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

• URL: http://arxiv.org/abs/2003.07311v7
• Date: Fri, 15 Jul 2022 10:39:38 GMT
• Title: clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation
• Authors: Suprosanna Shit, Johannes C. Paetzold, Anjany Sekuboyina, Ivan Ezhov, Alexander Unger, Andrey Zhylka, Josien P. W. Pluim, Ulrich Bauer, Bjoern H. Menze
• Abstract summary: 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)
• Score: 57.20783326661043
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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; particularly preserving connectedness: in the case of vascular networks, missing a connected vessel entirely alters the blood-flow dynamics. We introduce a novel similarity measure termed centerlineDice (short clDice), which is calculated on the intersection of the segmentation masks and their (morphological) skeleta. We theoretically prove that clDice guarantees topology preservation up to homotopy equivalence for binary 2D and 3D segmentation. Extending this, we propose a computationally efficient, differentiable loss function (soft-clDice) for training arbitrary neural segmentation networks. We benchmark the soft-clDice loss on five public datasets, including vessels, roads and neurons (2D and 3D). Training on soft-clDice leads to segmentation with more accurate connectivity information, higher graph similarity, and better volumetric scores.

Related papers

• Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures [2.0710692923459804]
  Accurately segmenting thin tubular structures, such as vessels, nerves, roads or concrete cracks, is a crucial task in computer vision. Standard deep learning-based segmentation loss functions, such as Dice or Cross-Entropy, focus on overlap, often at the expense of preserving structural connectivity or topology. We propose a novel Skeleton Recall Loss, which effectively addresses these challenges by circumventing intensive GPU-based calculations with inexpensive CPU operations.
  arXiv  Detail & Related papers  (2024-04-03T18:42:19Z)
• Leveraging Frequency Domain Learning in 3D Vessel Segmentation [50.54833091336862]
  In this study, we leverage Fourier domain learning as a substitute for multi-scale convolutional kernels in 3D hierarchical segmentation models. We show that our novel network achieves remarkable dice performance (84.37% on ASACA500 and 80.32% on ImageCAS) in tubular vessel segmentation tasks.
  arXiv  Detail & Related papers  (2024-01-11T19:07:58Z)
• Cascaded multitask U-Net using topological loss for vessel segmentation and centerline extraction [2.264332709661011]
  We propose to replace the soft-skeleton algorithm by a U-Net which computes the vascular skeleton directly from the segmentation. We build upon this network a cascaded U-Net trained with the clDice loss to embed topological constraints during the segmentation.
  arXiv  Detail & Related papers  (2023-07-21T14:12:28Z)
• Dynamic Snake Convolution based on Topological Geometric Constraints for Tubular Structure Segmentation [12.081234339680456]
  We use this knowledge to guide our DSCNet to simultaneously enhance perception in three stages: feature extraction, feature fusion, and loss constraint. Experiments on 2D and 3D datasets show that our DSCNet provides better accuracy and continuity on the tubular structure segmentation task compared with several methods.
  arXiv  Detail & Related papers  (2023-07-17T10:55:58Z)
• Graph Convolution Based Cross-Network Multi-Scale Feature Fusion for Deep Vessel Segmentation [36.12106059822428]
  Vessels reconstructed using existing methods are often not sufficiently accurate to meet clinical use standards. Our network consists of two cascadedworks performing initial and refined segmentation respectively. Cross-network multi-scale feature fusion is performed between these two U-shaped networks to effectively support high-quality vessel segmentation.
  arXiv  Detail & Related papers  (2023-01-06T05:56:50Z)
• Understanding Imbalanced Semantic Segmentation Through Neural Collapse [81.89121711426951]
  We show that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes. We introduce a regularizer on feature centers to encourage the network to learn features closer to the appealing structure. Our method ranks 1st and sets a new record on the ScanNet200 test leaderboard.
  arXiv  Detail & Related papers  (2023-01-03T13:51:51Z)
• Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation [133.02190910009384]
  We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes. Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
  arXiv  Detail & Related papers  (2022-04-19T10:41:09Z)
• A persistent homology-based topological loss for CNN-based multi-class segmentation of CMR [5.898114915426535]
  Multi-class segmentation of cardiac magnetic resonance (CMR) images seeks a separation of data into anatomical components with known structure and configuration. Most popular CNN-based methods are optimised using pixel wise loss functions, ignorant of the spatially extended features that characterise anatomy. We extend these approaches to the task of multi-class segmentation by building an enriched topological description of all class labels and class label pairs.
  arXiv  Detail & Related papers  (2021-07-27T09:21:38Z)
• TSGCNet: Discriminative Geometric Feature Learning with Two-Stream GraphConvolutional Network for 3D Dental Model Segmentation [141.2690520327948]
  We propose a two-stream graph convolutional network (TSGCNet) to learn multi-view information from different geometric attributes. We evaluate our proposed TSGCNet on a real-patient dataset of dental models acquired by 3D intraoral scanners.
  arXiv  Detail & Related papers  (2020-12-26T08:02:56Z)
• Adaptive feature recombination and recalibration for semantic segmentation with Fully Convolutional Networks [57.64866581615309]
  We propose recombination of features and a spatially adaptive recalibration block that is adapted for semantic segmentation with Fully Convolutional Networks. Results indicate that Recombination and Recalibration improve the results of a competitive baseline, and generalize across three different problems.
  arXiv  Detail & Related papers  (2020-06-19T15:45:03Z)

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.