3D-CurvSegFlow is presented, a flow matching-based model for 3D curvilinear structure segmentation that outperforms general-purpose and vessel-specific approaches, with strong preservation of thin branches and vascular continuity.
Abstract
Segmentation of curvilinear anatomical structures in 3D medical images remains challenging due to complex topology, severe class imbalance, weak contrast, and large variations in structure morphology. While deep learning approaches for 3D curvilinear segmentation have been proposed, they are often tailored to specific anatomies or modalities, limiting generalization across clinical settings and leaving room for improvement. Recent generative models have shown the benefits of iterative prediction for structured segmentation tasks, yet diffusion-based methods suffer from computationally expensive sampling, hindering their use on high-resolution 3D volumes. We present 3D-CurvSegFlow, a flow matching-based model for 3D curvilinear structure segmentation. The model learns a continuous transformation from a simple source distribution to the target vascular representation, enabling progressive refinement of complex curvilinear geometries with efficient inference. We evaluate our method on Three public challenging datasets covering distinct anatomies and modalities: portal vein, cerebral vessel, and coronary arteries. Using a common architecture and training strategy across all tasks, our method outperforms general-purpose and vessel-specific approaches, with strong preservation of thin branches and vascular continuity. This work not only advances the state-of-the-art in 3D curvilinear segmentation but also opens new avenues for efficient, generalizable, and clinically applicable methods in medical image analysis.
This work proposes a conditional Flow Matching (CFM) based framework for efficient 3D medical image segmentation that maintains competitive segmentation accuracy while achieving an inference time of only 1.14 seconds per volume, offering a clear efficiency advantage over existing generative segmentation methods.
Y. Yilihamu, Jian Xue, Chuang Jia et al.· International Conference on...· 0 citations
A modality-routed 3D cardiac segmentation pipeline that combines TotalSegmentator-initialized nnU-Netv2 models with site-characterized, label-preserving appearance augmentation is proposed, suggesting that site-motivated appearance augmentation is a practical strategy for improving cross-site robustness in limited-data...
Tanishqua H Mudaliar, Justin D. Li, Daniel Lin et al.· 0 citations
Interactive segmentation of 3D medical images supports quantitative analysis of anatomical structures and disease while allowing users to specify and refine their targets. Despite substantial progress by nnInteractive and VISTA3D, reliable segmentation across diverse clinical targets remains challenging, particularly f...
Ping-Qiu Gong, Shi-Yuan Su, Fan-Dong Zhang et al.· arXiv.org· 0 citations
This paper proposes ReG-SAM, a SAM-based framework tailored to 2D vessel segmentation that leverages reference graph set for enhancing vascular representations and introduces two modality-aware representations derived from the reference masks.
Donghang Lyu, Zi-Chen Zhang, O. Dzyubachyk et al.· 0 citations
Inspired by traditional probabilistic atlases, PCMap is an average anatomical map generated from all initial segmentations, intended to enforce structural consistency, which increased shape regularity and reduced interslice discontinuities but did not consistently improve voxel-wise accuracy.
Hirohisa Oda, Toshiaki Akita· Radiological Physics and Tec...· 0 citations
This work proposes a novel unsupervised domain adaptation (UDA) framework based on redundancy-reducing feature alignment, enabling 3D CBCT segmentation with no target-domain annotations or inference-time adaptation, and demonstrates that this approach consistently outperforms existing pretrained foundation model and UD...
Gauthier Miralles, Loic Le Folgoc, Vincent Jugnon et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.