Complex Swin Transformer for Accelerating Enhanced SMWI Reconstruction

Motivation: Susceptibility Map-Weighted Imaging (SMWI), an advanced imaging technique for detecting nigral hyperintensity in Parkinson's Disease, is hindered by long scan times at full resolution. There is a need for efficient methods to produce high-quality SMWI from reduced k-space data. Goal(s): To maintain diagnostic relevance in SMWI images reconstructed from low-resolution k-space data. Approach: Complex Swin Transformer Network for super-resolving multi-echo MRI data. Results: The method achieved SSIM of 91.16% and MSE of 0.076 for SMWI reconstructions from 256x256 k-space data, preserving diagnostic quality. Impact: This research enables high-quality SMWI generation from reduced k-space data, accelerating scan times while preserving diagnostic detail. The approach could significantly enhance SMWI's clinical application for Parkinson's Disease and support faster, more efficient neuroimaging workflows.