MRecover: A Conditional Generative Model for Recovering Motion-Corrupted MR images Using AI Generated Contrast
Addresses data loss from motion artifacts in high-resolution T2w MRI for hippocampal subfield segmentation, a critical bottleneck in neuroimaging studies.
MRecover synthesizes T2w TSE images from T1w MRI to recover motion-corrupted hippocampal subfield segmentation data, achieving 31.8% more analyzable subjects in ADNI3 and improved effect sizes for diagnostic group differences.
Hippocampal subfield segmentation requires high-resolution T2w turbo spin echo (TSE) MRI, yet this sequence is susceptible to motion artifacts, leading to substantial data loss. We developed a conditional generative model (MRecover) that synthesizes routinely acquired T1w images to create TSE images with autoregressive slice conditioning for volumetric consistency. Trained on 7T MRI data (n=577), the model achieved high in-domain fidelity (n=148, SSIM=0.84, FSIM=0.94) and generalized well to out-of-domain 3T data: subfield volumes from synthesized and the as-acquired images closely matched: (n=416, r=0.87-0.97) and yielded 31.8% more analyzable subjects in the motion-affected ADNI3 dataset after quality control (593 vs 450). The synthesized images also achieved larger effect sizes due to increasing the sample size for diagnostic group differences in hippocampal subfield atrophy (whole hippocampus $ε^2$= 0.121-0.100 vs. 0.086-0.062, left-right hemispheres). Project page: https://jinghangli98.github.io/MRecover/