Specialized computational methods for denoising, B1 correction, and kinetic modeling in hyperpolarized 13 C MR EPSI studies of liver tumors.

Philip M Lee Hsin-Yu Chen Jeremy W GordonZihan ZhuPeder Eric Zufall Larson Nicholas DworkMark Van CriekingeLucas CarvajalMichael A OhilgerZhen J WangDuan Xu John Kurhanewicz Robert A BokRahul AggarwalPamela N MunsterDaniel B Vigneron

Published in: Magnetic resonance in medicine (2021)

The new HP 13 C EPSI post-processing pipeline integrated tensor denoising and B 1 + correction to measure kPL in patients with liver tumors. These technical developments not only recovered metabolite signals in voxels that did not receive the prescribed flip angle, but also increased the extent and accuracy of kPL estimations throughout the tumor and adjacent regions including normal-appearing tissue and additional lesions.

Keyphrases

convolutional neural network
palliative care
high resolution
magnetic resonance
machine learning
contrast enhanced
mass spectrometry
deep learning