Recursive Centerline- and Direction-Aware Joint Learning Network with Ensemble Strategy for Vessel Segmentation in X-ray Angiography Images. (June 2022)

• Record Type: Journal Article
• Authors: Han, Tao; Ai, Danni; Wang, Yining; Bian, Yonglin; An, Ruirui; Fan, Jingfan; Song, Hong; Xie, Hongzhi; Yang, Jian
• Is Part Of: Computer methods and programs in biomedicine. Volume 220(2022)
• Publication Date: 2022-06
• Subjects: vessel segmentation -- X-ray angiography -- multi-task learning -- recursive learning -- ensemble; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.106787
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: A new multi-task learning network joining vessel direction and CDTM auxiliary tasks is presented for vessel segmentation. A recursive learning framework is introduced to progressively boost vessel segmentation performance without extra network parameters. A complementary-task ensemble strategy is designed by fusing the outputs of the three tasks with training only one model. The method is evaluated on the XRA images of the coronary artery and aorta. Compared with the six other state-of-the-art methods, the method achieves the most complete and accurate vessel segmentation results. Abstract: Background and objective: Automatic vessel segmentation from X-ray angiography images is an important research topic for the diagnosis and treatment of cardiovascular disease. The main challenge is how to extract continuous and completed vessel structures from XRA images with poor quality and high complexity. Most existing methods predominantly focus on pixel-wise segmentation and overlook the geometric features, resulting in breaking and absence in segmentation results. To improve the completeness and accuracy of vessel segmentation, we propose a recursive joint learning network embedded with geometric features. Methods: The network joins the centerline- and direction-aware auxiliary tasks with the primary task of segmentation, which guides the network to explore the geometric features of vessel connectivity. Moreover, the recursive learning strategy is designed by passing the previous segmentation result into the same network iteratively to improve segmentation. To further enhance connectivity, we present a complementary-task ensemble strategy by fusing the outputs of the three tasks for the final segmentation result with majority voting. Results: To validate the effectiveness of our method, we conduct qualitative and quantitative experiments on the XRA images of the coronary artery and aorta including aortic arch, thoracic aorta, and abdominal aorta. Our method achieves F1 scores of 85.61±3.48% for the coronary artery, 89.02±2.89% for the aortic arch, 88.22±3.33% for the thoracic aorta, and 83.12±4.61% for the abdominal aorta. Conclusions: Compared with six state-of-the-art methods, our method shows the most complete and accurate vessel segmentation results.