Automatic stenosis recognition from coronary angiography using convolutional neural networks. (January 2021)

• Record Type: Journal Article
• Authors: Moon, Jong Hak; Lee, Da Young; Cha, Won Chul; Chung, Myung Jin; Lee, Kyu-Sung; Cho, Baek Hwan; Choi, Jin Ho
• Is Part Of: Computer methods and programs in biomedicine. Volume 198(2021)
• Publication Date: 2021-01
• Subjects: Coronary angiography -- Coronary artery stenosis -- Deep learning -- Stenosis recognition -- Automated screening; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2020.105819
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: A weakly-supervised learning based stenosis recognition algorithm was developed to classify and localize the stenosis automatically from coronary angiographic images. The developed algorithms showed average area under the curve of 0.971 from 5-fold cross validation and 0.956 on three external datasets. With the self-attention mechanism, the recognition of the stenosis became more precise. Our approach can be used as a screening tool to help clinicians find stenosis better and faster in hospital emergency departments. Abstract: Background and objective: Coronary artery disease, which is mostly caused by atherosclerotic narrowing of the coronary artery lumen, is a leading cause of death. Coronary angiography is the standard method to estimate the severity of coronary artery stenosis, but is frequently limited by intra- and inter-observer variations. We propose a deep-learning algorithm that automatically recognizes stenosis in coronary angiographic images. Methods: The proposed method consists of key frame detection, deep learning model training for classification of stenosis on each key frame, and visualization of the possible location of the stenosis. Firstly, we propose an algorithm that automatically extracts key frames essential for diagnosis from 452 right coronary artery angiography movie clips. Our deep learning model is then trained with image-level annotations to classify the areas narrowed by over 50 %. To make the model focus on the salient features, we apply a self-attention mechanism. The stenotic locations are visualized using the activated area of feature maps with gradient-weighted class activation mapping. Results: The automatically detected key frame was very close to the manually selected key frame (average distance (1.70 ± 0.12) frame per clip). The model was trained with key frames on internal datasets, and validated with internal and external datasets. Our training method achieved high frame-wise area-under-the-curve of 0.971, frame-wise accuracy of 0.934, and clip-wise accuracy of 0.965 in the average values of cross-validation evaluations. The external validation results showed high performances with the mean frame-wise area-under-the-curve of (0.925 and 0.956) in the single and ensemble model, respectively. Heat map visualization shows the location for different types of stenosis in both internal and external data sets. With the self-attention mechanism, the stenosis could be precisely localized, which helps to accurately classify the stenosis by type. Conclusions: Our automated classification algorithm could recognize and localize coronary artery stenosis highly accurately. Our approach might provide the basis for a screening and assistant tool for the interpretation of coronary angiography.