CSWinUNETR: Segmentation of Thin Anatomical Structures in Medical Images

• URL: http://arxiv.org/abs/2606.19824v1
• Date: Thu, 18 Jun 2026 06:01:31 GMT
• Title: CSWinUNETR: Segmentation of Thin Anatomical Structures in Medical Images
• Abstract summary: We propose CSWinUNETR, a general-purpose backbone for 2D and 3D thin-structure segmentation.<n>It employs cross-shaped self-attention to model long-range principal-axis context and incorporates cyclic shifts to enhance information exchange across stripes.<n>It consistently outperforms state-of-the-art methods without task-specific post-processing or topology-aware losses.
• Score: 0.01268579273097071
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Accurate segmentation of thin, tortuous anatomical structures, such as retinal vessels, cerebral vasculature, and facial wrinkles, remains challenging due to low contrast, frequent discontinuities, and severe class imbalance. Although recent convolutional and Transformer-based models have improved performance, they often yield fragmented predictions and fail to recover fine branches. We propose CSWinUNETR, a general-purpose backbone for 2D and 3D thin-structure segmentation. It employs cross-shaped stripe self-attention to model long-range principal-axis context and incorporates cyclic shifts to enhance information exchange across stripes. To better preserve fine-grained details, we further introduce a detail-enhanced multi-scale self-attention module that aggregates contextual features from multi-resolution representations. In addition, we propose sparse-control dynamic snake convolution, which reconstructs reliable dense curvilinear kernels from sparsely predicted control points to better follow tortuous geometry. Extensive experiments on four benchmarks across ophthalmology, neurovascular imaging, and dermatology demonstrate that CSWinUNETR consistently outperforms state-of-the-art methods without task-specific post-processing or topology-aware losses. The code is available at https://github.com/labhai/CSWinUNETR.

Related papers

• MorVess: Morphology-Aware Pulmonary Vessel Segmentation Network [19.918899366472214]
  We introduce MorVess, a morphology-aware segmentation framework that integrates differentiable geometric priors with large-scale foundation model adaptation to achieve fine-grained vascular parsing.<n>A lightweight 2.5D adapter bridges 3D spatial context and 2D SAM representations, while a global-local fusion block aggregates multi-level semantics and geometric cues for high-fidelity topology reconstruction.<n>Across two challenging pulmonary CT benchmarks, MorVess delivers superior Dice, clDice, and HD95 scores, substantially improving small-vessel recovery and global connectivity.
  arXiv  Detail & Related papers  (2026-06-23T06:59:34Z)
• VessShape: Few-shot 2D blood vessel segmentation by leveraging shape priors from synthetic images [0.11458853556386794]
  We introduce VessShape, a methodology for generating large-scale 2D synthetic datasets designed to instill a shape bias in segmentation models.<n>VessShape images contain procedurally generated tubular geometries combined with a wide variety of foreground and background textures.<n>We demonstrate that a model pre-trained on VessShape images achieves strong few-shot segmentation performance on two real-world datasets from different domains.
  arXiv  Detail & Related papers  (2025-10-31T17:19:33Z)
• PASC-Net:Plug-and-play Shape Self-learning Convolutions Network with Hierarchical Topology Constraints for Vessel Segmentation [9.102738065373615]
  We propose a novel vessel segmentation framework called PASC Net.<n>It includes two key modules: a plug-and-play shape self-learning convolutional (SSL) module that optimize convolution kernel design, and a hierarchical topological constraint (HTC) module that ensures vascular connectivity through topological constraints.<n>When integrated into the nnUNet framework, our method outperformed other methods on multiple metrics, achieving state-of-the-art vascular segmentation performance.
  arXiv  Detail & Related papers  (2025-07-05T11:28:35Z)
• Low-Rank Tensor Recovery via Variational Schatten-p Quasi-Norm and Jacobian Regularization [49.85875869048434]
  We propose a CP-based low-rank tensor function parameterized by neural networks for implicit neural representation.<n>To achieve sparser CP decomposition, we introduce a variational Schatten-p quasi-norm to prune redundant rank-1 components.<n>For smoothness, we propose a regularization term based on the spectral norm of the Jacobian and Hutchinson's trace estimator.
  arXiv  Detail & Related papers  (2025-06-27T11:23:10Z)
• A Novel Hybrid Approach for Retinal Vessel Segmentation with Dynamic Long-Range Dependency and Multi-Scale Retinal Edge Fusion Enhancement [0.3611754783778107]
  Existing methods struggle with challenges such as multi-scale vessel variability, complex curvatures, and ambiguous boundaries.<n>We propose a novel hybrid framework that synergistically integrates CNNs and Mamba for high-precision retinal vessel segmentation.<n>Our approach achieves state-of-the-art performance, particularly in maintaining vascular continuity and effectively segmenting vessels in low-contrast regions.
  arXiv  Detail & Related papers  (2025-04-18T08:41:35Z)
• A Novel Convolutional-Free Method for 3D Medical Imaging Segmentation [0.0]
  Convolutional neural networks (CNNs) have dominated the field, achieving significant success in 3D medical image segmentation.<n>Recent transformer-based models, such as TransUNet and nnFormer, have demonstrated promise in addressing these limitations.<n>This paper introduces a novel, fully convolutional-free model based on transformer architecture and self-attention mechanisms.
  arXiv  Detail & Related papers  (2025-02-08T00:52:45Z)
• TBConvL-Net: A Hybrid Deep Learning Architecture for Robust Medical Image Segmentation [6.013821375459473]
  We introduce a novel deep learning architecture for medical image segmentation. Our proposed model shows consistent improvement over the state of the art on ten publicly available datasets.
  arXiv  Detail & Related papers  (2024-09-05T09:14:03Z)
• U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation [48.40120035775506]
  Kolmogorov-Arnold Networks (KANs) reshape the neural network learning via the stack of non-linear learnable activation functions. We investigate, modify and re-design the established U-Net pipeline by integrating the dedicated KAN layers on the tokenized intermediate representation, termed U-KAN. We further delved into the potential of U-KAN as an alternative U-Net noise predictor in diffusion models, demonstrating its applicability in generating task-oriented model architectures.
  arXiv  Detail & Related papers  (2024-06-05T04:13:03Z)
• 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)
• Shape Matters: Detecting Vertebral Fractures Using Differentiable Point-Based Shape Decoding [51.38395069380457]
  Degenerative spinal pathologies are highly prevalent among the elderly population. Timely diagnosis of osteoporotic fractures and other degenerative deformities facilitates proactive measures to mitigate the risk of severe back pain and disability. In this study, we specifically explore the use of shape auto-encoders for vertebrae.
  arXiv  Detail & Related papers  (2023-12-08T18:11:22Z)
• Lesion-aware Dynamic Kernel for Polyp Segmentation [49.63274623103663]
  We propose a lesion-aware dynamic network (LDNet) for polyp segmentation. It is a traditional u-shape encoder-decoder structure incorporated with a dynamic kernel generation and updating scheme. This simple but effective scheme endows our model with powerful segmentation performance and generalization capability.
  arXiv  Detail & Related papers  (2023-01-12T09:53:57Z)
• 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)

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.