria San Giovanni di Dio e Ruggi d'Aragona - OO. RR. Scuola Medica Salernitana, Salerno, Italy
| | - Marianna Capuano
- Department of Clinical Medicine and Surgery, University of Naples, “Federico II”, Sergio Pansini 5, 80131, Naples, Italy
| | - Giovanni Domenico De Palma
- Department of Clinical Medicine and Surgery, University of Naples, “Federico II”, Sergio Pansini 5, 80131, Naples, Italy
| | - Giovanni Aprea
- Department of Clinical Medicine and Surgery, University of Naples, “Federico II”, Sergio Pansini 5, 80131, Naples, Italy
| |
Collapse
|
|
9
|
Kim HK, Han E, Lee J, Yim K, Abdul-Ghafar J, Seo KJ, Seo JW, Gong G, Cho NH, Kim M, Yoo CW, Chong Y. Artificial-Intelligence-Assisted Detection of Metastatic Colorectal Cancer Cells in Ascitic Fluid. Cancers (Basel) 2024; 16:1064. [PMID: 38473421 DOI: 10.3390/cancers16051064] [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: 11/29/2023] [Revised: 02/17/2024] [Accepted: 02/29/2024] [Indexed: 03/14/2024] Open
Abstract
Ascites cytology is a cost-effective test for metastatic colorectal cancer (CRC) in the abdominal cavity. However, metastatic carcinoma of the peritoneum is difficult to diagnose based on biopsy findings, and ascitic aspiration cytology has a low sensitivity and specificity and a high inter-observer variability. The aim of the present study was to apply artificial intelligence (AI) to classify benign and malignant cells in ascites cytology patch images of metastatic CRC using a deep convolutional neural network. Datasets were collected from The OPEN AI Dataset Project, a nationwide cytology dataset for AI research. The numbers of patch images used for training, validation, and testing were 56,560, 7068, and 6534, respectively. We evaluated 1041 patch images of benign and metastatic CRC in the ascitic fluid to compare the performance of pathologists and an AI algorithm, and to examine whether the diagnostic accuracy of pathologists improved with the assistance of AI. This AI method showed an accuracy, a sensitivity, and a specificity of 93.74%, 87.76%, and 99.75%, respectively, for the differential diagnosis of malignant and benign ascites. The diagnostic accuracy and sensitivity of the pathologist with the assistance of the proposed AI method increased from 86.8% to 90.5% and from 73.3% to 79.3%, respectively. The proposed deep learning method may assist pathologists with different levels of experience in diagnosing metastatic CRC cells of ascites.
Collapse
Affiliation(s)
- Hyung Kyung Kim
- Department of Pathology, Seoul National University Bundang Hospital, Seongnam 13620, Republic of Korea
- Department of Pathology, Samsung Medical Center, Seoul 06351, Republic of Korea
| | - Eunkyung Han
- Department of Pathology, Soonchunyang University Hospital Bucheon, Bucheon 14584, Republic of Korea
| | - Jeonghyo Lee
- Department of Pathology, Seoul National University Bundang Hospital, Seongnam 13620, Republic of Korea
| | - Kwangil Yim
- Department of Hospital Pathology, The Catholic University of Korea College of Medicine, Seoul 06591, Republic of Korea
| | - Jamshid Abdul-Ghafar
- Department of Hospital Pathology, The Catholic University of Korea College of Medicine, Seoul 06591, Republic of Korea
| | - Kyung Jin Seo
- Department of Hospital Pathology, The Catholic University of Korea College of Medicine, Seoul 06591, Republic of Korea
| | - Jang Won Seo
- AI Team, MTS Company Inc., Seoul 06178, Republic of Korea
| | - Gyungyub Gong
- Department of Pathology, Asan Medical Center, Seoul 05505, Republic of Korea
| | - Nam Hoon Cho
- Department of Pathology, Yonsei University College of Medicine, Seoul 03722, Republic of Korea
| | - Milim Kim
- Department of Pathology, Yonsei University College of Medicine, Seoul 03722, Republic of Korea
| | - Chong Woo Yoo
- Department of Pathology, National Cancer Center, Goyang 10408, Republic of Korea
| | - Yosep Chong
- Department of Hospital Pathology, The Catholic University of Korea College of Medicine, Seoul 06591, Republic of Korea
| |
Collapse
|
|
10
|
Fang H, Fu K, Shi P, Zhao Z, Yang F, Liu Y. Forkhead box F2/ Lysyl oxidase like 1 contribute to epithelial-mesenchymal transition and angiogenesis in thyroid cancer. Cell Signal 2024; 113:110956. [PMID: 37918464 DOI: 10.1016/j.cellsig.2023.110956] [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: 07/31/2023] [Revised: 10/17/2023] [Accepted: 10/27/2023] [Indexed: 11/04/2023]
Abstract
BACKGROUND Bioinformatics analysis suggests an association between lysyl oxidase like 1 (LOXL1) and forkhead box F2 (FOXF2), both of which are found to be dysregulated in thyroid cancer. This study aims to elucidate their specific roles in thyroid cancer. METHODS The correlation of LOXL1 expression with thyroid cancer staging and the overall survival was analyzed. LOXL1 levels were determined in several thyroid cancer cells, and its effects on poorly differentiated BCPAP cell proliferation, colony formation, malignant phenotypes, epithelial-mesenchymal transition (EMT) progression, and angiogenesis were evaluated. The relationship between LOXL1 and FOXF2 was confirmed using Luciferase reporter and ChIP assays. The impacts of FOXF2 on LOXL1 regulation along with the Wnt/β-catenin signaling were assessed, followed by the verification of transplanted tumor in nude mice. RESULTS Elevated LOXL1 expression was associated with advanced clinical staging and poorer overall survival. Reduced LOXL1 suppressed cell proliferation, colony formation, migration, invasion, EMT, and angiogenesis. FOXF2 was found to be down-regulated in thyroid cancer, acting as a transcription factor that recognizes the LOXL1 promoter and modulates its transcriptional expression. Moreover, the regulatory outcome of LOXL1 knockdown was partially reversed upon FOXF2 knockdown, including the modulation of the Wnt/β-catenin signaling and tumor growth in vivo. CONCLUSION Our findings indicate that LOXL1 is transcriptionally regulated by FOXF2 and activates the Wnt/β-catenin to promote malignant phenotypes, EMT progression, and angiogenesis in BCPAP cells.
Collapse
Affiliation(s)
- Hao Fang
- Hepatobiliary Surgery Department, Hebei Medical University Fourth Affiliated Hospital/Hebei Provincial Tumor Hospital, Shijiazhuang, Hebei 050000, China
| | - Kai Fu
- Otorhinolaryngology, Hebei Medical University Fourth Affiliated Hospital/Hebei Provincial Tumor Hospital, Shijiazhuang, Hebei 050000, China
| | - Ping Shi
- Otorhinolaryngology, Hebei Medical University Fourth Affiliated Hospital/Hebei Provincial Tumor Hospital, Shijiazhuang, Hebei 050000, China
| | - Zhen Zhao
- Otorhinolaryngology, Hebei Medical University Fourth Affiliated Hospital/Hebei Provincial Tumor Hospital, Shijiazhuang, Hebei 050000, China
| | - Fei Yang
- Otorhinolaryngology, Hebei Medical University Fourth Affiliated Hospital/Hebei Provincial Tumor Hospital, Shijiazhuang, Hebei 050000, China
| | - Yan Liu
- Otorhinolaryngology, Hebei Medical University Fourth Affiliated Hospital/Hebei Provincial Tumor Hospital, Shijiazhuang, Hebei 050000, China.
| |
Collapse
|
|
11
|
Slabaugh G, Beltran L, Rizvi H, Deloukas P, Marouli E. Applications of machine and deep learning to thyroid cytology and histopathology: a review. Front Oncol 2023; 13:958310. [PMID: 38023130 PMCID: PMC10661921 DOI: 10.3389/fonc.2023.958310] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2022] [Accepted: 10/12/2023] [Indexed: 12/01/2023] Open
Abstract
This review synthesises past research into how machine and deep learning can improve the cyto- and histopathology processing pipelines for thyroid cancer diagnosis. The current gold-standard preoperative technique of fine-needle aspiration cytology has high interobserver variability, often returns indeterminate samples and cannot reliably identify some pathologies; histopathology analysis addresses these issues to an extent, but it requires surgical resection of the suspicious lesions so cannot influence preoperative decisions. Motivated by these issues, as well as by the chronic shortage of trained pathologists, much research has been conducted into how artificial intelligence could improve current pipelines and reduce the pressure on clinicians. Many past studies have indicated the significant potential of automated image analysis in classifying thyroid lesions, particularly for those of papillary thyroid carcinoma, but these have generally been retrospective, so questions remain about both the practical efficacy of these automated tools and the realities of integrating them into clinical workflows. Furthermore, the nature of thyroid lesion classification is significantly more nuanced in practice than many current studies have addressed, and this, along with the heterogeneous nature of processing pipelines in different laboratories, means that no solution has proven itself robust enough for clinical adoption. There are, therefore, multiple avenues for future research: examine the practical implementation of these algorithms as pathologist decision-support systems; improve interpretability, which is necessary for developing trust with clinicians and regulators; and investigate multiclassification on diverse multicentre datasets, aiming for methods that demonstrate high performance in a process- and equipment-agnostic manner.
Collapse
Affiliation(s)
- Greg Slabaugh
- Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom
| | - Luis Beltran
- Barts Health NHS Trust, The Royal London Hospital, London, United Kingdom
| | - Hasan Rizvi
- Barts Health NHS Trust, The Royal London Hospital, London, United Kingdom
| | - Panos Deloukas
- William Harvey Research Institute, Barts and The London School of Medicine and Dentistry, Queen Mary University of London, London, United Kingdom
| | - Eirini Marouli
- Digital Environment Research Institute, Queen Mary University of London, London, United Kingdom
- Barts Health NHS Trust, The Royal London Hospital, London, United Kingdom
- William Harvey Research Institute, Barts and The London School of Medicine and Dentistry, Queen Mary University of London, London, United Kingdom
| |
Collapse
|
|
12
|
Nagendra L, Pappachan JM, Fernandez CJ. Artificial intelligence in the diagnosis of thyroid cancer: Recent advances and future directions. Artif Intell Cancer 2023; 4:1-10. [DOI: 10.35713/aic.v4.i1.1] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/03/2023] [Revised: 07/24/2023] [Accepted: 08/07/2023] [Indexed: 09/07/2023] Open
Abstract
The diagnosis and management of thyroid cancer is fraught with challenges despite the advent of innovative diagnostic, surgical, and chemotherapeutic modalities. Challenges like inaccuracy in prognostication, uncertainty in cytopathological diagnosis, trouble in differentiating follicular neoplasms, intra-observer and inter-observer variability on ultrasound imaging preclude personalised treatment in thyroid cancer. Artificial intelligence (AI) is bringing a paradigm shift to the healthcare, powered by quick advancement of the analytic techniques. Several recent studies have shown remarkable progress in thyroid cancer diagnostics based on AI-assisted algorithms. Application of AI techniques in thyroid ultrasonography and cytopathology have shown remarkable impro-vement in sensitivity and specificity over the traditional diagnostic modalities. AI has also been explored in the development of treatment algorithms for indeterminate nodules and for prognostication in the patients with thyroid cancer. The benefits of high repeatability and straightforward implementation of AI in the management of thyroid cancer suggest that it holds promise for clinical application. Limited clinical experience and lack of prospective validation studies remain the biggest drawbacks. Developing verified and trustworthy algorithms after extensive testing and validation using prospective, multi-centre trials is crucial for the future use of AI in the pipeline of precision medicine in the management of thyroid cancer.
Collapse
Affiliation(s)
- Lakshmi Nagendra
- Department of Endocrinology, JSS Medical College & JSS Academy of Higher Education and Research Center, Mysore 570015, India
| | - Joseph M Pappachan
- Department of Endocrinology & Metabolism, Lancashire Teaching Hospitals NHS Trust, Preston PR2 9HT, United Kingdom
- Faculty of Science, Manchester Metropolitan University, Manchester M15 6BH, M15 6BH, United Kingdom
- Faculty of Biology, Medicine and Health, The University of Manchester, Manchester M13 9PL, United Kingdom
| | - Cornelius James Fernandez
- Department of Endocrinology & Metabolism, Pilgrim Hospital, United Lincolnshire Hospitals NHS Trust, PE21 9QS PE21 9QS, United Kingdom
| |
Collapse
|
|
13
|
Sharma R, Mahanti GK, Panda G, Rath A, Dash S, Mallik S, Hu R. A Framework for Detecting Thyroid Cancer from Ultrasound and Histopathological Images Using Deep Learning, Meta-Heuristics, and MCDM Algorithms. J Imaging 2023; 9:173. [PMID: 37754937 PMCID: PMC10532397 DOI: 10.3390/jimaging9090173] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2023] [Revised: 08/17/2023] [Accepted: 08/22/2023] [Indexed: 09/28/2023] Open
Abstract
Computer-assisted diagnostic systems have been developed to aid doctors in diagnosing thyroid-related abnormalities. The aim of this research is to improve the diagnosis accuracy of thyroid abnormality detection models that can be utilized to alleviate undue pressure on healthcare professionals. In this research, we proposed deep learning, metaheuristics, and a MCDM algorithms-based framework to detect thyroid-related abnormalities from ultrasound and histopathological images. The proposed method uses three recently developed deep learning techniques (DeiT, Swin Transformer, and Mixer-MLP) to extract features from the thyroid image datasets. The feature extraction techniques are based on the Image Transformer and MLP models. There is a large number of redundant features that can overfit the classifiers and reduce the generalization capabilities of the classifiers. In order to avoid the overfitting problem, six feature transformation techniques (PCA, TSVD, FastICA, ISOMAP, LLE, and UMP) are analyzed to reduce the dimensionality of the data. There are five different classifiers (LR, NB, SVC, KNN, and RF) evaluated using the 5-fold stratified cross-validation technique on the transformed dataset. Both datasets exhibit large class imbalances and hence, the stratified cross-validation technique is used to evaluate the performance. The MEREC-TOPSIS MCDM technique is used for ranking the evaluated models at different analysis stages. In the first stage, the best feature extraction and classification techniques are chosen, whereas, in the second stage, the best dimensionality reduction method is evaluated in wrapper feature selection mode. Two best-ranked models are further selected for the weighted average ensemble learning and features selection using the recently proposed meta-heuristics FOX-optimization algorithm. The PCA+FOX optimization-based feature selection + random forest model achieved the highest TOPSIS score and performed exceptionally well with an accuracy of 99.13%, F2-score of 98.82%, and AUC-ROC score of 99.13% on the ultrasound dataset. Similarly, the model achieved an accuracy score of 90.65%, an F2-score of 92.01%, and an AUC-ROC score of 95.48% on the histopathological dataset. This study exploits the combination novelty of different algorithms in order to improve the thyroid cancer diagnosis capabilities. This proposed framework outperforms the current state-of-the-art diagnostic methods for thyroid-related abnormalities in ultrasound and histopathological datasets and can significantly aid medical professionals by reducing the excessive burden on the medical fraternity.
Collapse
Affiliation(s)
- Rohit Sharma
- Department of Electronics and Communication Engineering, National Institute of Technology, Durgapur 713209, India; (R.S.); (G.K.M.)
| | - Gautam Kumar Mahanti
- Department of Electronics and Communication Engineering, National Institute of Technology, Durgapur 713209, India; (R.S.); (G.K.M.)
| | - Ganapati Panda
- Department of Electronics and Communication Engineering, C.V. Raman Global University, Bhubaneswar 752054, India;
| | - Adyasha Rath
- Department of Computer Science and Engineering, C.V. Raman Global University, Bhubaneswar 752054, India;
| | - Sujata Dash
- Department of Information Technology, Nagaland University, Dimapur 797112, India;
| | - Saurav Mallik
- Department of Environmental Health, Harvard T H Chan School of Public Health, Boston, MA 02115, USA
- Department of Pharmacology & Toxicology, The University of Arizona, Tucson, MA 85721, USA
| | - Ruifeng Hu
- Department of Neurology, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, USA
| |
Collapse
|
|
14
|
Lee YK, Ryu D, Kim S, Park J, Park SY, Ryu D, Lee H, Lim S, Min HS, Park Y, Lee EK. Machine-learning-based diagnosis of thyroid fine-needle aspiration biopsy synergistically by Papanicolaou staining and refractive index distribution. Sci Rep 2023; 13:9847. [PMID: 37330568 PMCID: PMC10276805 DOI: 10.1038/s41598-023-36951-2] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Accepted: 06/13/2023] [Indexed: 06/19/2023] Open
Abstract
We developed a machine learning algorithm (MLA) that can classify human thyroid cell clusters by exploiting both Papanicolaou staining and intrinsic refractive index (RI) as correlative imaging contrasts and evaluated the effects of this combination on diagnostic performance. Thyroid fine-needle aspiration biopsy (FNAB) specimens were analyzed using correlative optical diffraction tomography, which can simultaneously measure both, the color brightfield of Papanicolaou staining and three-dimensional RI distribution. The MLA was designed to classify benign and malignant cell clusters using color images, RI images, or both. We included 1535 thyroid cell clusters (benign: malignancy = 1128:407) from 124 patients. Accuracies of MLA classifiers using color images, RI images, and both were 98.0%, 98.0%, and 100%, respectively. As information for classification, the nucleus size was mainly used in the color image; however, detailed morphological information of the nucleus was also used in the RI image. We demonstrate that the present MLA and correlative FNAB imaging approach has the potential for diagnosing thyroid cancer, and complementary information from color and RI images can improve the performance of the MLA.
Collapse
Affiliation(s)
- Young Ki Lee
- Division of Endocrinology and Metabolism, Department of Internal Medicine, National Cancer Center, Goyang, 10408, South Korea
| | | | - Seungwoo Kim
- Artificial Intelligence Graduate School, Ulsan National Institute of Science and Technology (UNIST), Ulsan, 44919, South Korea
| | - Juyeon Park
- Department of Physics, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, 34141, South Korea
- KAIST Institute for Health Science and Technology, KAIST, Daejeon, 34141, South Korea
| | - Seog Yun Park
- Deparment of Pathology, National Cancer Center, Goyang, 10408, South Korea
| | - Donghun Ryu
- Department of Physics, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, 34141, South Korea
- KAIST Institute for Health Science and Technology, KAIST, Daejeon, 34141, South Korea
- Department of Electrical Engineering and Computer Science (EECS), MIT, Cambridge, MA, 02139, USA
| | - Hayoung Lee
- Division of Endocrinology and Metabolism, Department of Internal Medicine, National Cancer Center, Goyang, 10408, South Korea
| | - Sungbin Lim
- Department of Statistics, Korea University, Seoul, 02841, South Korea
| | | | - YongKeun Park
- Tomocube Inc., Daejeon, 34051, South Korea.
- Department of Physics, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, 34141, South Korea.
- KAIST Institute for Health Science and Technology, KAIST, Daejeon, 34141, South Korea.
| | - Eun Kyung Lee
- Division of Endocrinology and Metabolism, Department of Internal Medicine, National Cancer Center, Goyang, 10408, South Korea.
| |
Collapse
|
|
15
|
Assaad S, Dov D, Davis R, Kovalsky S, Lee WT, Kahmke R, Rocke D, Cohen J, Henao R, Carin L, Range DE. Thyroid Cytopathology Cancer Diagnosis from Smartphone Images Using Machine Learning. Mod Pathol 2023; 36:100129. [PMID: 36931041 PMCID: PMC10293075 DOI: 10.1016/j.modpat.2023.100129] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2022] [Revised: 01/17/2023] [Accepted: 01/31/2023] [Indexed: 02/17/2023]
Abstract
We examined the performance of deep learning models on the classification of thyroid fine-needle aspiration biopsies using microscope images captured in 2 ways: with a high-resolution scanner and with a mobile phone camera. Our training set consisted of images from 964 whole-slide images captured with a high-resolution scanner. Our test set consisted of 100 slides; 20 manually selected regions of interest (ROIs) from each slide were captured in 2 ways as mentioned above. Applying a baseline machine learning algorithm trained on scanner ROIs resulted in performance deterioration when applied to the smartphone ROIs (97.8% area under the receiver operating characteristic curve [AUC], CI = [95.4%, 100.0%] for scanner images vs 89.5% AUC, CI = [82.3%, 96.6%] for mobile images, P = .019). Preliminary analysis via histogram matching showed that the baseline model was overly sensitive to slight color variations in the images (specifically, to color differences between mobile and scanner images). Adding color augmentation during training reduces this sensitivity and narrows the performance gap between mobile and scanner images (97.6% AUC, CI = [95.0%, 100.0%] for scanner images vs 96.0% AUC, CI = [91.8%, 100.0%] for mobile images, P = .309), with both modalities on par with human pathologist performance (95.6% AUC, CI = [91.6%, 99.5%]) for malignancy prediction (P = .398 for pathologist vs scanner and P = .875 for pathologist vs mobile). For indeterminate cases (pathologist-assigned Bethesda category of 3, 4, or 5), color augmentations confer some improvement (88.3% AUC, CI = [73.7%, 100.0%] for the baseline model vs 96.2% AUC, CI = [90.9%, 100.0%] with color augmentations, P = .158). In addition, we found that our model's performance levels off after 15 ROIs, a promising indication that ROI data collection would not be time-consuming for our diagnostic system. Finally, we showed that the model has sensible Bethesda category (TBS) predictions (increasing risk malignancy rate with predicted TBS category, with 0% malignancy for predicted TBS 2 and 100% malignancy for TBS 6).
Collapse
Affiliation(s)
- Serge Assaad
- Department of Electrical and Computer Engineering, Duke University, Durham, North Carolina
| | - David Dov
- I-Medata AI Center, Tel Aviv Sourasky Medical Center, Tel Aviv-Yafo, Israel; Department of Pathology, Duke University Medical Center, Durham, North Carolina
| | - Richard Davis
- Department of Pathology, Duke University Medical Center, Durham, North Carolina
| | - Shahar Kovalsky
- Department of Mathematics, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina
| | - Walter T Lee
- Department of Pathology, Duke University Medical Center, Durham, North Carolina
| | - Russel Kahmke
- Department of Head and Neck Surgery and Communication Sciences, Duke University Medical Center, Durham, North Carolina
| | - Daniel Rocke
- Department of Head and Neck Surgery and Communication Sciences, Duke University Medical Center, Durham, North Carolina
| | - Jonathan Cohen
- Department of Head and Neck Surgery and Communication Sciences, Duke University Medical Center, Durham, North Carolina
| | - Ricardo Henao
- Department of Electrical and Computer Engineering, Duke University, Durham, North Carolina; King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
| | - Lawrence Carin
- Department of Electrical and Computer Engineering, Duke University, Durham, North Carolina; King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
| | | |
Collapse
|
|
16
|
Luvhengo TE, Bombil I, Mokhtari A, Moeng MS, Demetriou D, Sanders C, Dlamini Z. Multi-Omics and Management of Follicular Carcinoma of the Thyroid. Biomedicines 2023; 11:biomedicines11041217. [PMID: 37189835 DOI: 10.3390/biomedicines11041217] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2023] [Revised: 04/05/2023] [Accepted: 04/11/2023] [Indexed: 05/17/2023] Open
Abstract
Follicular thyroid carcinoma (FTC) is the second most common cancer of the thyroid gland, accounting for up to 20% of all primary malignant tumors in iodine-replete areas. The diagnostic work-up, staging, risk stratification, management, and follow-up strategies in patients who have FTC are modeled after those of papillary thyroid carcinoma (PTC), even though FTC is more aggressive. FTC has a greater propensity for haematogenous metastasis than PTC. Furthermore, FTC is a phenotypically and genotypically heterogeneous disease. The diagnosis and identification of markers of an aggressive FTC depend on the expertise and thoroughness of pathologists during histopathological analysis. An untreated or metastatic FTC is likely to de-differentiate and become poorly differentiated or undifferentiated and resistant to standard treatment. While thyroid lobectomy is adequate for the treatment of selected patients who have low-risk FTC, it is not advisable for patients whose tumor is larger than 4 cm in diameter or has extensive extra-thyroidal extension. Lobectomy is also not adequate for tumors that have aggressive mutations. Although the prognosis for over 80% of PTC and FTC is good, nearly 20% of the tumors behave aggressively. The introduction of radiomics, pathomics, genomics, transcriptomics, metabolomics, and liquid biopsy have led to improvements in the understanding of tumorigenesis, progression, treatment response, and prognostication of thyroid cancer. The article reviews the challenges that are encountered during the diagnostic work-up, staging, risk stratification, management, and follow-up of patients who have FTC. How the application of multi-omics can strengthen decision-making during the management of follicular carcinoma is also discussed.
Collapse
Affiliation(s)
- Thifhelimbilu Emmanuel Luvhengo
- Department of Surgery, Charlotte Maxeke Johannesburg Academic Hospital, University of the Witwatersrand, Parktown, Johannesburg 2193, South Africa
| | - Ifongo Bombil
- Department of Surgery, Chris Hani Baragwanath Academic Hospital, University of the Witwatersrand, Johannesburg 1864, South Africa
| | - Arian Mokhtari
- Department of Surgery, Dr. George Mukhari Academic Hospital, Sefako Makgatho Health Sciences University, Ga-Rankuwa 0208, South Africa
| | - Maeyane Stephens Moeng
- Department of Surgery, Charlotte Maxeke Johannesburg Academic Hospital, University of the Witwatersrand, Parktown, Johannesburg 2193, South Africa
| | - Demetra Demetriou
- SAMRC Precision Oncology Research Unit (PORU), DSI/NRF SARChI Chair in Precision Oncology and Cancer Prevention (POCP), Pan African Cancer Research Institute (PACRI), University of Pretoria, Hatfield 0028, South Africa
| | - Claire Sanders
- Department of Surgery, Helen Joseph Hospital, University of the Witwatersrand, Auckland Park, Johannesburg 2006, South Africa
| | - Zodwa Dlamini
- SAMRC Precision Oncology Research Unit (PORU), DSI/NRF SARChI Chair in Precision Oncology and Cancer Prevention (POCP), Pan African Cancer Research Institute (PACRI), University of Pretoria, Hatfield 0028, South Africa
| |
Collapse
|
|
17
|
Wong CM, Kezlarian BE, Lin O. Current status of machine learning in thyroid cytopathology. J Pathol Inform 2023; 14:100309. [PMID: 37077698 PMCID: PMC10106504 DOI: 10.1016/j.jpi.2023.100309] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/24/2023] [Revised: 03/24/2023] [Accepted: 03/27/2023] [Indexed: 04/03/2023] Open
Abstract
The implementation of Digital Pathology has allowed the development of computational Pathology. Digital image-based applications that have received FDA Breakthrough Device Designation have been primarily focused on tissue specimens. The development of Artificial Intelligence-assisted algorithms using Cytology digital images has been much more limited due to technical challenges and a lack of optimized scanners for Cytology specimens. Despite the challenges in scanning whole slide images of cytology specimens, there have been many studies evaluating CP to create decision-support tools in Cytopathology. Among different Cytology specimens, thyroid fine needle aspiration biopsy (FNAB) specimens have one of the greatest potentials to benefit from machine learning algorithms (MLA) derived from digital images. Several authors have evaluated different machine learning algorithms focused on thyroid cytology in the past few years. The results are promising. The algorithms have mostly shown increased accuracy in the diagnosis and classification of thyroid cytology specimens. They have brought new insights and demonstrated the potential for improving future cytopathology workflow efficiency and accuracy. However, many issues still need to be addressed to further build on and improve current MLA models and their applications. To optimally train and validate MLA for thyroid cytology specimens, larger datasets obtained from multiple institutions are needed. MLAs hold great potential in improving thyroid cancer diagnostic speed and accuracy that will lead to improvements in patient management.
Collapse
Affiliation(s)
| | | | - Oscar Lin
- Corresponding author at: Department of Pathology and Laboratory Medicine, Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA.
| |
Collapse
|
|
18
|
Yang L, Lin N, Wang M, Chen G. Diagnostic efficiency of existing guidelines and the AI-SONIC™ artificial intelligence for ultrasound-based risk assessment of thyroid nodules. Front Endocrinol (Lausanne) 2023; 14:1116550. [PMID: 36875473 PMCID: PMC9975494 DOI: 10.3389/fendo.2023.1116550] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/13/2022] [Accepted: 02/03/2023] [Indexed: 02/17/2023] Open
Abstract
Introduction The thyroid ultrasound guidelines include the American College of Radiology Thyroid Imaging Reporting and Data System, Chinese-Thyroid Imaging Reporting and Data System, Korean Society of Thyroid Radiology, European-Thyroid Imaging Reporting and Data System, American Thyroid Association, and American Association of Clinical Endocrinologists/American College of Endocrinology/Associazione Medici Endocrinologi guidelines. This study aimed to compare the efficiency of the six ultrasound guidelines vs. an artificial intelligence system (AI-SONICTM) in differentiating thyroid nodules, especially medullary thyroid carcinoma. Methods This retrospective study included patients with medullary thyroid carcinoma, papillary thyroid carcinoma, or benign nodules who underwent nodule resection between May 2010 and April 2020 at one hospital. The diagnostic efficacy of the seven diagnostic tools was evaluated using the receiver operator characteristic curves. Results Finally, 432 patients with 450 nodules were included for analysis. The American Association of Clinical Endocrinologists/American College of Endocrinology/Associazione Medici Endocrinologi guidelines had the best sensitivity (88.1%) and negative predictive value (78.6%) for differentiating papillary thyroid carcinoma or medullary thyroid carcinoma vs. benign nodules, while the Korean Society of Thyroid Radiology guidelines had the best specificity (85.6%) and positive predictive value (89.6%), and the American Thyroid Association guidelines had the best accuracy (83.7%). When assessing medullary thyroid carcinoma, the American Thyroid Association guidelines had the highest area under the curve (0.78), the American College of Radiology Thyroid Imaging Reporting and Data System guidelines had the best sensitivity (90.2%), and negative predictive value (91.8%), and AI-SONICTM had the best specificity (85.6%) and positive predictive value (67.5%). The Chinese-Thyroid Imaging Reporting and Data System guidelines had the best under the curve (0.86) in diagnosing malignant tumors vs. benign tumors, followed by the American Thyroid Association and Korean Society of Thyroid Radiology guidelines. The best positive likelihood ratios were achieved by the Korean Society of Thyroid Radiology guidelines and AI-SONICTM (both 5.37). The best negative likelihood ratio was achieved by the American Association of Clinical Endocrinologists/American College of Endocrinology/Associazione Medici Endocrinologi guidelines (0.17). The highest diagnostic odds ratio was achieved by the American Thyroid Association guidelines (24.78). Discussion All six guidelines and the AI-SONICTM system had satisfactory value in differentiating benign vs. malignant thyroid nodules.
Collapse
Affiliation(s)
- Linxin Yang
- Department of Ultrasound, Shengli Clinical Medical College of Fujian Medical University, Fuzhou, China
- Department of Ultrasound, Fujian Provincial Hospital, Fuzhou, China
| | - Ning Lin
- Department of Ultrasound, Shengli Clinical Medical College of Fujian Medical University, Fuzhou, China
- Department of Ultrasound, Fujian Provincial Hospital, Fuzhou, China
| | - Mingyan Wang
- Department of Ultrasound, Shengli Clinical Medical College of Fujian Medical University, Fuzhou, China
| | - Gaofang Chen
- Department of Ultrasound, Shengli Clinical Medical College of Fujian Medical University, Fuzhou, China
| |
Collapse
|
|
19
|
Sorrenti S, Dolcetti V, Radzina M, Bellini MI, Frezza F, Munir K, Grani G, Durante C, D’Andrea V, David E, Calò PG, Lori E, Cantisani V. Artificial Intelligence for Thyroid Nodule Characterization: Where Are We Standing? Cancers (Basel) 2022; 14:cancers14143357. [PMID: 35884418 PMCID: PMC9315681 DOI: 10.3390/cancers14143357] [Citation(s) in RCA: 47] [Impact Index Per Article: 15.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2022] [Revised: 06/24/2022] [Accepted: 07/08/2022] [Indexed: 12/12/2022] Open
Abstract
Simple Summary In the present review, an up-to-date summary of the state of the art of artificial intelligence (AI) implementation for thyroid nodule characterization and cancer is provided. The opinion on the real effectiveness of AI systems remains controversial. Taking into consideration the largest and most scientifically valid studies, it is possible to state that AI provides results that are comparable or inferior to expert ultrasound specialists and radiologists. Promising data approve AI as a support tool and simultaneously highlight the need for a radiologist supervisory framework for AI provided results. Therefore, current solutions might be more suitable for educational purposes. Abstract Machine learning (ML) is an interdisciplinary sector in the subset of artificial intelligence (AI) that creates systems to set up logical connections using algorithms, and thus offers predictions for complex data analysis. In the present review, an up-to-date summary of the current state of the art regarding ML and AI implementation for thyroid nodule ultrasound characterization and cancer is provided, highlighting controversies over AI application as well as possible benefits of ML, such as, for example, training purposes. There is evidence that AI increases diagnostic accuracy and significantly limits inter-observer variability by using standardized mathematical algorithms. It could also be of aid in practice settings with limited sub-specialty expertise, offering a second opinion by means of radiomics and computer-assisted diagnosis. The introduction of AI represents a revolutionary event in thyroid nodule evaluation, but key issues for further implementation include integration with radiologist expertise, impact on workflow and efficiency, and performance monitoring.
Collapse
Affiliation(s)
- Salvatore Sorrenti
- Department of Surgical Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (S.S.); (V.D.); (E.L.)
| | - Vincenzo Dolcetti
- Department of Radiological, Anatomo-Pathological Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (V.D.); (V.C.)
| | - Maija Radzina
- Radiology Research Laboratory, Riga Stradins University, LV-1007 Riga, Latvia;
- Medical Faculty, University of Latvia, Diagnostic Radiology Institute, Paula Stradina Clinical University Hospital, LV-1007 Riga, Latvia
| | - Maria Irene Bellini
- Department of Surgical Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (S.S.); (V.D.); (E.L.)
- Correspondence:
| | - Fabrizio Frezza
- Department of Information Engineering, Electronics and Telecommunications, “Sapienza” University of Rome, 00184 Rome, Italy; (F.F.); (K.M.)
- Consorzio Nazionale Interuniversitario per le Telecomunicazioni (CNIT), Viale G.P. Usberti 181/A Sede Scientifica di Ingegneria-Palazzina 3, 43124 Parma, Italy
| | - Khushboo Munir
- Department of Information Engineering, Electronics and Telecommunications, “Sapienza” University of Rome, 00184 Rome, Italy; (F.F.); (K.M.)
| | - Giorgio Grani
- Department of Translational and Precision Medicine, “Sapienza” University of Rome, 00161 Rome, Italy; (G.G.); (C.D.); (E.D.)
| | - Cosimo Durante
- Department of Translational and Precision Medicine, “Sapienza” University of Rome, 00161 Rome, Italy; (G.G.); (C.D.); (E.D.)
| | - Vito D’Andrea
- Department of Surgical Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (S.S.); (V.D.); (E.L.)
| | - Emanuele David
- Department of Translational and Precision Medicine, “Sapienza” University of Rome, 00161 Rome, Italy; (G.G.); (C.D.); (E.D.)
| | - Pietro Giorgio Calò
- Department of Surgical Sciences, “Policlinico Universitario Duilio Casula”, University of Cagliari, 09042 Monserrato, Italy;
| | - Eleonora Lori
- Department of Surgical Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (S.S.); (V.D.); (E.L.)
| | - Vito Cantisani
- Department of Radiological, Anatomo-Pathological Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (V.D.); (V.C.)
| |
Collapse
|
|
20
|
Editorial on the Special Issue "Novel Methods of Diagnostics of Thyroid and Parathyroid Lesions". J Clin Med 2022; 11:jcm11040932. [PMID: 35207205 PMCID: PMC8875917 DOI: 10.3390/jcm11040932] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2022] [Accepted: 02/09/2022] [Indexed: 02/05/2023] Open
Abstract
Thyroid nodular disease is one of the most frequent endocrine diseases [...].
Collapse
|
|
21
|
Lau RP, Kim TH, Rao J. Advances in Imaging Modalities, Artificial Intelligence, and Single Cell Biomarker Analysis, and Their Applications in Cytopathology. Front Med (Lausanne) 2021; 8:689954. [PMID: 34277664 PMCID: PMC8282905 DOI: 10.3389/fmed.2021.689954] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2021] [Accepted: 06/08/2021] [Indexed: 12/14/2022] Open
Abstract
Several advances in recent decades in digital imaging, artificial intelligence, and multiplex modalities have improved our ability to automatically analyze and interpret imaging data. Imaging technologies such as optical coherence tomography, optical projection tomography, and quantitative phase microscopy allow analysis of tissues and cells in 3-dimensions and with subcellular granularity. Improvements in computer vision and machine learning have made algorithms more successful in automatically identifying important features to diagnose disease. Many new automated multiplex modalities such as antibody barcoding with cleavable DNA (ABCD), single cell analysis for tumor phenotyping (SCANT), fast analytical screening technique fine needle aspiration (FAST-FNA), and portable fluorescence-based image cytometry analyzer (CytoPAN) are under investigation. These have shown great promise in their ability to automatically analyze several biomarkers concurrently with high sensitivity, even in paucicellular samples, lending themselves well as tools in FNA. Not yet widely adopted for clinical use, many have successfully been applied to human samples. Once clinically validated, some of these technologies are poised to change the routine practice of cytopathology.
Collapse
Affiliation(s)
- Ryan P. Lau
- Department of Pathology and Laboratory Medicine, David Geffen School of Medicine at the University of California, Los Angeles, CA, United States
| | | | | |
Collapse
|