Calibrationless Parallel MRI using Model based Deep Learning (C-MODL)
This addresses faster, more reliable MRI reconstruction for medical imaging applications, representing a novel method for a known bottleneck.
The paper tackles calibrationless parallel MRI reconstruction by introducing a model-based deep learning approach that learns non-linear annihilation relations in Fourier domain, achieving three orders of magnitude faster computation than structured low rank methods while eliminating the need for fully sampled calibration data.
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.