Multi-Resolution 3D Convolutional Neural Networks for Automatic Coronary Centerline Extraction in Cardiac CT Angiography Scans

TL;DR

This paper introduces AuCoTrack, a deep learning method using multi-scale 3D CNNs to automatically extract coronary artery centerlines from cardiac CT scans, achieving high accuracy and outperforming existing techniques.

Contribution

The paper presents a novel dual pathway 3D CNN architecture for automatic coronary artery tracking, including bifurcation detection and endpoint identification, trained on proprietary data and benchmarked on public datasets.

Findings

Achieved 87.1% sensitivity on proprietary data

Obtained 93.6% overlap on benchmark datasets

Outperformed state-of-the-art methods with 95% vessel detection rate

Abstract

We propose a deep learning-based automatic coronary artery tree centerline tracker (AuCoTrack) extending the vessel tracker by Wolterink (arXiv:1810.03143). A dual pathway Convolutional Neural Network (CNN) operating on multi-scale 3D inputs predicts the direction of the coronary arteries as well as the presence of a bifurcation. A similar multi-scale dual pathway 3D CNN is trained to identify coronary artery endpoints for terminating the tracking process. Two or more continuation directions are derived based on the bifurcation detection. The iterative tracker detects the entire left and right coronary artery trees based on only two ostium landmarks derived from a model-based segmentation of the heart. The 3D CNNs were trained on a proprietary dataset consisting of 43 CCTA scans. An average sensitivity of 87.1% and clinically relevant overlap of 89.1% was obtained relative to a refined manual segmentation. In addition, the MICCAI 2008 Coronary Artery Tracking Challenge (CAT08) training and test datasets were used to benchmark the algorithm and to assess its generalization. An average overlap of 93.6% and a clinically relevant overlap of 96.4% were obtained. The proposed method achieved better overlap scores than the current state-of-the-art automatic centerline extraction techniques on the CAT08 dataset with a vessel detection rate of 95%.