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

arXiv: https://arxiv.org/abs/2202.03671 · HTML: https://mlsanity.com/paper/2202.03671/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 20 references that are in the map.
- First posted on arXiv 8 Feb 2022.

## Builds on (most cited first, 5 of 5)

- [A Recurrent CNN for Automatic Detection and Classification of Coronary Artery Plaque and Stenosis in Coronary CT Angiography](https://mlsanity.com/paper/1804.04360/) (2018)
- [Transformer Network for Significant Stenosis Detection in CCTA of Coronary Arteries](https://mlsanity.com/paper/2107.03035/) (2021)
- [Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions](https://mlsanity.com/paper/1711.00349/) (2017)
- [Coronary Artery Plaque Characterization from CCTA Scans using Deep Learning and Radiomics](https://mlsanity.com/paper/1912.06075/) (2019)
- [Deep Learning Algorithms for Coronary Artery Plaque Characterisation from CCTA Scans](https://mlsanity.com/paper/1912.06417/) (2019)

## Built on by (most cited first, 2 of 2)

- [CAD-RADS scoring of coronary CT angiography with Multi-Axis Vision Transformer: a clinically-inspired deep learning pipeline](https://mlsanity.com/paper/2304.07277/) (2023)
- [Handling Label Uncertainty on the Example of Automatic Detection of Shepherd's Crook RCA in Coronary CT Angiography](https://mlsanity.com/paper/2306.01752/) (2023)

## Abstract (arXiv)

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.