Deep learning in Myocarditis: A novel approach to severity assessment
Makoto Nishimori, Tomoyuki Otani, Yasuhide Asaumi, Keiko Ogo, Yoshihiko Ikeda, Kisaki Amemiya, Teruo Noguchi, Chisato Izumi · 2026
Read Deep learning in Myocarditis: A novel approach to severity assessment by Makoto Nishimori, Tomoyuki Otani, Yasuhide Asaumi, Keiko Ogo, Yoshihiko Ikeda, Kisaki Amemiya, Teruo Noguchi, Chisato Izumi (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0354714.txt.
Description
Makoto Nishimori and colleagues taught deep learning systems to grade heart muscle inflammation from biopsy slides. Myocarditis can kill quickly, yet the gold-standard biopsy lacks an objective severity score. Their 2026 study used slides from several hundred patients at a national heart centre, with severe cases defined by shock, support machines, or death.
One model scored severity from the density of immune cells counted by a detection system. A second model, reading the most telling slide patches with a transformer, separated severe from milder cases almost perfectly in testing. Its attention maps highlighted both inflammation and muscle injury. Nishimori and colleagues propose the score as a standardised tissue index, pending wider validation.
Catalog record
| CREATOR | Makoto Nishimori, Tomoyuki Otani, Yasuhide Asaumi, Keiko Ogo, Yoshihiko Ikeda, Kisaki Amemiya, Teruo Noguchi, Chisato Izumi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 27314 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |