paper-with-me

홈 › Papers

Centerline Boundary Dice Loss for Vascular Segmentation

2024-07-01 · Pengcheng Shi, Jiesi Hu, Yanwu Yang, Zilve Gao, Wei Liu, Ting Ma

Vascular segmentation in medical imaging plays a crucial role in analysing morphological and functional assessments. Traditional methods, like the centerline Dice (clDice) loss, ensure topology preservation but falter in capturing geometric details, especially under translation and deformation. The combination of clDice with traditional Dice loss can lead to diameter imbalance, favoring larger vessels. Addressing these challenges, we introduce the centerline boundary Dice (cbDice) loss function, which harmonizes topological integrity and geometric nuances, ensuring consistent segmentation across various vessel sizes. cbDice enriches the clDice approach by including boundary-aware aspects, thereby improving geometric detail recognition. It matches the performance of the boundary difference over union (B-DoU) loss through a mask-distance-based approach, enhancing traslation sensitivity. Crucially, cbDice incorporates radius information from vascular skeletons, enabling uniform adaptation to vascular diameter changes and maintaining balance in branch growth and fracture impacts. Furthermore, we conducted a theoretical analysis of clDice variants (cl-X-Dice). We validated cbDice's efficacy on three diverse vascular segmentation datasets, encompassing both 2D and 3D, and binary and multi-class segmentation. Particularly, the method integrated with cbDice demonstrated outstanding performance on the MICCAI 2023 TopCoW Challenge dataset. Our code is made publicly available at: https://github.com/PengchengShi1220/cbDice.

📄 PDF Abstract BibTeX arXiv:2407.01517

Code (1)

pengchengshi1220/cbdice 공식 구현 pytorch

Tasks

Segmentation

Methods 이 논문이 사용한 방법론

Dice Loss \begin{equation} DiceLoss\left( y, \overline{p} \right) = 1 - \dfrac{\left( 2y\overline{p} + 1 \right)} {\left( y+\overline{p } + 1 \right)} \end{equation}

Similar Papers 제목 키워드 기반

Cascaded multitask U-Net using topological loss for vessel segmentation and centerline extraction

2023-07-21 · Pierre Rougé, Nicolas Passat, Odyssée Merveille

Vessel segmentation and centerline extraction are two crucial preliminary tasks for many computer-aided diagnosis tools dealing with vascular diseases. Recently, deep-learning based methods have been widely applied to th…

Segmentation

clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation

2020-03-16 · Suprosanna Shit, Johannes C. Paetzold, Anjany Sekuboyina, Ivan Ezhov 외

Accurate segmentation of tubular, network-like structures, such as vessels, neurons, or roads, is relevant to many fields of research. For such structures, the topology is their most important characteristic; particularl…

Graph SimilaritySegmentation

clDice - A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation

2021-06-19 · CVPR 2021 1 · Suprosanna Shit, Johannes C. Paetzold, Anjany Sekuboyina, Ivan Ezhov 외

Accurate segmentation of tubular, network-like structures, such as vessels, neurons, or roads, is relevant to many fields of research. For such structures, the topology is their most important characteristic; particu…

Graph SimilaritySegmentation

An automated framework for brain vessel centerline extraction from CTA images

2024-01-13 · Sijie Liu, Ruisheng Su, Jianghang Su, Jingmin Xin 외

Accurate automated extraction of brain vessel centerlines from CTA images plays an important role in diagnosis and therapy of cerebrovascular diseases, such as stroke. However, this task remains challenging due to the co…

Segmentation

A Physics-Informed Loss Function for Boundary-Consistent and Robust Artery Segmentation in DSA Sequences

2025-11-25 · Muhammad Irfan, Nasir Rahim, Khalid Mahmood Malik arxiv

Accurate extraction and segmentation of the cerebral arteries from digital subtraction angiography (DSA) sequences is essential for developing reliable clinical management models of complex cerebrovascular diseases. Conv…