用扩散模型检测放疗中器官分割误差，定位更准。
Image-Conditioned Diffusion Models for Quality Assurance of Organ-at-Risk Segmentations in Radiotherapy
- 用图像条件扩散模型重建分割图，对比原图找误差
- 在头颈部数据上，对边界微调的误差检测准确率更高
- 适合放疗医生快速质检，尤其擅长发现细微边界错误
精准的危及器官分割对放射治疗规划至关重要，但人工审核耗时且主观。本文研究基于范式建模的分割误差检测方法，在头颈部CT上对比了变分自编码器（VAE）与图像条件分割扩散模型。模型在RADCURE数据集的脑干和脊髓分割上，通过模拟边界和宽度扰动进行评估。采用骰子相似系数和输入与重建分割间的距离一致度（DTA）衡量误差检测效果。两种模型均能识别部分模拟误差，但区域DTA显示，扩散模型对细微边界误差的定位更一致。结果表明，图像条件扩散重建是实现局部化、解剖感知分割质量保证的有前景框架。
原文摘要 · Abstract (English)
Accurate organ-at-risk segmentation is essential for radiotherapy planning, but reviewing segmentations is time-consuming and subjective. We investigate normative modelling for segmentation error detection in head-and-neck CT, comparing a VAE framework with an image-conditioned segmentation diffusion model. Models were evaluated on RADCURE brainstem and spinal cord segmentations using simulated boundary and width perturbations. Error detection was assessed using the Dice similarity coefficient and the Distance to Agreement (DTA) between the input and reconstructed segmentations. While both models detected some simulated errors, regional DTA showed that the diffusion model localised subtle boundary errors more consistently. These results support image-conditioned diffusion reconstruction as a promising framework for localised, anatomy-aware segmentation QA.
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。