{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T23:31:46Z","timestamp":1790379106453,"version":"4.1.0"},"reference-count":61,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T00:00:00Z","timestamp":1749600000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Metastatic detection in sentinel lymph nodes remains a crucial prognostic factor in breast cancer management, with accurate and timely diagnosis directly impacting treatment decisions. While traditional histopathological assessment relies on microscopic examination of stained tissues, the digitization of slides as whole-slide images (WSI) has enabled the development of computer-aided diagnostic systems. These automated approaches offer potential improvements in detection consistency and efficiency compared to conventional methods.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>This study leverages transfer learning on hematoxylin and eosin (HE) WSIs to achieve computationally efficient metastasis detection without compromising accuracy. We propose an approach for generating segmentation masks by transferring spatial annotations from immunohistochemistry (IHC) WSIs to corresponding H&amp;amp;E slides. Using these masks, four distinct datasets were constructed to fine-tune a pretrained ResNet50 model across eight different configurations, incorporating varied dataset combinations and data augmentation techniques. To enhance interpretability, we developed a visualization tool that employs color-coded probability maps to highlight tumor regions alongside their prediction confidence. Our experiments demonstrated that integrating an external dataset (Camelyon16) during training significantly improved model performance, surpassing the benefits of data augmentation alone. The optimal model, trained on both external and local data, achieved an accuracy and F1-score of 0.98, outperforming existing state-of-the-art methods.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>This study demonstrates that transfer learning architectures, when enhanced with multi-source data integration and interpretability frameworks, can significantly improve metastatic detection in whole slide imaging. Our methodology achieves diagnostic performance comparable to gold-standard techniques while dramatically accelerating analytical workflows. The synergistic combination of external dataset incorporation and probabilistic visualization outputs provides a clinically actionable solution that maintains both computational efficiency and pathological interpretability.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fonc.2025.1598289","type":"journal-article","created":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T05:14:54Z","timestamp":1749618894000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["AI-augmented pathology: the experience of transfer learning and intra-domain data diversity in breast cancer metastasis detection"],"prefix":"10.3389","volume":"15","author":[{"given":"Manuel","family":"Cossio","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nina","family":"Wiedemann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esther","family":"Sanfeliu Torres","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esther","family":"Barnadas Sole","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura","family":"Igual","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3322\/caac.21551","article-title":"Cancer statistics, 2019","volume":"69","author":"Siegel","year":"2019","journal-title":"CA: Cancer J Clin"},{"key":"B2","first-page":"97","volume-title":"Ajcc cancer staging manual","author":"Edge","year":"2010"},{"key":"B3","doi-asserted-by":"publisher","first-page":"giy065","DOI":"10.1093\/gigascience\/giy065","article-title":"1399 h&e-stained sentinel lymph node sections of breast cancer patients: the camelyon dataset","volume":"7","author":"Litjens","year":"2018","journal-title":"GigaScience"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1746-1596-6-18","article-title":"Predictive value of pathological and immunohistochemical parameters for axillary lymph node metastasis in breast carcinoma","volume":"6","author":"Yenidunya","year":"2011","journal-title":"Diagn Pathol"},{"key":"B5","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1148\/radiol.2019190372","article-title":"Lymph node metastasis prediction from primary breast cancer us images using deep learning","volume":"294","author":"Zhou","year":"2020","journal-title":"Radiology"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1136\/jcp.57.1.73","article-title":"Factors affecting metastases to non-sentinel lymph nodes in breast cancer","volume":"57","author":"Fleming","year":"2004","journal-title":"J Clin Pathol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1038\/sj.bjc.6602641","article-title":"The value of immunohistochemistry in sentinel lymph node histopathology in breast cancer","volume":"92","author":"Klevesath","year":"2005","journal-title":"Br J Cancer"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.v101:5","article-title":"Cytokeratin-positive cells in sentinel lymph nodes in breast cancer are not random events: experience in patients undergoing prophylactic mastectomy","volume":"101","author":"King","year":"2004","journal-title":"Cancer"},{"key":"B9","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1097\/00000658-199509000-00016","article-title":"Improved axillary staging of breast cancer with sentinel lymphadenectomy","volume":"222","author":"Giuliano","year":"1995","journal-title":"Ann Surg"},{"key":"B10","article-title":"Principle and techniques of immunohistochemistry\u2014a review","volume":"6","author":"Kabiraj","year":"2015","journal-title":"Int J Biol Med Res"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-022-06264-x","article-title":"A promising deep learning-assistive algorithm for histopathological screening of colorectal cancer","volume":"12","author":"Ho","year":"2022","journal-title":"Sci Rep"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0177-5","article-title":"Classification and mutation prediction from non\u2013small cell lung cancer histopathology images using deep learning","volume":"24","author":"Coudray","year":"2018","journal-title":"Nat Med"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1111\/jop.13560","article-title":"Feasibility study of resnet-50 in the distinction of intraoral neural tumors using histopathological images","author":"Santos","year":"2024","journal-title":"J Oral Pathol Med"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/srep46450","article-title":"Accurate and reproducible invasive breast cancer detection in whole-slide images: A deep learning approach for quantifying tumor extent","volume":"7","author":"Cruz-Roa","year":"2017","journal-title":"Sci Rep"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3187765","article-title":"A deep learning method for breast cancer classification in the pathology images","volume":"26","author":"Liu","year":"2022","journal-title":"IEEE J Biomed Health Inf"},{"key":"B16","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.ymeth.2019.06.014","article-title":"Breast cancer histopathological image classification using a hybrid deep neural network","volume":"173","author":"Yan","year":"2020","journal-title":"Methods"},{"key":"B17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ISBI56570.2024.10635534","article-title":"Transfer learning approach for detecting breast cancer tumour subtypes in whole-slide images","volume-title":"2024 IEEE international symposium on biomedical imaging (ISBI)","author":"Varavadekar","year":"2024"},{"key":"B18","doi-asserted-by":"publisher","first-page":"661","DOI":"10.3390\/cancers13040661","article-title":"Boosted efficientnet: Detection of lymph node metastases in breast cancer using convolutional neural networks","volume":"13","author":"Wang","year":"2021","journal-title":"Cancers"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-78129-0","article-title":"Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections","volume":"10","author":"Kim","year":"2020","journal-title":"Sci Rep"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01614-0","article-title":"Ai in health and medicine","volume":"28","author":"Rajpurkar","year":"2022","journal-title":"Nat Med"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-21-0482","article-title":"Predicting molecular phenotypes from histopathology images: a transcriptome-wide expression-morphology analysis in breast cancer","author":"Wang","year":"2020","journal-title":"arXiv preprint arXiv:2009.08917"},{"key":"B22","article-title":"The lancet digital health","volume":"5","year":"2023","journal-title":"Curbing carbon footprint Health Care"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2559.2007.02869.x","article-title":"Angiogenesis and mast cells in human breast cancer sentinel lymph nodes with and without micrometastases","volume":"51","author":"Ribatti","year":"2007","journal-title":"Histopathology"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2559.2011.03814.x","article-title":"Digital pathology: current status and future perspectives","author":"Al-Janabi","year":"2012","journal-title":"Histopathology"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajpath.2019.05.007","article-title":"Pathology image analysis using segmentation deep learning algorithms","volume":"189","author":"Wang","year":"2019","journal-title":"Am J Pathol"},{"key":"B26","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-23937-4_12","article-title":"Multi-tissue partitioning for whole slide images of colorectal cancer histopathology images with deeptissue net","volume-title":"Digital pathology: 15th european congress, ECDP 2019, warwick, UK, april 10\u201313, 2019, proceedings","author":"Xu","year":"2019"},{"key":"B27","doi-asserted-by":"publisher","first-page":"6753","DOI":"10.1038\/s41467-022-34275-9","article-title":"Deep learning-based image analysis predicts pd-l1 status from h&e-stained histopathology images in breast cancer","volume":"13","author":"Shamai","year":"2022","journal-title":"Nat Commun"},{"key":"B28","article-title":"Deep learning for detecting breast cancer metastases on wsi","volume-title":"In","author":"Fan","year":"2019"},{"key":"B29","doi-asserted-by":"publisher","first-page":"11579","DOI":"10.1038\/s41598-021-90444-8","article-title":"A generalized deep learning framework for whole-slide image segmentation and analysis","volume":"11","author":"Khened","year":"2021","journal-title":"Sci Rep"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1109\/Access.6287639","article-title":"Deep learning applied for histological diagnosis of breast cancer","volume":"8","author":"Yari","year":"2020","journal-title":"IEEE Access"},{"key":"B31","doi-asserted-by":"crossref","DOI":"10.1109\/ISCIT.2019.8905196","article-title":"Breast cancer histology image classification using deep learning","volume-title":"2019 19th international symposium on communications and information technologies (ISCIT)","author":"Nguyen","year":"2019"},{"key":"B32","article-title":"Leandro T Hattori, and Heitor S Lopes. The effect of data augmentation on the performance of convolutional neural networks","volume":"10","author":"Romero Aquino","year":"2017","journal-title":"Braz Soc Comput Intell"},{"key":"B33","doi-asserted-by":"publisher","first-page":"100138","DOI":"10.1016\/j.jpi.2022.100138","article-title":"Artificial intelligence as a tool for diagnosis in digital pathology whole slide images: a systematic review","volume":"13","author":"Rodriguez","year":"2022","journal-title":"J Pathol Inf"},{"key":"B34","first-page":"1","article-title":"Histotransfer: understanding transfer learning for histopathology","volume-title":"In","author":"Sharmay","year":"2021"},{"key":"B35","doi-asserted-by":"publisher","first-page":"19","DOI":"10.3390\/info9010019","article-title":"Histopathological breast-image classification using local and frequency domains by convolutional neural network","volume":"9","author":"Nahid","year":"2018","journal-title":"Information"},{"key":"B36","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.neucom.2019.09.044","article-title":"Breakhis based breast cancer automatic diagnosis using deep learning: Taxonomy, survey and insights","volume":"375","author":"Benhammou","year":"2020","journal-title":"Neurocomputing"},{"key":"B37","first-page":"21","volume-title":"In","author":"Cascianelli","year":"2018"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.47852\/bonviewJDSIS3202744","article-title":"Resnet for histopathologic cancer detection, the deeper, the better","volume":"2","author":"Wang","year":"2024","journal-title":"J Data Sci Intelligent Syst"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1007\/s12553-021-00592-0","article-title":"Classification of breast cancer types, subtypes and grade from histopathological images using deep learning technique","volume":"11","author":"Zewdie","year":"2021","journal-title":"Health Technol"},{"key":"B40","article-title":"Breast cancer detection from histopathological biopsy images using transfer learning","volume-title":"In","author":"Vo-Le","year":"2021"},{"key":"B41","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2019.2897281","article-title":"Heterogeneity-aware local binary patterns for retrieval of histopathology images","volume-title":"IEEE access","author":"Erfankhah","year":"2019"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2470529","article-title":"Triaging diagnostically relevant regions from pathology whole slides of breast cancer: A texture based approach","volume":"35","author":"Peikari","year":"2015","journal-title":"IEEE Trans Med Imaging"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2016.2515127","article-title":"Robust nucleus\/cell detection and segmentation in digital pathology and microscopy images: a comprehensive review","volume":"9","author":"Xing","year":"2016","journal-title":"IEEE Rev Biomed Eng"},{"key":"B44","doi-asserted-by":"publisher","first-page":"3383","DOI":"10.1038\/s41598-022-07217-0","article-title":"A deep learning system for prostate cancer diagnosis and grading in whole slide images of core needle biopsies","volume":"12","author":"Singhal","year":"2022","journal-title":"Sci Rep"},{"key":"B45","doi-asserted-by":"publisher","first-page":"4","DOI":"10.61356\/SMIJ.2024.8290","article-title":"Visioncam: a comprehensive xai toolkit for interpreting image-based deep learning models","volume":"8","author":"Abdullah","year":"2024","journal-title":"Sustain Mach Intell J"},{"key":"B46","doi-asserted-by":"publisher","first-page":"96","DOI":"10.59275\/j.melba.2023-5g54","article-title":"Deep weakly-supervised learning methods for classification and localization in histology images: A survey","volume":"2","author":"Rony","year":"2023","journal-title":"J Mach Learn Biomed Imaging"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-022-00722-8","article-title":"Convolutional neural networks for classifying cervical cancer types using histological images","volume":"36","author":"Li","year":"2023","journal-title":"J Digital Imaging"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2867350","article-title":"From detection of individual metastases to classification of lymph node status at the patient level: the camelyon17 challenge","volume":"38","author":"Bandi","year":"2018","journal-title":"IEEE Trans Med Imaging"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2021.01.025","article-title":"Deep learning in image classification using residual network (resnet) variants for detection of colorectal cancer","volume":"179","author":"Sarwinda","year":"2021","journal-title":"Proc Comput Sci"},{"key":"B50","article-title":"Deep learning approach for breast cancer diagnosis from microscopy biopsy images","volume-title":"In","author":"Eldin","year":"2021"},{"key":"B51","article-title":"Deep residual learning for image recognition","volume-title":"In","author":"He","year":"2016"},{"key":"B52","doi-asserted-by":"crossref","DOI":"10.1117\/12.2623103","article-title":"A new breast cancer diagnosis application based on resnet50","volume-title":"Second IYSF academic symposium on artificial intelligence and computer engineering","author":"Le","year":"2021"},{"key":"B53","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-93000-8_92","article-title":"Classification of breast cancer histology images using transfer learning","volume-title":"Image analysis and recognition: 15th international conference, ICIAR 2018, p\u00f3voa de varzim, Portugal, june 27\u201329, 2018, proceedings","author":"Vesal","year":"2018"},{"key":"B54","first-page":"1","article-title":"Going deeper with convolutions","volume-title":"In","author":"Szegedy","year":"2015"},{"key":"B55","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"B56","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint arXiv:1409.1556"},{"key":"B57","volume-title":"arXiv preprint arXiv:1507.07242","author":"Wang","year":"2015"},{"key":"B58","doi-asserted-by":"publisher","first-page":"3945","DOI":"10.1038\/s41598-024-74531-0","article-title":"Comparison of deep transfer learning models for classification of cervical cancer from pap smear images","volume":"15","author":"Kaur","year":"2025","journal-title":"Sci Rep"},{"key":"B59","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.surge.2016.07.002","article-title":"Micro-and macro-metastasis in the axillary lymph node: A review","volume":"15","author":"Naidoo","year":"2017","journal-title":"surgeon"},{"key":"B60","volume-title":"Immunohistochemistry: methods express","author":"Renshaw","year":"2006"},{"key":"B61","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3892\/mco.2022.2491","article-title":"ntraoperative prediction of non-sentinel lymph node metastases in breast cancer using cytokeratin 19 mrna copy number: A retrospective analysis","volume":"16","author":"Pina","year":"2022","journal-title":"Mol Clin Oncol"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1598289\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T05:14:59Z","timestamp":1749618899000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1598289\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,11]]},"references-count":61,"alternative-id":["10.3389\/fonc.2025.1598289"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2025.1598289","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,11]]},"article-number":"1598289"}}