CAD-RADS Scoring using Deep Learning and Task-Specific Centerline Labeling

Denzinger F, Wels M, Taubmann O, Gülsün MA, Schöbinger M, Andre F, Buss SJ, Goerich J, Sühling M, Maier A, Breininger K (2022)

Publication Type: Conference contribution, Conference Contribution

Publication year: 2022

Pages Range: 315-324

Conference Proceedings Title: PMLR

Event location: Zürich CH



With coronary artery disease (CAD) persisting to be one of the leading causes of death worldwide, interest in supporting physicians with algorithms to speed up and improve diagnosis is high. In clinical practice, the severeness of CAD is often assessed with a coronary CT angiography (CCTA) scan and manually graded with the CAD-Reporting and Data System (CAD-RADS) score. The clinical questions this score assesses are whether patients have CAD or not (rule-out) and whether they have severe CAD or not (hold-out). In this work, we reach new state-of-the-art performance for automatic CAD-RADS scoring. We propose using severity-based label encoding, test time augmentation (TTA) and model ensembling for a task-specific deep learning architecture. Furthermore, we introduce a novel task-and model-specific, heuristic coronary segment labeling, which subdivides coronary trees into consistent parts across patients. It is fast, robust, and easy to implement. We were able to raise the previously reported area under the receiver operating characteristic curve (AUC) from 0.914 to 0.942 in the rule-out and from 0.921 to 0.950 in the hold-out task respectively.

Authors with CRIS profile

Involved external institutions

How to cite


Denzinger, F., Wels, M., Taubmann, O., Gülsün, M.A., Schöbinger, M., Andre, F.,... Breininger, K. (2022). CAD-RADS Scoring using Deep Learning and Task-Specific Centerline Labeling. In PMLR (Eds.), PMLR (pp. 315-324). Zürich, CH.


Denzinger, Felix, et al. "CAD-RADS Scoring using Deep Learning and Task-Specific Centerline Labeling." Proceedings of the International Conference on Medical Imaging with Deep Learning, Zürich Ed. PMLR, 2022. 315-324.

BibTeX: Download