用扩散模型实现更准更快的医学图像分割，还能给出可信度估计。
Prior-Guided Residual Diffusion: Calibrated and Efficient Medical Image Segmentation
- 先用粗略预测提供引导，再学残差修正，提升收敛速度和校准度。
- 在多个脑部与胸部影像数据集上，分割准确率更高，误差更小。
- 适合需要高可靠性和快速推理的医疗影像分析场景。
医学图像分割中的不确定性要求模型捕捉完整的条件分布，而非单一点估计。本文提出先验引导残差扩散（PGRD），一种基于扩散的框架，在保持强校准性的同时实现高效采样。PGRD将离散标签嵌入连续空间作为一热目标，使分割与扩散建模对齐；通过粗略先验预测逐步引导，扩散网络学习对先验的残差修正，加速收敛并提升校准性；采用深层扩散监督机制，通过中间时间步监督稳定训练过程。在代表性MRI与CT数据集上的实验表明，PGRD在Dice分数、NLL和ECE值上均优于贝叶斯、集成、概率U-Net及普通扩散基线模型，且采样步骤更少即可达到优异性能。
原文摘要 · Abstract (English)
Ambiguity in medical image segmentation calls for models that capture full conditional distributions rather than a single point estimate. We present Prior-Guided Residual Diffusion (PGRD), a diffusion-based framework that learns voxel-wise distributions while maintaining strong calibration and practical sampling efficiency. PGRD embeds discrete labels as one-hot targets in a continuous space to align segmentation with diffusion modeling. A coarse prior predictor provides step-wise guidance; the diffusion network then learns the residual to the prior, accelerating convergence and improving calibration. A deep diffusion supervision scheme further stabilizes training by supervising intermediate time steps. Evaluated on representative MRI and CT datasets, PGRD achieves higher Dice scores and lower NLL/ECE values than Bayesian, ensemble, Probabilistic U-Net, and vanilla diffusion baselines, while requiring fewer sampling steps to reach strong performance.
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。