SPICER: Self-Supervised Learning for MRI with Automatic Coil Sensitivity Estimation and Reconstruction

TL;DR

SPICE introduces a self-supervised learning framework for MRI that simultaneously estimates coil sensitivities and reconstructs images from undersampled data without groundtruth, achieving state-of-the-art results in accelerated MRI.

Contribution

It presents a novel self-supervised approach that jointly estimates coil sensitivities and reconstructs MRI images, removing the need for pre-estimated sensitivities and groundtruth images.

Findings

Achieves high-quality MRI reconstruction with up to 10x acceleration.

Outperforms existing methods in highly undersampled scenarios.

Operates effectively without groundtruth data.

Abstract

Deep model-based architectures (DMBAs) integrating physical measurement models and learned image regularizers are widely used in parallel magnetic resonance imaging (PMRI). Traditional DMBAs for PMRI rely on pre-estimated coil sensitivity maps (CSMs) as a component of the measurement model. However, estimation of accurate CSMs is a challenging problem when measurements are highly undersampled. Additionally, traditional training of DMBAs requires high-quality groundtruth images, limiting their use in applications where groundtruth is difficult to obtain. This paper addresses these issues by presenting SPICE as a new method that integrates self-supervised learning and automatic coil sensitivity estimation. Instead of using pre-estimated CSMs, SPICE simultaneously reconstructs accurate MR images and estimates high-quality CSMs. SPICE also enables learning from undersampled noisy measurements without any groundtruth. We validate SPICE on experimentally collected data, showing that it can achieve state-of-the-art performance in highly accelerated data acquisition settings (up to 10x).