GABA-Edited Magnetic Resonance Spectroscopy Deep Learning Quality Assessment Framework

Abstract

PurposeMotivated by the need to improve GABA-edited magnetic resonance spectroscopy (MRS) quality, we developed a three-module framework to improve transient averaging based on quality. We hypothesized that training a deep learning (DL) to differentiate spectrum quality could improve transient averaging compared to traditional averaging. MethodsThe transient averaging framework was approached through three modules: (1) a continuous-valued automated quality labeling algorithm using both traditional and recently developed MRS quality metrics, (2) a dual-domain (time and frequency) DL model that learns from these quality labels to assess quality scores for new data, and (3) a transient weighting algorithm informed by DL quality scores. The labeling algorithm was used to produce quality labels focused on retaining GABA peak shape in difference spectra (1) to train the DL model (2). The DL model quality scores were used to assign weights (3) for transient pairs within the final average difference spectrum. Results were compared to an existing software weighting algorithm for transient averaging and traditional transient averaging. ResultsRetaining only GABA-edited transient pairs with quality labels above zero, defined by metrics evaluating peak shapes, resulted in overall better traditional and recently developed mean metric values as well as better visual assessment of GABA and Glx peaks. Applying the trained DL model to in vivo scans, the average difference spectra calculated from the DL quality scores and weighting algorithm resulted in lower fit errors than averaging all transients with equal weights. ConclusionThe proposed framework can optimize transient averaging based on quality for edited-MRS.