Abstract #4201

Feasibility of an abdominal thin-slice breath-hold single-shot FSE sequence processed using a deep learning-based noise-reduction approach

Taku Tajima^1,2, Hiroyuki Akai³, Koichiro Yasaka⁴, Akira Kunimatsu¹, Masaaki Akahane², Naoki Yoshioka², Osamu Abe⁴, Kuni Ohtomo⁵, and Shigeru Kiryu²

¹Department of Radiology, International University of Health and Welfare Mita Hospital, Tokyo, Japan, ²Department of Radiology, International University of Health and Welfare Narita Hospital, Chiba, Japan, ³Department of Radiology, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan, ⁴Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan, ⁵International University of Health and Welfare, Tochigi, Japan

Synopsis

Single-shot fast spin echo (single-shot FSE) sequence is an accelerated T2-weighted imaging (T2WI) in pancreatic MRI. Fast advanced spin echo (FASE) is one of similar modalities. However, single-shot FSE suffers from image blurring and relatively low tissue contrast. We hypothesized that denoising approach with deep learning-based reconstruction (dDLR) would facilitate accelerated breath-hold thin-slice single-shot FSE MRI. We assessed the image quality of respiratory-triggered FSE T2WI (Resp-FSE) and breath-hold FASE with and without dDLR (BH-dDLR-FASE and BH-FASE, respectively) at 1.5 T. The image quality of BH-dDLR-FASE was superior to BH-FASE and Resp-FSE, and BH-dDLR-FASE had a shorter acquisition time than Resp-FSE.

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

Join Here