Zenon Starčuk

This study uses dynamic 1H-[2H]-FID-MRSI and a metabolic model to quantify glucose oxidative metabolism in rat brain regions during 2H-Glc infusion.

This paper introduces a self-supervised deep learning method for quantifying metabolite concentrations in MR spectroscopy data, showing comparable accuracy to traditional methods with faster processing.

This paper develops unsupervised deep learning methods for frequency and phase correction of MRS signals, showing comparable performance to supervised approaches and improved efficiency.