---
title: "Flow Matching 结合三维医学图像曲线结构分割新方法"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.19965v1"
permalink: "https://feed.astralor.com/items/itm_3088f2bd42dc7b7a045b1f4d"
published: "2026-08-20T12:35:27.000Z"
score: 75
channel: "tech"
tags: ["3D-CurvSegFlow","Flow Matching","医学图像分割","扩散模型"]
---

# Flow Matching 结合三维医学图像曲线结构分割新方法

## AI 点评

> 如果依赖扩散模型做三维分割的团队被算力劝退，这篇值得读：flow matching 用更少的采样步骤达到了接近甚至更好的结构保持效果。对医学影像算法工程师来说，3D-CurvSegFlow 提供了一个即插即用的通用框架，不必再为每个器官单独调模型。

## 速览

三维医学图像中的曲线解剖结构分割面临复杂拓扑、类别不平衡、对比度弱和形态差异大等挑战。现有深度学习方法多针对特定解剖部位或模态，泛化能力有限；扩散模型虽能迭代细化，但采样成本高昂。本文提出 3D-CurvSegFlow，基于 flow matching 学习从简单分布到目标血管表示的连续变换，实现高效推理和渐进式细化。在门静脉、脑血管和冠状动脉三个公开数据集上，使用统一架构和训练策略，方法优于通用和血管专用模型，尤其擅长保留细薄分支和血管连续性，为高效、通用且临床适用的医学图像分析开辟了新路径。

## 关键点

- 提出 3D-CurvSegFlow，首次将 flow matching 应用于三维曲线结构分割，替代高成本扩散模型。
- 在门静脉、脑血管、冠状动脉三个公开数据集上，统一架构与训练策略超越通用及血管专用方法。
- 有效保留细薄分支和血管连续性，推理效率优于扩散模型，适合高分辨率三维体数据。

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_3088f2bd42dc7b7a045b1f4d