Abstract #0331

A 3D Dense-U-Net for fully automated 5D flow MRI segmentation

Liliana E. Ma^1,2, Haben Berhane^1,2, Justin Baraboo^1,2, Michael Sugimura³, Christopher W. Roy⁴, Mariana Falcão⁴, Jérôme Yerly⁴, Matthias Stuber^4,5, and Michael Markl^1,2

¹Department of Radiology, Northwestern University, Feinberg School of Medicine, Chicago, IL, United States, ²Department of Biomedical Engineering, Northwestern University, Evanston, IL, United States, ³Self-employed, Chicago, IL, United States, ⁴Department of Radiology, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland, ⁵Center for Biomedical Imaging, Lausanne, Switzerland

Synopsis

Recently, a free-running 5D flow framework was introduced and validated. However, some 5D flow MRI is based on 3D radial imaging, which is limited by reduced SNR that can result in challenges with 3D segmentation. A number of previous studies have investigated automatic segmentation for 4D flow MRI, however these have been traditionally optimized for Cartesian datasets, which are typically acquired over much smaller spatial matrices and cover only one respiratory position. The purpose of this study was thus to adapt and expand a deep-learning framework to cardiac 5D flow MRI data for automatic segmentation of the thoracic aorta.

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

Join Here