Hanna Bugler

This paper develops a deep learning framework to improve GABA-edited MRS quality by optimizing transient averaging based on quality scores.

The paper introduces a Python toolbox, SMART_MRS, to simulate common artifacts in GABA-edited MRS data, enhancing the diversity and quality of simulated data.

This study compares complex-valued and real-valued inputs and convolutions in CNNs for frequency and phase correction of GABA-edited MRS data, finding complex inputs with real convolutions most effective.

This paper presents a benchmark challenge to compare machine learning models for GABA-edited MRS reconstruction using reduced transients, finding that deep learning models achieve comparable metrics to conventional methods.