[论文] [论文] FleXray: Universal Clinical X-ray Segmentation

论文概要

研究领域: CV
作者: Victor Ion Butoi, Vivek Gopalakrishnan, John V. Guttag, Adrian V. Dalca, Neel Dey
发布时间: 2026-09-22
arXiv: 2609.26756

中文摘要

X 光是医学最常用的影像模态，却也是最不定量的之一：与 CT/MRI 不同，X 光把 3D 解剖压成 2D 投影，结构重叠、边界模糊，即便专家亦然。为通用分割系统标注 X 光数据库因此不现实，形态计量与功能 X 光分析长期局限于狭窄解剖区域。我们提出 FleXray——临床 X 光全身解剖分割的通用模型。不整理大型人工标注集，而是构建可扩展、基于物理的生成式 X 光数据引擎：利用现有 3D 全身 CT 分割数据集与生成式图像编辑模型，模拟外观多样、生理特性各异、成像几何不同的全标注 2D X 光。在此模拟上训练的 FleXray 能在未见研究数据集与真实世界 X 光上精确分割 60 个解剖结构，并支持疾病分级自动测量、X 光引导介入的稳健导航、病理目标的数据高效学习。我们在 https://flexray.csail.mit.edu 发布模型、代码、全身分割数据集与本地浏览器工具。

原文摘要

X-ray is medicine's most widely used imaging modality, yet remains among its least quantitative. Unlike volumetric modalities like CT or MRI, X-ray collapses 3D anatomy into a 2D projection, causing structures to overlap and anatomical boundaries to be ambiguous, even to experts. As a result, labeling X-ray databases for training general-purpose segmentation systems is impractical, leaving morphometric and functional X-ray analysis confined to narrow anatomical regions and applications. To this end, we present FleXray, a generalist model for anatomical segmentation across the entire body in clinical X-rays. Instead of curating large, manually annotated X-ray datasets, we build a scalable, physics-based generative X-ray data engine. Using existing 3D whole-body CT segmentation datasets and generative image-editing models, we simulate fully-annotated 2D X-rays with diverse appearances, physiological properties, and imaging geometries. Trained on these simulations, FleXray accurately segments 60 anatomical structures across unseen research datasets and in-the-wild X-rays. We further show that FleXray makes X-rays directly amenable to quantitative analysis, enabling automated measurements for disease grading, robust navigation during X-ray-guided interventions, and data-efficient learning of pathological targets. We release the model, code, a full-body X-ray segmentation dataset, and a local, easy-to-use browser-based tool at https://flexray.csail.mit.edu .

自动采集于 2026-09-24

#论文 #arXiv #CV #小凯