Rxivist logo

A deep convolutional neural network-based algorithm for muscle biopsy diagnosis outperforms human specialists

By Yoshinori Kabeya, Mariko Okubo, Sho Yonezawa, Hiroki Nakano, Michio Inoue, Masashi Ogasawara, Yoshihiko Saito, Jantima Tanboon, Luh Ari Indrawati, Theerawat Kumutpongpanich, Yen-Lin Chen, Wakako Yoshioka, Shinichiro Hayashi, Toshiya Iwamori, Yusuke Takeuchi, Reitaro Tokumasu, Atsushi Takano, Fumihiko Matsuda, Ichizo Nishino

Posted 16 Dec 2020
medRxiv DOI: 10.1101/2020.12.15.20248231

Histopathologic evaluation is essential for categorizing and studying neuromuscular disorders. However, experienced specialists and pathologists are limited, especially in underserved areas. Although new technologies, such as artificial intelligence, are expected to improve medical reach, their use in rare diseases is challenging because of the limited availability of training datasets. To address this knowledge gap, we developed an algorithm based on deep convolutional neural networks that used data from microscopic images of hematoxylin-and-eosin-stained pathology slides. Our algorithm differentiated idiopathic inflammatory myopathies (mostly treatable) from hereditary muscle diseases (mostly non-treatable) and achieved better sensitivity and specificity than real physicians' diagnoses. Furthermore, it successfully and accurately classified four subtypes of the abovementioned muscular conditions. These results suggest that our algorithm can be safely used in a clinical setting. We established the similarity between the algorithm's and physicians' predictions using visualization technology, and clarified the validity of the predictions.

Download data

  • Downloaded 188 times
  • Download rankings, all-time:
    • Site-wide: 110,493
    • In pathology: 642
  • Year to date:
    • Site-wide: 20,808
  • Since beginning of last month:
    • Site-wide: 19,715

Altmetric data


Downloads over time

Distribution of downloads per paper, site-wide


PanLingua

Sign up for the Rxivist weekly newsletter! (Click here for more details.)


News