Calibrationless Parallel MRI using Model based Deep Learning (C-MODL)

TL;DR

This paper presents a fast, calibrationless deep learning method for parallel MRI reconstruction that learns non-linear relations directly from data, significantly reducing computation time and improving image quality without calibration data.

Contribution

It introduces a novel non-linear deep learning framework that generalizes structured low rank methods for calibrationless MRI, enabling faster and more accurate reconstructions.

Findings

Achieves three orders of magnitude faster reconstruction than traditional SLR methods.

Improves image quality by integrating spatial domain priors with hybrid regularization.

Eliminates the need for calibration data, reducing potential mismatches.

Abstract

We introduce a fast model based deep learning approach for calibrationless parallel MRI reconstruction. The proposed scheme is a non-linear generalization of structured low rank (SLR) methods that self learn linear annihilation filters from the same subject. It pre-learns non-linear annihilation relations in the Fourier domain from exemplar data. The pre-learning strategy significantly reduces the computational complexity, making the proposed scheme three orders of magnitude faster than SLR schemes. The proposed framework also allows the use of a complementary spatial domain prior; the hybrid regularization scheme offers improved performance over calibrated image domain MoDL approach. The calibrationless strategy minimizes potential mismatches between calibration data and the main scan, while eliminating the need for a fully sampled calibration region.