Deep Learning Algorithm to Detect Cardiac Sarcoidosis From Echocardiographic Movies
Deep Learning Algorithm to Detect Cardiac Sarcoidosis From Echocardiographic Movies
复制标题
DOI：
10.1253/circj.cj-21-0265
复制
发表时间：
2022-01-01
影响因子：
3.3
通讯作者：
Komuro, Issei
中科院分区：
文献类型：
--
作者：
Katsushika, Susumu;Kodera, Satoshi;Komuro, Issei
背景：由于亚临床心脏结节病（CS）的早期诊断仍然困难，我们开发了一种深度学习算法，通过超声心动图将CS患者与健康受试者区分开来。方法与结果：在2015年1月至2019年12月接受超声心动图检查的患者中，我们从50名CS患者中选择151张超声心动图，从149名健康受试者中选择151张。我们训练了两个3D卷积神经网络（3D- cnn）来识别CS患者，使用212个超声心动图电影数据集，使用和不使用迁移学习方法（预训练算法和非预训练算法）。在一组独立的41张超声心动图片上，预训练算法的受者工作特征曲线下面积（AUC）大于非预训练算法（0.842,95%可信区间（CI）： 0.722-0.962 vs. 0.724, 95% CI: 0.566-0.882， P=0.253）。5位心内科医生对同一组41部超声心动图的AUC与预训练算法的AUC差异无统计学意义（0.855,95% CI: 0.735-0.975 vs. 0.842, 95% CI: 0.722-0.962， P=0.885）。敏感度图表明，预训练算法的重点是二尖瓣的面积。结论：采用迁移学习方法的3D-CNN可能是一种很有前途的超声心动图电影检测CS的工具。
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.