Measurement Score-Based MRI Reconstruction with Automatic Coil Sensitivity Estimation
This addresses a practical bottleneck in medical imaging by enabling more flexible MRI reconstruction, though it is incremental as it builds on existing diffusion-based methods.
The paper tackles the problem of MRI reconstruction without needing pre-calibrated coil sensitivity maps or ground truth images, proposing C-MSM which jointly estimates coil sensitivities and learns from k-space data, achieving performance close to methods that rely on clean priors.
Diffusion-based inverse problem solvers (DIS) have recently shown outstanding performance in compressed-sensing parallel MRI reconstruction by combining diffusion priors with physical measurement models. However, they typically rely on pre-calibrated coil sensitivity maps (CSMs) and ground truth images, making them often impractical: CSMs are difficult to estimate accurately under heavy undersampling and ground-truth images are often unavailable. We propose Calibration-free Measurement Score-based diffusion Model (C-MSM), a new method that eliminates these dependencies by jointly performing automatic CSM estimation and self-supervised learning of measurement scores directly from k-space data. C-MSM reconstructs images by approximating the full posterior distribution through stochastic sampling over partial measurement posterior scores, while simultaneously estimating CSMs. Experiments on the multi-coil brain fastMRI dataset show that C-MSM achieves reconstruction performance close to DIS with clean diffusion priors -- even without access to clean training data and pre-calibrated CSMs.