Accelerated Quantitative Magnetization Transfer Mapping with Deep Learning (MTAcqNet)

Motivation: Quantitative MT mapping provides valuable insights into macromolecular content in the brain. However, its long scan times limit clinical applicability. This study aims to reduce acquisition time while maintaining accuracy in parameter mapping. Goal(s): To develop MTAcqNet, a deep-learning framework that accurately synthesizes images with varying MT contrasts, enabling efficient MMPF map generation from a small set of acquired MT images. Approach: MTAcqNet was designed to predict six MT images from four input MT images, which performance was evaluated by comparing generated MMPF maps with ground truth. Results: MTAcqNet predictions showed excellent correlation with ground truth, enabling more efficient MT scans for modeling. Impact: The proposed MTAcqNet accelerates MT data acquisition and enables faster macromolecular proton fraction mapping using quantitative MT modeling. By reducing scan time, it facilitates rapid clinical translation of quantitative MT imaging, providing valuable insights into macromolecular content in the brain.