Automatic coronary artery segmentation of CCTA images using UNet with a local contextual transformer

Frontiers in Physiology

Physiology

Stephen E. Greenwald¹  Lisheng Xu²  Yu Sun³  Benqiang Yang⁴  Xiaofan Yang⁵  Qianjin Wang⁵  Lu Wang⁵ 

[1] Blizard Institute, Barts and the London School of Medicine and Dentistry, Queen Mary University of London, London, United Kingdom;College of Medicine and Biological and Information Engineering, Northeastern University, Shenyang, China;College of Medicine and Biological and Information Engineering, Northeastern University, Shenyang, China;Department of Radiology, General Hospital of Northern Theater Command, Shenyang, China;Key Laboratory of Cardiovascular Imaging and Research of Liaoning Province, Shenyang, China;Department of Radiology, General Hospital of Northern Theater Command, Shenyang, China;Key Laboratory of Cardiovascular Imaging and Research of Liaoning Province, Shenyang, China;School of Computer Science and Engineering, Northeastern University, Shenyang, China;

关键词: coronary artery segmentation;    3D-Unet;    local contextual transformer;    dense residual connection;    convolutional neural network;   

DOI  :  10.3389/fphys.2023.1138257

 received in 2023-01-05, accepted in 2023-08-01,  发布年份 2023

来源: Frontiers

【 摘 要 】

Coronary artery segmentation is an essential procedure in the computer-aided diagnosis of coronary artery disease. It aims to identify and segment the regions of interest in the coronary circulation for further processing and diagnosis. Currently, automatic segmentation of coronary arteries is often unreliable because of their small size and poor distribution of contrast medium, as well as the problems that lead to over-segmentation or omission. To improve the performance of convolutional-neural-network (CNN) based coronary artery segmentation, we propose a novel automatic method, DR-LCT-UNet, with two innovative components: the Dense Residual (DR) module and the Local Contextual Transformer (LCT) module. The DR module aims to preserve unobtrusive features through dense residual connections, while the LCT module is an improved Transformer that focuses on local contextual information, so that coronary artery-related information can be better exploited. The LCT and DR modules are effectively integrated into the skip connections and encoder-decoder of the 3D segmentation network, respectively. Experiments on our CorArtTS2020 dataset show that the dice similarity coefficient (DSC), Recall, and Precision of the proposed method reached 85.8%, 86.3% and 85.8%, respectively, outperforming 3D-UNet (taken as the reference among the 6 other chosen comparison methods), by 2.1%, 1.9%, and 2.1%.

【 授权许可】

Unknown   
Copyright © 2023 Wang, Xu, Wang, Yang, Sun, Yang and Greenwald.