Abstract #3100

Deep Learning Reconstruction improves CEST MRI

Shu Zhang¹, Xinzeng Wang², F. William Schuler¹, R. Marc Lebel³, Mitsuharu Miyoshi⁴, Ersin Bayram², Elena Vinogradov⁵, Jason M. Johnson⁶, Jingfei Ma⁷, and Mark D. Pagel¹

¹Cancer Systems Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX, United States, ²Global MR Applications & Workflow, GE Healthcare, Houston, TX, United States, ³Global MR Applications & Workflow, GE Healthcare, Calgary, AB, Canada, ⁴Global MR Applications & Workflow, GE Healthcare Japan, Tokyo, Japan, ⁵Radiology, UT Southwestern Medical Center, Dallas, TX, United States, ⁶Neuroradiology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States, ⁷Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, United States

Image reconstruction using deep learning (DL Recon) is capable of enhancing image signal-to-noise ratio (SNR) without losing image resolution or altering the image contrast. Our study demonstrates that CEST imaging and quantification, which are often limited by SNR and long scan time, can be improved with DL Recon. Our results clearly indicated that DL Recon can be used for CEST imaging with higher spatial resolution without or with only a mild increase in scan time or for CEST imaging in reduced scan time by using parallel imaging without the typical SNR penalty.

This abstract and the presentation materials are available to members only; a login is required.

Join Here