Adaptive Diffusion Priors for Accelerated MRI Reconstruction
Alper Güngör Salman UH Dar Şaban Öztürk Yilmaz Korkmaz Hasan A Bedel Gokberk Elmas Muzaffer Ozbey Tolga Çukur Department of Electrical and Electronics Engineering, Bilkent University, Ankara 06800, Turkey National Magnetic Resonance Research Center (UMRAM), Bilkent University, Ankara 06800, Turkey ASELSAN Research Center, Ankara 06200, Turkey Department of Electrical and Electronics Engineering, Amasya University, Amasya 05100, Turkey Neuroscience Program, Bilkent University, Ankara 06800, Turkey denotes equal contribution
Abstract
Deep MRI reconstruction is commonly performed with conditional models that de-alias undersampled acquisitions to recover images consistent with fully-sampled data. Since conditional models are trained with knowledge of the imaging operator, they can show poor generalization across variable operators. Unconditional models instead learn generative image priors decoupled from the operator to improve reliability against domain shifts related to the imaging operator. Recent diffusion models are particularly promising given their high sample fidelity. Nevertheless, inference with a static image prior can perform suboptimally. Here we propose the first adaptive diffusion prior for MRI reconstruction, AdaDiff, to improve performance and reliability against domain shifts. AdaDiff leverages an efficient diffusion prior trained via adversarial mapping over large reverse diffusion steps. A two-phase reconstruction is executed following training: a rapid-diffusion phase that produces an initial reconstruction with the trained prior, and an adaptation phase that further refines the result by updating the prior to minimize data-consistency loss. Demonstrations on multi-contrast brain MRI clearly
中文速览
加速磁共振成像（MRI）需要从欠采样数据中重建高质量图像，传统的条件深度学习方法因为与特定采集参数绑定，一旦扫描协议改变（如加速倍率或线圈配置变化）就容易掉性能。AdaDiff提出了一种基于扩散模型（diffusion model）的自适应无条件图像先验方法：先用对抗映射网络（adversarial mapper）实现只需少数大步反向扩散的高效采样，再在推理阶段分两步走——快速扩散阶段用训练好的先验得到初始重建，随后的先验自适应阶段通过最小化数据一致性损失对先验网络参数进行在线更新，使其向当前被试的真实数据分布靠拢。在多对比度脑部MRI实验中，AdaDiff在训练-测试条件匹配时与最优方法持平，而在采集算子或图像分布发生偏移的跨域场景下则明显优于现有条件模型和静态无条件模型。这项工作的价值在于，它首次将推理阶段的先验自适应引入扩散模型重建框架，在不依赖特定采集参数的同时兼顾了效率与鲁棒性，对临床中频繁变化扫描协议的实际需求具有直接意义。
原文 arXiv:2207.05876;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2207.05876v3