{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T18:27:14Z","timestamp":1786559234933,"version":"build-2736575974"},"reference-count":24,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:00:00Z","timestamp":1786492800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Myocarditis is life-threatening in the acute phase, yet biopsy\u2014the diagnostic gold standard\u2014lacks an objective method to quantify cardiomyocyte damage. We developed deep learning models to derive a pathology-based severity index for myocarditis from whole-slide biopsy images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods and results<\/jats:title>\n                    <jats:p>We retrospectively analyzed 305 consecutive patients (1,056 digitized hematoxylin\u2013eosin slides) who underwent endomyocardial biopsy between 2002 and 2021 at the National Cerebral and Cardiovascular Center; 145 met Dallas criteria for myocarditis and were used for severity modeling. Severe myocarditis was defined by short-term in-hospital outcomes (SCAI-aligned cardiogenic shock, initiation of mechanical circulatory support, or death). A multiple instance learning (MIL) classifier was first trained on slide-level myocarditis labels. We then built two severity models: (1) logistic regression using lymphocyte density derived from a YOLOv8-based object detector (Model 1), and (2) a Transformer that processed the top MIL-ranked patches to predict severe versus non-severe myocarditis (Model 2). Model 1 confirmed a strong association between inflammatory burden and severe outcomes (AUROC 0.809). Model 2 achieved superior discrimination (AUROC 0.993) with higher accuracy and precision. Attention maps indicated that Model 2 focused not only on inflammatory infiltrates but also on myocyte injury and architectural disruption, suggesting broader histologic signal capture. The final output was a continuous pathology-based severity score; clinical variables were not input to the models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Combining MIL with a Transformer enables comprehensive extraction of histologic features associated with clinically severe myocarditis and yields an objective, reproducible tissue-injury index. This score is intended to standardize histologic severity assessment and complement, rather than replace, clinical evaluation; incremental clinical utility requires prospective, multi-center validation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0354714","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T17:28:36Z","timestamp":1786555716000},"page":"e0354714","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning in Myocarditis: A novel approach to severity assessment"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1366-9948","authenticated-orcid":true,"given":"Makoto","family":"Nishimori","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomoyuki","family":"Otani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9009-7234","authenticated-orcid":true,"given":"Yasuhide","family":"Asaumi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keiko","family":"Ogo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshihiko","family":"Ikeda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kisaki","family":"Amemiya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teruo","family":"Noguchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chisato","family":"Izumi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masakazu","family":"Shinohara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kinta","family":"Hatakeyama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0639-0949","authenticated-orcid":true,"given":"Kunihiro","family":"Nishimura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,12]]},"reference":[{"issue":"3","key":"pone.0354714.ref001","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1016\/j.athoracsur.2015.08.014","article-title":"Venoarterial extracorporeal membrane oxygenation for acute fulminant myocarditis in adult patients: a 5-year multi-institutional experience","volume":"101","author":"R Lorusso","year":"2016","journal-title":"Ann Thorac Surg"},{"issue":"10","key":"pone.0354714.ref002","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1056\/NEJM200003093421003","article-title":"Long-term outcome of fulminant myocarditis as compared with acute (nonfulminant) myocarditis","volume":"342","author":"3rd McCarthy RE","year":"2000","journal-title":"N Engl J Med"},{"issue":"11","key":"pone.0354714.ref003","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1038\/ncpcardio1331","article-title":"Fulminant myocarditis","volume":"5","author":"S Gupta","year":"2008","journal-title":"Nat Clin Pract Cardiovasc Med"},{"issue":"1","key":"pone.0354714.ref004","first-page":"3","article-title":"Myocarditis. A histopathologic definition and classification","volume":"1","author":"HT Aretz","year":"1987","journal-title":"Am J Cardiovasc Pathol"},{"issue":"11","key":"pone.0354714.ref005","doi-asserted-by":"crossref","DOI":"10.1161\/CIRCHEARTFAILURE.120.007405","article-title":"Management of acute myocarditis and chronic inflammatory cardiomyopathy: an expert consensus document","volume":"13","author":"E Ammirati","year":"2020","journal-title":"Circ Heart Fail"},{"issue":"1","key":"pone.0354714.ref006","doi-asserted-by":"crossref","DOI":"10.52225\/narra.v3i1.104","article-title":"Monkeypox virus infection and myocarditis: a review of current evidence and possible pathogenesis","volume":"3","author":"SK Ahmed","year":"2023","journal-title":"Narra J"},{"issue":"19","key":"pone.0354714.ref007","doi-asserted-by":"crossref","first-page":"1425","DOI":"10.1161\/CIRCULATIONAHA.121.058869","article-title":"Features and outcomes of histologically proven myocarditis with fulminant presentation","volume":"146","author":"K Kanaoka","year":"2022","journal-title":"Circulation"},{"issue":"1","key":"pone.0354714.ref008","doi-asserted-by":"crossref","first-page":"4294","DOI":"10.1038\/s41467-020-18147-8","article-title":"Clinically applicable histopathological diagnosis system for gastric cancer detection using deep learning","volume":"11","author":"Z Song","year":"2020","journal-title":"Nat Commun"},{"issue":"1","key":"pone.0354714.ref009","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1186\/s12916-021-01953-2","article-title":"Deep learning-based six-type classifier for lung cancer and mimics from histopathological whole slide images: a retrospective study","volume":"19","author":"H Yang","year":"2021","journal-title":"BMC Med"},{"issue":"1","key":"pone.0354714.ref010","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1186\/s13058-024-01895-6","article-title":"Deep learning applications in breast cancer histopathological imaging: diagnosis, treatment, and prognosis","volume":"26","author":"B Jiang","year":"2024","journal-title":"Breast Cancer Res"},{"key":"pone.0354714.ref011","doi-asserted-by":"crossref","first-page":"8733632","DOI":"10.1155\/2022\/8733632","article-title":"RLMD-PA: a reinforcement learning-based myocarditis diagnosis combined with a population-based algorithm for pretraining weights","volume":"2022","author":"SV Moravvej","year":"2022","journal-title":"Contrast Media Mol Imaging"},{"key":"pone.0354714.ref012","article-title":"Support vector machines for multiple-instance learning","volume":"15","author":"S Andrews","year":"2002","journal-title":"Advances in neural information processing systems"},{"key":"pone.0354714.ref013","doi-asserted-by":"crossref","first-page":"102337","DOI":"10.1016\/j.compmedimag.2024.102337","article-title":"Multiple instance learning for digital pathology: a review of the state-of-the-art, limitations & future potential","volume":"112","author":"M Gadermayr","year":"2024","journal-title":"Comput Med Imaging Graph"},{"key":"pone.0354714.ref014","article-title":"Attention is all you need","author":"A Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"9","key":"pone.0354714.ref015","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1016\/j.jacc.2022.01.018","article-title":"SCAI SHOCK Stage Classification Expert Consensus Update: A Review and Incorporation of Validation Studies: This statement was endorsed by the American College of Cardiology (ACC), American College of Emergency Physicians (ACEP), American Heart Association (AHA), European Society of Cardiology (ESC) Association for Acute Cardiovascular Care (ACVC), International Society for Heart and Lung Transplantation (ISHLT), Society of Critical Care Medicine (SCCM), and Society of Thoracic Surgeons (STS) in December 2021","volume":"79","author":"SS Naidu","year":"2022","journal-title":"J Am Coll Cardiology"},{"key":"pone.0354714.ref016","doi-asserted-by":"crossref","first-page":"27","DOI":"10.4103\/2153-3539.119005","article-title":"OpenSlide: a vendor-neutral software foundation for digital pathology","volume":"4","author":"A Goode","year":"2013","journal-title":"J Pathol Inform"},{"issue":"8","key":"pone.0354714.ref017","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1038\/s41591-019-0508-1","article-title":"Clinical-grade computational pathology using weakly supervised deep learning on whole slide images","volume":"25","author":"G Campanella","year":"2019","journal-title":"Nat Med"},{"key":"pone.0354714.ref018","unstructured":"Wang Z, Wang P, Liu K, Wang P, Fu Y, Lu CT. A Comprehensive Survey on Data Augmentation. 2024. https:\/\/doi.org\/arXiv:240509591"},{"key":"pone.0354714.ref019","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: unified, real-time object detection. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), 2016. 779\u201388. https:\/\/doi.org\/10.1109\/cvpr.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"pone.0354714.ref020","article-title":"Practical bayesian optimization of machine learning algorithms","volume":"25","author":"J Snoek","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0354714.ref021","doi-asserted-by":"crossref","DOI":"10.4135\/9781412983532","volume-title":"Bootstrapping: a nonparametric approach to statistical inference","author":"CZ Mooney","year":"1993"},{"key":"pone.0354714.ref022","article-title":"Pytorch: an imperative style, high-performance deep learning library","volume":"32","author":"A Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"6","key":"pone.0354714.ref023","doi-asserted-by":"crossref","DOI":"10.3390\/biology12060874","article-title":"Myocarditis: etiology, pathogenesis, and their implications in clinical practice","volume":"12","author":"E Brociek","year":"2023","journal-title":"Biology"},{"issue":"9","key":"pone.0354714.ref024","doi-asserted-by":"crossref","first-page":"517","DOI":"10.3390\/info15090517","article-title":"Recurrent neural networks: a comprehensive review of architectures, variants, and applications","volume":"15","author":"ID Mienye","year":"2024","journal-title":"Information"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0354714","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T17:28:41Z","timestamp":1786555721000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0354714"}},"subtitle":[],"editor":[{"given":"Muhammad","family":"Iqhrammullah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,12]]},"references-count":24,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,12]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0354714","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,12]]}}}