3D Regression Neural Network for the Quantification of Enlarged Perivascular Spaces in Brain MRI

This paper addresses the problem of automated quantification of enlarged perivascular spaces from MR images. The perivascular space - also called Virchow-Robin space - is the space between a vein or an artery and pia mater, the envelope covering the brain. These spaces are known to have a tendency to dilate for reasons not yet clearly understood (Adams et  al., 2015). Enlarged - or dilated - perivascular spaces (EPVS) can be identified as hyperintensities on T2-weighted MRI. In Fig. 1, we show examples of EPVS in T2-weighted scans.

Source: Medical Image Analysis - October 25, 2018 Category: Radiology Authors: Florian Dubost, Hieab Adams, Gerda Bortsova, M. Arfan Ikram, Wiro Niessen, Meike Vernooij, Marleen de Bruijne Source Type: research