Automatic extraction of coronary arteries using deep learning in invasive coronary angiograms

Article type: Research Article

Authors: Meng, Yinghui^a | Du, Zhenglong^a | Zhao, Chen^b | Dong, Minghao^a | Pienta, Drew^c | Tang, Jinshan^{d; *} | Zhou, Weihua^{b; e; f; *}

Affiliations: [a] School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, Henan, China | [b] Department of Applied Computing, Michigan Technological University, Houghton, MI, USA | [c] Department of Mechanical Engineering-Engineering Mechanics, Michigan Technological University, Houghton, MI, USA | [d] Department of Health Administration and Policy, College of Health and Human Services, George Mason University, Fairfax, VA, USA | [e] Center for Biocomputing and Digital Health, Institute of Computing and Cybersystems, Michigan Technological University, Houghton, MI, USA | [f] Health Research Institute, Michigan Technological University, Houghton, MI, USA

Correspondence: [*] Corresponding authors: Weihua Zhou, Department of Applied Computing, Michigan Technological University 1400 Townsend Dr, Houghton, MI 49931, USA. E-mail: whzhou@mtu.edu. Jinshan Tang, Department of Health Administration and Policy, College of Health and Human Services, George Mason University, Fairfax, VA, USA. Email: jtang25@gmu.edu.

Abstract: BACKGROUND: Accurate extraction of coronary arteries from invasive coronary angiography (ICA) images is essential for the diagnosis and risk stratification of coronary artery disease (CAD). OBJECTIVE: In this study, a novel deep learning (DL) method is proposed for automatically extracting coronary arteries from ICA images. METHODS: A convolutional neural network (CNN) was developed with full-scale skip connections and full-scale deep supervisions. The encoder architecture was based on the residual and inception modules to obtain multi-scale features from multiple convolutional layers with different window shapes. Transfer learning was utilized to improve both the initial performance and learning efficiency. A hybrid loss function was employed to further optimize the segmentation model. RESULTS: The model was tested on a data set of 616 ICAs obtained from 210 patients, composed of 437 images for training, 49 images for validation, and 130 images for testing. The segmentation model achieved a Dice score of 0.8942, a sensitivity of 0.8735, a specificity of 0.9954, and a Hausdorff distance of 6.0794 mm; it could predict arteries for a single ICA frame in 0.2114 seconds. CONCLUSIONS: The results showed that our model outperformed the state-of-the-art deep-learning models. Our new method has great potential for clinical use.

Keywords: Coronary artery disease, invasive coronary angiography, image segmentation, deep learning, convolutional neural network

DOI: 10.3233/THC-230278

Journal: Technology and Health Care, vol. 31, no. 6, pp. 2303-2317, 2023