Automated Coronary Artery Atherosclerosis Detection and Weakly Supervised Localization on Coronary CT Angiography with a Deep 3-Dimensional Convolutional Neural Network

•Automated screening of CCTA examinations with a deep-learning-based approach.•Detection of presence or absence of atherosclerotic plaque of the coronary arteries.•3-dimensional convolutional neural network.•Weakly localization of pathological changes, plaques with/without calcifications.•Scratch training strategy due to lack of pre-trained models for 3D-CNN.•High negative predictive value•Potential usage for assisting physicians in excluding coronary atherosclerosis