Scan-specific learning techniques improve accelerated MRI reconstruction by training models using data solely from the specific scan; but they are constrained to Cartesian imaging and require an integrated auto-calibration signal (ACS), reducing acceleration. This abstract extends the scan-specific model SPARK, which estimates and corrects reconstruction errors in k-space, to arbitrary acquisitions and reconstructions. We demonstrate improvements in 3D volumetric imaging either with an integrated or external ACS region and in simultaneous multi-slice, wave-encoded imaging. SPARK enables an order of magnitude acceleration with ~2-fold reduction in reconstruction error compared to advanced reconstruction techniques that serve as its input.
This abstract and the presentation materials are available to members only; a login is required.