Uncertainty-Guided Conservative Propagation for Structured Inference in Vessel Segmentation

• URL: http://arxiv.org/abs/2605.20543v1
• Date: Tue, 19 May 2026 22:31:13 GMT
• Title: Uncertainty-Guided Conservative Propagation for Structured Inference in Vessel Segmentation
• Abstract summary: Uncertainty-Guided Conservative Propagation (UGCP) is a plug-in module for vessel segmentation.<n> Predictive uncertainty guides reliable regions to support ambiguous regions.<n> structure-aware modulation and source-based stabilization reduce unreliable propagation and excessive drift.
• Score: 10.73944733412427
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate vessel segmentation is essential for medical image analysis, yet remains challenging due to complex vascular patterns and imaging ambiguity. Most deep models rely on single-pass prediction, limiting their ability to refine uncertain or disconnected regions during inference. To address this limitation, we propose Uncertainty-Guided Conservative Propagation (UGCP), a general plug-in module for vessel segmentation. Instead of directly using a one-shot output as the final prediction, UGCP performs a small number of logit-space update steps to refine the segmentation through local predictions interaction. Predictive uncertainty guides reliable regions to support ambiguous regions, while structure-aware modulation and source-based stabilization reduce unreliable propagation and excessive drift. The module is differentiable and can be trained end-to-end with different segmentation networks. We evaluate UGCP on four public vessel segmentation datasets covering 2D and 3D tasks, including retinal vessel, coronary artery, and cerebral vessel segmentation. Experiments with convolutional neural network-based and Transformer-based backbones show consistent improvements in Dice similarity coefficient, centerline Dice, and 95th percentile Hausdorff distance. Further analysis demonstrates that UGCP reduces vessel disconnections and improves structural consistency with limited additional computation. The code will be made available at https://github.com/chenzhao2023/UGC_PR.

Related papers

• Test-time Adaptation of Pelvic Bone Segmentation Models via Dynamic Reliability-Guided [62.10276009853225]
  Reliable pelvic bone segmentation from CT is essential for robot-assisted pelvic trauma surgery.<n>Existing methods show limited effectiveness for PBS.<n>We propose a novel closed-loop dynamic Reliability-Guided framework (ReGA) for PBS.
  arXiv  Detail & Related papers  (2026-08-01T08:13:20Z)
• VCDP: Variation-Conditioned Distributional Proxy Learning for Semi-Supervised Medical Image Segmentation [2.050962785065208]
  Semi-supervised 3D medical image segmentation reduces the need for dense voxel-level annotations by exploiting unlabeled volumes.<n>We propose Variation-Conditioned Distributional Proxy Learning (VCDP), a training-only regularization module for semi-supervised 3D medical image segmentation.
  arXiv  Detail & Related papers  (2026-07-08T13:46:53Z)
• UHR-Net: An Uncertainty-Aware Hypergraph Refinement Network for Medical Image Segmentation [8.273126013629057]
  We propose an Uncertainty-Aware Hypergraph Refinement Network (UHR-Net)<n>We introduce an Uncertainty-Oriented Instance Contrastive (UO-IC) pretraining strategy that couples geometry-aware copy-paste augmentation with hard-negative mining of lesion-like background regions.<n>Second, we design an Uncertainty-Guided Hypergraph Refinement (UGHR) block, which derives an entropy-based uncertainty map from a coarse probability map to guide hypergraph refinement.
  arXiv  Detail & Related papers  (2026-04-30T16:38:51Z)
• Efficient KernelSHAP Explanations for Patch-based 3D Medical Image Segmentation [0.7178174536168246]
  We present an efficient framework for 3D medical image segmentation based on a user-defined region of interest and receptive-field support.<n>We show that caching substantially reduces redundant computation (with computational savings ranging from 15% to 30%) and that faithfulness and interpretability exhibit clear trade-offs.
  arXiv  Detail & Related papers  (2026-04-13T17:43:33Z)
• From GEV to ResLogit: Spatially Correlated Discrete Choice Models for Pedestrian Movement Prediction [1.8262547855491453]
  We formulate the pedestrian next step choice as a spatial discrete choice defined by a grid of speed adjustment and heading change.<n>In dense, high frequency spatial choice sets, learning based residual corrections can capture proximity induced correlation more effectively than analyst specified GEV nesting structures.
  arXiv  Detail & Related papers  (2026-03-01T23:50:33Z)
• VasGuideNet: Vascular Topology-Guided Couinaud Liver Segmentation with Structural Contrastive Loss [15.54612173358869]
  We propose VasGuideNet, the first Couinaud segmentation framework explicitly guided by vascular topology.<n>VasGuideNet achieves Dice scores of 83.68% and 76.65% with RVDs of 1.68 and 7.08.<n>It consistently outperforms representative baselines including UNETR, Swin UNETR, and G-UNETR++.
  arXiv  Detail & Related papers  (2026-02-25T03:50:48Z)
• 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)
• Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images [55.83984261827332]
  In this paper, we propose a novel reliable multi-scale wavelet-enhanced transformer network. We develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module. Our proposed method achieves better segmentation accuracy with a high degree of reliability as compared to other state-of-the-art segmentation approaches.
  arXiv  Detail & Related papers  (2022-12-01T07:32:56Z)
• Receptive Field-based Segmentation for Distributed CNN Inference Acceleration in Collaborative Edge Computing [93.67044879636093]
  We study inference acceleration using distributed convolutional neural networks (CNNs) in collaborative edge computing network. We propose a novel collaborative edge computing using fused-layer parallelization to partition a CNN model into multiple blocks of convolutional layers.
  arXiv  Detail & Related papers  (2022-07-22T18:38:11Z)
• Hepatic vessel segmentation based on 3Dswin-transformer with inductive biased multi-head self-attention [46.46365941681487]
  We propose a robust end-to-end vessel segmentation network called Indu BIased Multi-Head Attention Vessel Net. We introduce the voxel-wise embedding rather than patch-wise embedding to locate precise liver vessel voxels. On the other hand, we propose inductive biased multi-head self-attention which learns inductive biased relative positional embedding from absolute position embedding.
  arXiv  Detail & Related papers  (2021-11-05T10:17:08Z)
• An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation [53.425900196763756]
  We propose a segmentation refinement method based on uncertainty analysis and graph convolutional networks. We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem. We show that our method outperforms the state-of-the-art CRF refinement method by improving the dice score by 1% for the pancreas and 2% for spleen.
  arXiv  Detail & Related papers  (2020-12-06T18:55:07Z)
• 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.