Saved in:
Bibliographic Details
Main Authors: Wu, Chun-Hung, Chen, Shih-Hong, Hu, Chih-Yao, Wu, Hsin-Yu, Chen, Kai-Hsin, Chen, Yu-You, Su, Chih-Hai, Lee, Chih-Kuo, Liu, Yu-Lun
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.01591
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913755367997440
author Wu, Chun-Hung
Chen, Shih-Hong
Hu, Chih-Yao
Wu, Hsin-Yu
Chen, Kai-Hsin
Chen, Yu-You
Su, Chih-Hai
Lee, Chih-Kuo
Liu, Yu-Lun
author_facet Wu, Chun-Hung
Chen, Shih-Hong
Hu, Chih-Yao
Wu, Hsin-Yu
Chen, Kai-Hsin
Chen, Yu-You
Su, Chih-Hai
Lee, Chih-Kuo
Liu, Yu-Lun
contents This paper presents Deformable Neural Vessel Representations (DeNVeR), an unsupervised approach for vessel segmentation in X-ray angiography videos without annotated ground truth. DeNVeR utilizes optical flow and layer separation techniques, enhancing segmentation accuracy and adaptability through test-time training. Key contributions include a novel layer separation bootstrapping technique, a parallel vessel motion loss, and the integration of Eulerian motion fields for modeling complex vessel dynamics. A significant component of this research is the introduction of the XACV dataset, the first X-ray angiography coronary video dataset with high-quality, manually labeled segmentation ground truth. Extensive evaluations on both XACV and CADICA datasets demonstrate that DeNVeR outperforms current state-of-the-art methods in vessel segmentation accuracy and generalization capability while maintaining temporal coherency.
format Preprint
id arxiv_https___arxiv_org_abs_2406_01591
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation
Wu, Chun-Hung
Chen, Shih-Hong
Hu, Chih-Yao
Wu, Hsin-Yu
Chen, Kai-Hsin
Chen, Yu-You
Su, Chih-Hai
Lee, Chih-Kuo
Liu, Yu-Lun
Computer Vision and Pattern Recognition
This paper presents Deformable Neural Vessel Representations (DeNVeR), an unsupervised approach for vessel segmentation in X-ray angiography videos without annotated ground truth. DeNVeR utilizes optical flow and layer separation techniques, enhancing segmentation accuracy and adaptability through test-time training. Key contributions include a novel layer separation bootstrapping technique, a parallel vessel motion loss, and the integration of Eulerian motion fields for modeling complex vessel dynamics. A significant component of this research is the introduction of the XACV dataset, the first X-ray angiography coronary video dataset with high-quality, manually labeled segmentation ground truth. Extensive evaluations on both XACV and CADICA datasets demonstrate that DeNVeR outperforms current state-of-the-art methods in vessel segmentation accuracy and generalization capability while maintaining temporal coherency.
title DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.01591