Deep learning in Myocarditis: A novel approach to severity assessment
PLOS One · 12.08.2026 · 21 (8) · e0354714
DOI: 10.1371/journal.pone.0354714 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 12.08.2026. Verfasst von Makoto Nishimori und 10 weiteren Autor:innen. Beteiligte Einrichtung: Division of Molecular Epidemiology, Kobe University Graduate School of Medicine, Kobe, Japan. Hauptthemen laut MEDLINE: Myocarditis, Deep Learning. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Myocarditis is life-threatening in the acute phase, yet biopsy—the diagnostic gold standard—lacks 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. Methods and results We retrospectively analyzed 305 consecutive patients (1,056 digitized hematoxylin–eosin 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.
Conclusions
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Division of Molecular Epidemiology, Kobe University Graduate School of Medicine, Kobe, Japan.
- Department of Preventive Medicine and Epidemiology, National Cerebral and Cardiovascular Center, Osaka, Japan.
- Department of Pathology, National Cerebral and Cardiovascular Center, Osaka, Japan.
- Department of Cardiology, National Cerebral and Cardiovascular Center, Osaka, Japan.
ORCID-Profile: Makoto Nishimori, Yasuhide Asaumi, Kunihiro Nishimura
Zitieren
APA
Nishimori, M., Otani, T., Asaumi, Y., Ogo, K., Ikeda, Y., Amemiya, K., Noguchi, T., Izumi, C., Shinohara, M., Hatakeyama, K., & Nishimura, K. (2026). Deep learning in Myocarditis: A novel approach to severity assessment. PLOS One, 21(8), e0354714. https://doi.org/10.1371/journal.pone.0354714
Vancouver
Nishimori M, Otani T, Asaumi Y, Ogo K, Ikeda Y, Amemiya K, et al. Deep learning in Myocarditis: A novel approach to severity assessment. PLOS One. 2026;21(8):e0354714. doi:10.1371/journal.pone.0354714
BibTeX
@article{Nishimori2026,
author = {Nishimori, Makoto and Otani, Tomoyuki and Asaumi, Yasuhide and Ogo, Keiko and Ikeda, Yoshihiko and Amemiya, Kisaki and Noguchi, Teruo and Izumi, Chisato and Shinohara, Masakazu and Hatakeyama, Kinta and Nishimura, Kunihiro},
title = {Deep learning in Myocarditis: A novel approach to severity assessment},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {8},
pages = {e0354714},
doi = {10.1371/journal.pone.0354714}
}
EUVIMED