Meeting Banner
Abstract #2450

Initial experience in abbreviated T2-weighted Prostate MRI using a Deep Learning reconstruction.

Aileen O'Shea1, Arnaud Guidon2, Robert Marc Lebel3, Ersin Bayram4, Theodore Pierce1, Amirkasra Mojtahed1, and Mukesh G Harisinghani1
1Massachusetts General Hospital, Boston, MA, United States, 2Applications and Workflow, GE Healthcare, Boston, MA, United States, 3Applications and Workflow, GE Healthcare, Calgary, AB, Canada, 4Applications and Workflow, GE Healthcare, Houston, TX, United States

Increasing the speed of multiparametric prostate MRI (mpMRI) is highly desirable. However, usual tradeoffs between signal-to-noise (SNR), scan time and lesion conspicuity must be considered. One recently proposed approach consists of using a bi-parametric protocol, whereby only the T2 and diffusion-weighted images are collected, thus highlighting the particular significance of achieving a robust, high-quality T2-weighted acquisition. As such, this work focuses on evaluating a Deep Learning reconstruction technique which shows promises to cut acquisition time of prostate T2-weighted imaging in half and would therefore benefit both bi-parametric as well as mpMRI.

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here