Topology-oriented foreground focusing network for semi-supervised coronary artery segmentation.

 0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: Yang Chen, Jean-Louis Coatrieux, Qianjin Feng, Huazhong Shu, Xiangxin Wang, Zhan Wu, Yujia Zhou

Ngôn ngữ: eng

Ký hiệu phân loại: 636.0885 Animal husbandry

Thông tin xuất bản: Netherlands : Medical image analysis , 2025

Mô tả vật lý:

Bộ sưu tập: NCBI

ID: 220623

Automatic coronary artery (CA) segmentation on coronary-computed tomography angiography (CCTA) images is critical for coronary-related disease diagnosis and pre-operative planning. However, such segmentation remains a challenging task due to the difficulty in maintaining the topological consistency of CA, interference from irrelevant tubular structures, and insufficient labeled data. In this study, we propose a novel semi-supervised topology-oriented foreground focusing network (TOFF-Net) to comprehensively address such challenges. Specifically, we first propose an explicit vascular connectivity preservation (VCP) loss to capture the topological information and effectively strengthen vascular connectivity. Then, we propose an irrelevant vessels removal (IVR) module, which aims to integrate local CA details and global CA distribution, thereby eliminating interference of irrelevant vessels. Moreover, we propose a foreground label migration and focusing (FLMF) module with Pioneer-Imitator learning as a semi-supervised strategy to exploit the unlabeled data. The FLMF can effectively guide the attention of TOFF-Net to the foreground. Extensive results on our in-house dataset and two public datasets demonstrate that our TOFF-Net achieves state-of-the-art CA segmentation performance with high topological consistency and few false-positive irrelevant tubular structures. The results also reveal that our TOFF-Net presents considerable potential for parsing other types of vessels.
Tạo bộ sưu tập với mã QR

THƯ VIỆN - TRƯỜNG ĐẠI HỌC CÔNG NGHỆ TP.HCM

ĐT: (028) 36225755 | Email: tt.thuvien@hutech.edu.vn

Copyright @2024 THƯ VIỆN HUTECH