Accelerating Multi-parametric Mapping using a Deep Wave-ESPIRiT Model

Motivation: The MULTIPLEX technique quantifies T1/T2*/PD/susceptibility maps in a single 3D scan, but dual TR, dual flip angle, and multi-echo acquisition strategies lead to long scan times. The CS-Wave method for 9-fold accelerated Wave-CAIPI faces issues like repeated iterations and limited information utilization, resulting in longer reconstruction times and reduced acceleration efficiency. Goal(s): Develop a fast, efficient reconstruction method to reduce time without losing quantification accuracy. Approach: This work introduces a deep Wave-ESPIRiT model to minimize iterations and maximize information utilization. Results: The DL-Wave-ESPIRiT reconstructs 9-fold accelerated Wave-CAIPI data in 30 seconds, achieving the quantification accuracy of a 4.5-minute CS-Wave reconstruction. Impact: The proposed DL-Wave-ESPIRiT method significantly reduces reconstruction time for accelerated MULTIPLEX imaging, achieving high accuracy in seconds instead of minutes. This advancement enhances clinical efficiency and enables faster, more effective imaging workflows.