Do Not Break the Vessels: Structure-Preserving Mean Flow for Vascular Image Translation

• URL: http://arxiv.org/abs/2606.31095v1
• Date: Tue, 30 Jun 2026 03:31:42 GMT
• Title: Do Not Break the Vessels: Structure-Preserving Mean Flow for Vascular Image Translation
• Abstract summary: Cross-modal translation methods mainly emphasize pixel-level fidelity or visual realism.<n>We propose a Structure-Preserving Mean Flow (SPMF) framework that formulates vascular image translation as a topology-invariant transport process.<n> Experiments on paired NIRII-to-2PF and fundus datasets demonstrate consistent improvements over state-of-the-art methods.
• Score: 10.186762856964831
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reconstructing anatomically faithful vascular structures from clinically accessible imaging modalities is of substantial clinical significance. However, existing cross-modal translation methods mainly emphasize pixel-level fidelity or visual realism and treat structure preservation as a property of the final output rather than an invariant of the generative process. This limitation often leads to structural discontinuities and artifacts, compromising anatomical coherence and clinical reliability. In this work, we propose a Structure-Preserving Mean Flow (SPMF) framework that formulates vascular image translation as a topology-invariant transport process. Based on a structural invariance principle, we derive an orthogonality constraint on the flow velocity field that formally separates appearance transport from topological distortion. We implement this constraint as a time-weighted surrogate objective within a Brownian bridge diffusion model to preserve topology at every diffusion step. Moreover, we propose a Prototype-Guided Structural Refinement (PGSR) module to align degraded inference-time structures with reliable training-time structures. Experiments on paired NIRII-to-2PF and fundus datasets demonstrate consistent improvements over state-of-the-art methods, achieving peak PSNR values of 24.96 dB and 24.83 dB, respectively.

Related papers

• Topological Flow Matching [56.16372813551555]
  Flow matching is a powerful generative modeling framework, valued for its simplicity and strong empirical performance.<n>We introduce topological flow matching, a topology-aware generalization of flow matching.<n>We demonstrate its effectiveness on diverse structured datasets, including brain fMRIs, ocean currents, seismic events, and traffic flows.
  arXiv  Detail & Related papers  (2026-06-14T16:29:33Z)
• PathAR: Structure-First Autoregressive Synthesis of Multimodal Pathology Images [51.428093790826814]
  We propose pathology Autorgressive modeling (PathAR) to factorize structure and appearance for modality-label-conditioned pathology generation.<n>PathAR stabilizes morphology under heterogeneous modality-specific appearances and enables spatially aligned image-mask pair generation.
  arXiv  Detail & Related papers  (2026-06-01T01:43:48Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• scHelix: Asymmetric Dual-Stream Integration via Explicit Gene-Level Disentanglement [84.88065404629079]
  scHelix is a dataset-adaptive framework that fundamentally changes how features are processed.<n> scHelix utilizes a dual-stream sparse diffusion encoder equipped with stop-gradient graph caching.<n> scHelix outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-18T15:55:13Z)
• HistDiT: A Structure-Aware Latent Conditional Diffusion Model for High-Fidelity Virtual Staining in Histopathology [3.5196641463125]
  HistDiT architecture establishes a new benchmark for visual fidelity in virtual histological staining.<n>Our model outperforms existing baselines as demonstrated through rigorous quantitative and qualitative evaluations.
  arXiv  Detail & Related papers  (2026-04-09T14:39:37Z)
• Layout-Guided Controllable Pathology Image Generation with In-Context Diffusion Transformers [57.54843029965778]
  Controllable pathology image synthesis requires reliable regulation of spatial layout, tissue morphology, and semantic detail.<n>We propose In-Context Diffusion Transformer (IC-DiT), a layout-aware generative model that incorporates spatial layouts, textual descriptions, and visual embeddings into a unified diffusion transformer.<n>IC-DiT achieves higher fidelity, stronger spatial controllability, and better diagnostic consistency than existing methods.
  arXiv  Detail & Related papers  (2026-03-11T06:14:11Z)
• VAOT: Vessel-Aware Optimal Transport for Retinal Fundus Enhancement [13.241000354696903]
  Unpaired enhancement pipelines can distort clinically critical vasculature, altering vessel topology and endpoint integrity.<n>We propose Vessel-Aware Optimal Transport (textbfVAOT), a framework that combines an optimal-transport objective with two structure-preserving regularizers.<n>These constraints guide learning in the unpaired setting, reducing noise while preserving vessel structure.
  arXiv  Detail & Related papers  (2025-11-24T04:56:08Z)
• Curvilinear Structure-preserving Unpaired Cross-domain Medical Image Translation [29.978321741632197]
  Unpaired image-to-image translation has emerged as a crucial technique in medical imaging.<n>Existing approaches often distort fine curvilinear structures, such as microvasculature.<n>We propose Curvilinear Structure-preserving Translation (CST), a framework that explicitly preserves fine curvilinear structures during unpaired translation.
  arXiv  Detail & Related papers  (2025-10-22T15:24:32Z)
• 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)
• KLDD: Kalman Filter based Linear Deformable Diffusion Model in Retinal Image Segmentation [51.03868117057726]
  This paper proposes a novel Kalman filter based Linear Deformable Diffusion (KLDD) model for retinal vessel segmentation. Our model employs a diffusion process that iteratively refines the segmentation, leveraging the flexible receptive fields of deformable convolutions. Experiments are evaluated on retinal fundus image datasets (DRIVE, CHASE_DB1) and the 3mm and 6mm of the OCTA-500 dataset.
  arXiv  Detail & Related papers  (2024-09-19T14:21:38Z)

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.