Investigative Radiology December 2021

Respiratory Motion-Resolved Reconstruction of Free-Breathing Magnetic Resonance Imaging Using Deep Learning Without a Ground Truth for Improved Liver Imaging

Carousel 2Objectives: Respiratory binning of free-breathing magnetic resonance imaging data reduces motion blurring; however, it exacerbates noise and introduces severe artifacts due to undersampling. Deep neural networks can remove artifacts and noise but usually require high-quality ground truth images for training. This study aimed to develop a network that can be trained without this requirement.  View/Download


Investigative_RadiologyThis article, and specifically a different article each month from the current issue, is made available courtesy of Lippincott Williams & Wilkins, the publisher of Investigative Radiology – for both viewing on the web and download, with the restriction that this is for personal use only. Additional information can be found at