Efficient Standardization of Clinical T2-Weighted Images: Phase-Conjugacy e-CAMP with Projected Gradient Descent

Motivation: Routine clinical images are a massive data source for machine learning. The previously introduced e-CAMP method can convert T2-weighted images of clinical TSE acquisition to quantitative T2 maps, but it requires tuning of many parameters, impeding widespread implementation. Goal(s): To present an algorithm that requires few parameter choices, is robust to those parameter values, and is faster to convergence. Approach: Projected Gradient Descent ensures efficient enforcement of the T2-decay model constraint and greatly eliminates parameter tuning. e-CAMP is further enhanced by phase conjugacy with Virtual Conjugate Coils. Results: The efficient and robust implementation of e-CAMP shows accurate T2 map reconstruction. Impact: Rather than acquire specific yet time-consuming quantitative images, e-CAMP can efficiently standardize the existing qualitative images from routine clinical scans and exploit the enormous amount of images to create dataset for large-scale machine learning.