{"ID":2867956,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.18402","arxiv_id":"2509.18402","title":"Measurement Score-Based MRI Reconstruction with Automatic Coil Sensitivity Estimation","abstract":"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.","short_abstract":"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 oft...","url_abs":"https://arxiv.org/abs/2509.18402","url_pdf":"https://arxiv.org/pdf/2509.18402v1","authors":"[\"Tingjun Liu\",\"Chicago Y. Park\",\"Yuyang Hu\",\"Hongyu An\",\"Ulugbek S. Kamilov\"]","published":"2025-09-22T20:33:41Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.LG\"]","methods":"[\"Diffusion Model\"]","has_code":false}