Meeting Banner
Abstract #0104

Value of Deep Learning-Accelerated T1-w Dixon MRI for Upper Abdominal Imaging

Johannes Beat Fingerhut1, Tobias Scheef1, Hannes Engel1, Alexander Rau1, Lorenz Kolbe1, Caroline Wilpert1, Ralph Strecker2, Marcel Dominik Nickel3, Fabian Bamberg1, Jakob Weiss1, and Niklas Verloh1
1Radiology, Medical Center – University of Freiburg, Freiburg, Germany, 2EMEA Scientific Partnerships, Siemens Healthineers AG, Forchheim, Germany, 3MR Application Predevelopment, Siemens Healthineers AG, Forchheim, Germany

Synopsis

Keywords: Hepatobiliary, AI/ML Image Reconstruction

Motivation: MRI is crucial for abdominal imaging due to its soft tissue contrast, but conventional sequences are limited by scan time and resolution. Deep-Learning-(DL)-based reconstruction may improve image quality and speed.

Goal(s): Does a DL-accelerated T1-weighted sequence (T1DL) enhance image quality and acquisition time for liver, spleen, and pancreas imaging?

Approach: This single-center study of 98 patients undergoing post-contrast 3T MRI with standard and T1DL sequences, with qualitative and independent quantitative image assessments.

Results: T1DL shortened the examination time from 17s to 13s and enhanced image quality.

Impact: DL-accelerated MRI optimizes scan time and image quality, especially benefiting patients with breath-holding difficulties.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords