Deep Learning Algorithm to Detect Cardiac Sarcoidosis From Echocardiographic Movies

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. Among the patients who underwent echocardiography from January 2015 to December 2019, we chos...

Full description

Saved in:
Bibliographic Details
Published in:Circulation journal : official journal of the Japanese Circulation Society Vol. 86; no. 1; p. 87
Main Authors: Katsushika, Susumu, Kodera, Satoshi, Nakamoto, Mitsuhiko, Ninomiya, Kota, Kakuda, Nobutaka, Shinohara, Hiroki, Matsuoka, Ryo, Ieki, Hirotaka, Uehara, Masae, Higashikuni, Yasutomi, Nakanishi, Koki, Nakao, Tomoko, Takeda, Norifumi, Fujiu, Katsuhito, Daimon, Masao, Ando, Jiro, Akazawa, Hiroshi, Morita, Hiroyuki, Komuro, Issei
Format: Journal Article
Language:English
Published: Japan 24.12.2021
Subjects:
Algorithms
Deep Learning
Echocardiography
Humans
Motion Pictures
Myocarditis
Sarcoidosis - diagnostic imaging
Deep learning
Echocardiography
Transfer learning
Artificial intelligence
Cardiac sarcoidosis
ISSN:1347-4820, 1347-4820
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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. 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. A 3D-CNN with a transfer learning method may be a promising tool for detecting CS using an echocardiographic movie.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1347-4820
1347-4820
DOI:10.1253/circj.CJ-21-0265