Jong Hak Moon1, Da Young Lee2, Won Chul Cha3, Myung Jin Chung4, Kyu-Sung Lee5, Baek Hwan Cho6, Jin Ho Choi7. 1. Department of Medical Device Management and Research, SAIHST, Sungkyunkwan University, Seoul 06351, South Korea. Electronic address: jhak.moon@kaist.ac.kr. 2. Department of Digital Health, SAIHST, Sungkyunkwan University, Seoul 06351, South Korea. Electronic address: rebe.lee17@gmail.com. 3. Department of Emergency Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul 06351, South Korea. Electronic address: wc.cha@samsung.com. 4. Medical AI Research Center, Samsung Medical Center, Seoul 06351, South Korea; Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul 06351, South Korea. Electronic address: mj1.chung@samsung.com. 5. Department of Medical Device Management and Research, SAIHST, Sungkyunkwan University, Seoul 06351, South Korea; Department of Urology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul 06351, South Korea. Electronic address: ks63.lee@samsung.com. 6. Department of Medical Device Management and Research, SAIHST, Sungkyunkwan University, Seoul 06351, South Korea; Medical AI Research Center, Samsung Medical Center, Seoul 06351, South Korea. Electronic address: baekhwan.cho@samsung.com. 7. Department of Medical Device Management and Research, SAIHST, Sungkyunkwan University, Seoul 06351, South Korea; Department of Emergency Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul 06351, South Korea. Electronic address: jhchoimd@gmail.com.
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.
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.