Premium
Towards the automatic computational assessment of enlarged perivascular spaces on brain magnetic resonance images: A systematic review
Author(s) -
Hernández Maria,
Piper Rory J.,
Wang Xin,
Deary Ian J.,
Wardlaw Joanna M.
Publication year - 2013
Publication title -
journal of magnetic resonance imaging
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.563
H-Index - 160
eISSN - 1522-2586
pISSN - 1053-1807
DOI - 10.1002/jmri.24047
Subject(s) - perivascular space , hyperintensity , fluid attenuated inversion recovery , segmentation , magnetic resonance imaging , terminology , computer science , white matter , pattern recognition (psychology) , artificial intelligence , nuclear magnetic resonance , physics , medicine , radiology , philosophy , linguistics
Enlarged perivascular spaces (EPVS), visible in brain MRI, are an important marker of small vessel disease and neuroinflammation. We systematically evaluated the literature up to June 2012 on possible methods for their computational assessment and analyzed confounds with lacunes and small white matter hyperintensities. We found six studies that assessed/identified EPVS computationally by seven different methods, and four studies that described techniques to automatically segment similar structures and are potentially suitable for EPVS segmentation. T2‐weighted MRI was the only sequence that identified all EPVS, but FLAIR and T1‐weighted images were useful in their differentiation. Inconsistency within the literature regarding their diameter and terminology, and overlap in shape, intensity, location, and size with lacunes, conspires against their differentiation and the accuracy and reproducibility of any computational segmentation technique. The most promising approach will need to combine various MR sequences and consider all these features for accurate EPVS determination. J. Magn. Reson. Imaging 2013;38:774–785. © 2013 Wiley Periodicals, Inc.