Deep Factor Model: A Novel Approach for Motion Compensated Multi-Dimensional MRI
This addresses the issue of slow MRI scans for medical imaging applications, though it appears incremental as it builds on existing quantitative parameter mapping methods like MR fingerprinting.
The authors tackled the problem of long scan times in 3D high-resolution multi-contrast MRI by introducing the Deep Factor Model (DFM), which enables highly undersampled acquisition, resulting in reduced scan time while integrating motion compensation for robustness.
Recent quantitative parameter mapping methods including MR fingerprinting (MRF) collect a time series of images that capture the evolution of magnetization. The focus of this work is to introduce a novel approach termed as Deep Factor Model(DFM), which offers an efficient representation of the multi-contrast image time series. The higher efficiency of the representation enables the acquisition of the images in a highly undersampled fashion, which translates to reduced scan time in 3D high-resolution multi-contrast applications. The approach integrates motion estimation and compensation, making the approach robust to subject motion during the scan.