Measurement Score-Based MRI Reconstruction with Automatic Coil Sensitivity Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Tingjun, Park, Chicago Y., Hu, Yuyang, An, Hongyu, Kamilov, Ulugbek S.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911171177611264
author Liu, Tingjun
Park, Chicago Y.
Hu, Yuyang
An, Hongyu
Kamilov, Ulugbek S.
author_facet Liu, Tingjun
Park, Chicago Y.
Hu, Yuyang
An, Hongyu
Kamilov, Ulugbek S.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18402
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Measurement Score-Based MRI Reconstruction with Automatic Coil Sensitivity Estimation
Liu, Tingjun
Park, Chicago Y.
Hu, Yuyang
An, Hongyu
Kamilov, Ulugbek S.
Image and Video Processing
Machine Learning
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.
title Measurement Score-Based MRI Reconstruction with Automatic Coil Sensitivity Estimation
topic Image and Video Processing
Machine Learning
url https://arxiv.org/abs/2509.18402