Clinically Feasible Whole Knee MR T1ρ and T2 Mapping in Under 3 Minutes with Accelerated Imaging and Automated Analysis

Motivation: Long MRI acquisition times limit T1ρ/T2 mapping for assessing cartilage health, necessitating faster and reliable quantification methods. Goal(s): This study evaluates the use of accelerated qMRI and deep learning-based segmentation for reliable T1ρ/T2 mapping without high-resolution morphological images. Approach: A pretrained segmentation model, with and without transfer learning, was used to segment six cartilage and meniscal regions from GRAPPA2-MAPSS and compressed sensing accelerated (CS-AF8)-MAPSS echo images. These segmentations, overlaid on maps, provided T1ρ/T2 quantification. Results: CS-AF8, with transfer learning, achieved comparable segmentation performance and T1ρ/T2 quantification to the standard MAPSS with DESS segmentation, although it showed higher variation in T1ρ/T2 values. Impact: This research offers a clinically feasible accelerated qMRI and deep learning-based approach for faster and accurate qMRI-based cartilage assessment, allowing T1ρ and T2 mapping in under 3 minutes.