Zhang N, Yang G, Zhang W, et al. - The present study was performed to construct a fully automatic multiview shape constraint framework for comprehensive coronary artery calcium scores (CACS) quantification via deep learning on nonenhanced cardiac CT images. A multi-task deep learning framework was proposed to diagnose and evaluate coronary artery calcification from CT images collected between October 2018 and March 2019 in this retrospective single-centre study. Researchers examined a sum of 232 non-contrast cardiac-gated CT scans (80% for model training and 20% for testing). This study’s findings revealed that for the CACS, the proposed framework can achieve reliable and comprehensive quantification, including the calcified extent and distribution indicators at both total and vessel-specific levels.