Centerline Boundary Dice Loss for Vascular Segmentation
- URL: http://arxiv.org/abs/2407.01517v1
- Date: Mon, 1 Jul 2024 17:58:44 GMT
- Title: Centerline Boundary Dice Loss for Vascular Segmentation
- Authors: Pengcheng Shi, Jiesi Hu, Yanwu Yang, Zilve Gao, Wei Liu, Ting Ma,
- Abstract summary: 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.
We introduce the centerline boundary Dice (cbDice) loss function, which harmonizes topological integrity and geometric nuances.
- Score: 6.988368827452061
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: 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.
Related papers
- ViG3D-UNet: Volumetric Vascular Connectivity-Aware Segmentation via 3D Vision Graph Representation [13.363621889050426]
A 3D vision graph neural network framework, named ViG3D-UNet, was introduced to facilitate continuous vascular segmentation.
The ViG3D-UNet method integrates 3D graph representation and aggregation within a U-shaped architecture to facilitate continuous vascular segmentation.
arXiv Detail & Related papers (2025-04-18T10:06:45Z) - A topology-preserving three-stage framework for fully-connected coronary artery extraction [39.47027832777158]
Coronary artery extraction is a crucial prerequisite for computer-aided diagnosis of coronary artery disease.
We propose a topology-preserving three-stage framework for fully-connected coronary artery extraction.
This framework includes vessel segmentation, centerline reconnection, and missing vessel reconstruction.
arXiv Detail & Related papers (2025-04-02T11:04:44Z) - SPOCKMIP: Segmentation of Vessels in MRAs with Enhanced Continuity using Maximum Intensity Projection as Loss [0.5224038339798621]
This study focuses on improving the segmentation quality using the Maximum Intensity Projection(MIP) as an additional loss criterion.
Two methods are proposed with the incorporation of MIPs of label segmentation on the single(z-axis) and multiple perceivable axes of the 3D volume.
The proposed MIP-based methods produce segmentations with improved vessel continuity, which is evident in visual examinations of ROIs.
arXiv Detail & Related papers (2024-07-11T16:39:24Z) - Dual-scale Enhanced and Cross-generative Consistency Learning for Semi-supervised Medical Image Segmentation [49.57907601086494]
Medical image segmentation plays a crucial role in computer-aided diagnosis.
We propose a novel Dual-scale Enhanced and Cross-generative consistency learning framework for semi-supervised medical image (DEC-Seg)
arXiv Detail & Related papers (2023-12-26T12:56:31Z) - Adaptive Semi-Supervised Segmentation of Brain Vessels with Ambiguous
Labels [63.415444378608214]
Our approach incorporates innovative techniques including progressive semi-supervised learning, adaptative training strategy, and boundary enhancement.
Experimental results on 3DRA datasets demonstrate the superiority of our method in terms of mesh-based segmentation metrics.
arXiv Detail & Related papers (2023-08-07T14:16:52Z) - Morphology Edge Attention Network and Optimal Geometric Matching
Connection model for vascular segmentation [3.6368619769561668]
We propose a novel Morphology Edge Attention Network (MEA-Net) for the segmentation of vessel-like structures.
We also present an Optimal Geometric Matching Connection (OGMC) model to connect the broken vessel segments.
Our method achieves superior or competitive results compared to state-of-the-art methods on four datasets of 3D vascular segmentation tasks.
arXiv Detail & Related papers (2023-06-02T01:52:35Z) - Segmentation and Vascular Vectorization for Coronary Artery by
Geometry-based Cascaded Neural Network [26.88627331841325]
We propose a geometry-based cascaded segmentation method for the coronary artery.
The generated meshes of the coronary artery are continuous and accurate for twisted and sophisticated coronary artery structures.
Our method generates an accurate, intact and smooth coronary artery, devoid of any fragmentations of segmented vessels.
arXiv Detail & Related papers (2023-05-07T07:26:41Z) - External Attention Assisted Multi-Phase Splenic Vascular Injury
Segmentation with Limited Data [72.99534552950138]
The spleen is one of the most commonly injured solid organs in blunt abdominal trauma.
accurate segmentation of splenic vascular injury is challenging for the following reasons.
arXiv Detail & Related papers (2022-01-04T02:35:56Z) - Rethinking the Extraction and Interaction of Multi-Scale Features for
Vessel Segmentation [53.187152856583396]
We propose a novel deep learning model called PC-Net to segment retinal vessels and major arteries in 2D fundus image and 3D computed tomography angiography (CTA) scans.
In PC-Net, the pyramid squeeze-and-excitation (PSE) module introduces spatial information to each convolutional block, boosting its ability to extract more effective multi-scale features.
arXiv Detail & Related papers (2020-10-09T08:22:54Z) - DONet: Dual Objective Networks for Skin Lesion Segmentation [77.9806410198298]
We propose a simple yet effective framework, named Dual Objective Networks (DONet), to improve the skin lesion segmentation.
Our DONet adopts two symmetric decoders to produce different predictions for approaching different objectives.
To address the challenge of large variety of lesion scales and shapes in dermoscopic images, we additionally propose a recurrent context encoding module (RCEM)
arXiv Detail & Related papers (2020-08-19T06:02:46Z) - clDice -- A Novel Topology-Preserving Loss Function for Tubular
Structure Segmentation [57.20783326661043]
We introduce a novel similarity measure termed centerlineDice (short clDice)
We theoretically prove that clDice guarantees topology preservation up to homotopy equivalence for binary 2D and 3D segmentation.
We benchmark the soft-clDice loss on five public datasets, including vessels, roads and neurons (2D and 3D)
arXiv Detail & Related papers (2020-03-16T16:27:49Z) - AttentionAnatomy: A unified framework for whole-body organs at risk
segmentation using multiple partially annotated datasets [30.23917416966188]
Organs-at-risk (OAR) delineation in computed tomography (CT) is an important step in Radiation Therapy (RT) planning.
Our proposed end-to-end convolutional neural network model, called textbfAttentionAnatomy, can be jointly trained with three partially annotated datasets.
Experimental results of our proposed framework presented significant improvements in both Sorensen-Dice coefficient (DSC) and 95% Hausdorff distance.
arXiv Detail & Related papers (2020-01-13T18:31:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.