Deep Learning Algorithm to Detect Cardiac Sarcoidosis From Echocardiographic Movies

• Published in: Circulation Journal Vol. 86; no. 1; pp. 87 - 95
• Main Authors: Kakuda, Nobutaka, Shinohara, Hiroki, Morita, Hiroyuki, Fujiu, Katsuhito, Ieki, Hirotaka, Akazawa, Hiroshi, Matsuoka, Ryo, Higashikuni, Yasutomi, Uehara, Masae, Kodera, Satoshi, Komuro, Issei, Takeda, Norifumi, Nakanishi, Koki, Daimon, Masao, Ninomiya, Kota, Ando, Jiro, Katsushika, Susumu, Nakamoto, Mitsuhiko, Nakao, Tomoko
• Format: Journal Article
• Language: English
• Published: Japan The Japanese Circulation Society 24.12.2021
• Subjects: Algorithms; Artificial intelligence; Cardiac sarcoidosis; Deep Learning; Echocardiography; Humans; Motion Pictures; Myocarditis; Sarcoidosis - diagnostic imaging; Transfer learning; Deep learning; Echocardiography; Transfer learning; Artificial intelligence; Cardiac sarcoidosis
• ISSN: 1346-9843; 1347-4820; 1347-4820
• DOI: 10.1253/circj.CJ-21-0265

Background:Because the early diagnosis of subclinical cardiac sarcoidosis (CS) remains difficult, we developed a deep learning algorithm to distinguish CS patients from healthy subjects using echocardiographic movies.Methods and Results:Among the patients who underwent echocardiography from January 2015 to December 2019, we chose 151 echocardiographic movies from 50 CS patients and 151 from 149 healthy subjects. We trained two 3D convolutional neural networks (3D-CNN) to identify CS patients using a dataset of 212 echocardiographic movies with and without a transfer learning method (Pretrained algorithm and Non-pretrained algorithm). On an independent set of 41 echocardiographic movies, the area under the receiver-operating characteristic curve (AUC) of the Pretrained algorithm was greater than that of Non-pretrained algorithm (0.842, 95% confidence interval (CI): 0.722–0.962 vs. 0.724, 95% CI: 0.566–0.882, P=0.253). The AUC from the interpretation of the same set of 41 echocardiographic movies by 5 cardiologists was not significantly different from that of the Pretrained algorithm (0.855, 95% CI: 0.735–0.975 vs. 0.842, 95% CI: 0.722–0.962, P=0.885). A sensitivity map demonstrated that the Pretrained algorithm focused on the area of the mitral valve.Conclusions:A 3D-CNN with a transfer learning method may be a promising tool for detecting CS using an echocardiographic movie.