无需标注数据，用医学影像物理特性实现肺部病灶无监督分割。
DiffSegLung: Diffusion Radiomic Distillation for Unsupervised Lung Pathology Segmentation
- 用手工提取的影像特征作物理教师，指导扩散模型学习病灶结构。
- 在4个不同数据集上，对4类肺部病灶分割效果均优于现有无监督方法。
- 适合做医学图像无监督分析或扩散模型改进的研究者参考。
CT中肺部病灶的无监督分割仍面临挑战，主要源于缺乏标注的多病种数据集，以及现有基于扩散的方法未能有效利用能物理区分组织类型的定量亨氏单位（HU）信号。为此，我们提出DiffSegLung框架，引入扩散放射组学蒸馏机制：手工提取的放射组学特征作为物理基础教师，通过对比损失函数引导3D扩散U-Net的瓶颈层，将病灶判别性结构信息无标注地融入学习表示中。推理时，教师被丢弃，利用高斯混合模型对多时间步瓶颈特征聚类，并结合HU引导的标签分配，最后通过Sobel扩散融合优化边界。在来自四个异构CT队列的190张专家标注轴向切片上评估，DiffSegLung在所有四类病理上均优于无监督基线，且生成保真度高于先前的CT扩散模型。
原文摘要 · Abstract (English)
Unsupervised segmentation of pulmonary pathologies in CT remains an open challenge due to the absence of annotated multi pathology cohorts and the failure of existing diffusion-based methods to exploit the quantitative Hounsfield Unit (HU) signal that physically distinguishes tissue classes. To address this, we propose DiffSegLung,a framework that introduces Diffusion Radiomic Distillation, in which handcrafted radiomic descriptors serve as a physics grounded teacher to shape the bottleneck of a 3D diffusion U-Net via a contrastive objective, transferring pathology discriminative structure into the learned representation without any annotations. At inference, the teacher is discarded and multitimestep bottleneck features are clustered by a Gaussian Mixture Model with HU-guided label assignment, followed by Sobel Diffusion Fusion for boundary refinement. Evaluated on 190 expert annotated axial slices drawn from four heterogeneous CT cohorts, Diff-SegLung improves segmentation across all four pathology classes over unsupervised baselines and improves generation fidelity over prior CT diffusion models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。