Efficient Extraction of Coronary Artery Vessels from Computed Tomography Angiography Images Using ResUnet and Vesselness

Abstract

Accurate and efficient segmentation of coronary arteries from CTA images is crucial for diagnosing and treating cardiovascular diseases. This study proposes a structured approach that combines vesselness enhancement, heart region of interest (ROI) extraction, and the ResUNet deep learning method to accurately and efficiently extract coronary artery vessels. Vesselness enhancement and heart ROI extraction significantly improve the accuracy and efficiency of the segmentation process, while ResUNet enables the model to capture both local and global features. The proposed method outperformed other state-of-the-art methods, achieving a Dice similarity coefficient (DSC) of 0.867, a Recall of 0.881, and a Precision of 0.892. The exceptional results for segmenting coronary arteries from CTA images demonstrate the potential of this method to significantly contribute to accurate diagnosis and effective treatment of cardiovascular diseases.

Keywords: CTA images; U-net; cardiovascular disease; coronary artery segmentation; deep learning.

Figure 1

Mainstages of the proposed method.

Figure 2

Coronary arteries vessels’ appearance: original (left) vs. enhanced (right).

Figure 3

The proposed U-net-based model.

Figure 4

Residual block (left), dense block (middle), and ResDense Block (right).

Figure 5

Training patches (heart region).

Figure 6

ResUnet model training curve for heart segmentation step.

Figure 7

Example of heart segmentation from target CTA.

Figure 8

Proposed model training curves for coronary arteries segmentation: without vesselness (top); with vesselness (bottom).

Figure 9

Coronary arteries masks: ground truth (left) without vesselness (middle) and with vesselness (right): the blue circles show the help of vesselness to improve the segmentation process. The green circle highlights the improving in the segmentation even better than the ground truth.