A 3D deep learning classifier and its explainability when assessing coronary artery disease

Corresponding author: Dr Joseph Jacob UCL Centre for Medical Image Computing 1st Floor, 90 High Holborn, London WC1V6LJ j.jacob@ucl.ac.uk Abstract Early detection and diagnosis of coronary artery disease (CAD) could save lives and reduce healthcare costs. In this study, we propose a 3D Resnet-50 deep learning model to directly classify normal subjects and CAD patients on computed tomography coronary angiography images. Our proposed method outperforms a 2D Resnet-50 model by 23.65%. Explainability is also provided by using a Grad-GAM. Furthermore, we link the 3D CAD classification to a 2D two-class semantic segmentation for improved explainability and accurate abnormality localisation. Introduction Coronary artery disease (CAD) is a common cause of death [1] in developed (i.e., UK, USA) and developing countries (i.e., India, Philippines). Early detection and diagnosis of CAD could save lives and costs [2]. Currently, computed tomography coronary angiography (CTCA) plays a central role in diagnosing or excluding CAD in patients with chest pain [3, 4].