DiffSegLung: 基于扩散的放射组学蒸馏用于无监督肺部病理分割
DiffSegLung: Diffusion Radiomic Distillation for Unsupervised Lung Pathology Segmentation
AI总结：
本文提出DiffSegLung，通过引入扩散放射组学蒸馏方法，利用手工制作的放射组学描述符作为物理基础的教师，引导3D扩散U-Net的瓶颈层，提升无监督肺部病理分割性能。
摘要：
无监督分割肺部病理在CT中仍是一个开放性挑战，由于缺乏标注的多病理种群以及现有基于扩散的方法无法有效利用定量的Hounsfield单位（HU）信号来区分组织类别。为此，我们提出DiffSegLung，一种引入扩散放射组学蒸馏的框架，其中手工制作的放射组学描述符作为物理基础的教师，通过对比目标引导3D扩散U-Net的瓶颈层，将病理判别结构转移到学习的表示中，而无需任何标注。在推理阶段，教师被丢弃，多时间步瓶颈特征通过高斯混合模型进行聚类，结合HU引导的标签分配，随后通过Sobel扩散融合进行边界细化。在190个专家标注的轴向切片上评估，DiffSegLung在所有四个病理类别上均优于无监督基线，并在生成保真度上优于先前的CT扩散模型。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
