Enlarged perivascular spaces in brain MRI: Automated quantification in four regions

&NA; Enlarged perivascular spaces (PVS) are structural brain changes visible in MRI, are common in aging, and are considered a reflection of cerebral small vessel disease. As such, assessing the burden of PVS has promise as a brain imaging marker. Visual and manual scoring of PVS is a tedious and observer‐dependent task. Automated methods would advance research into the etiology of PVS, could aid to assess what a “normal” burden is in aging, and could evaluate the potential of PVS as a biomarker of cerebral small vessel disease. In this work, we propose and evaluate an automated method to quantify PVS in the midbrain, hippocampi, basal ganglia and centrum semiovale. We also compare associations between (earlier established) determinants of PVS and visual PVS scores versus the automated PVS scores, to verify whether automated PVS scores could replace visual scoring of PVS in epidemiological and clinical studies. Our approach is a deep learning algorithm based on convolutional neural network regression, and is contingent on successful brain structure segmentation. In our work we used FreeSurfer segmentations. We trained and validated our method on T2‐contrast MR images acquired from 2115 subjects participating in a population‐based study. These scans were visually scored by an expert rater, who counted the number of PVS in each brain region. Agreement between visual and automated scores was found to be excellent for all four regions, with intraclass correlation coefficients (ICCs) between 0.75 and 0.88. These values were higher than the inter‐observer agreement of visual scoring (ICCs between 0.62 and 0.80). Scan‐rescan reproducibility was high (ICCs between 0.82 and 0.93). The association between 20 determinants of PVS, including aging, and the automated scores were similar to those between the same 20 determinants of PVS and visual scores. We conclude that this method may replace visual scoring and facilitate large epidemiological and clinical studies of PVS.

[1]  Sotirios A. Tsaftaris,et al.  Medical Image Computing and Computer Assisted Intervention , 2017 .

[2]  Andrew J Lees,et al.  Clinicopathological investigation of vascular parkinsonism, including clinical criteria for diagnosis , 2004, Movement disorders : official journal of the Movement Disorder Society.

[3]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[4]  Alan C. Evans,et al.  A nonparametric method for automatic correction of intensity nonuniformity in MRI data , 1998, IEEE Transactions on Medical Imaging.

[5]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[6]  Anand Viswanathan,et al.  Topography of dilated perivascular spaces in subjects from a memory clinic cohort , 2013, Neurology.

[7]  Nick C Fox,et al.  Neuroimaging standards for research into small vessel disease and its contribution to ageing and neurodegeneration , 2013, The Lancet Neurology.

[8]  J. Wardlaw,et al.  Cerebral Perivascular Spaces Visible on Magnetic Resonance Imaging: Development of a Qualitative Rating Scale and its Observer Reliability , 2015, Cerebrovascular Diseases.

[9]  Lucia Ballerini,et al.  Perivascular Spaces Segmentation in Brain MRI Using Optimal 3D Filtering , 2017, Scientific Reports.

[10]  S. Black,et al.  Understanding the role of the perivascular space in cerebral small vessel disease , 2018, Cardiovascular research.

[11]  D. Neary,et al.  Dilatation of the Virchow-Robin space is a sensitive indicator of cerebral microvascular disease: study in elderly patients with dementia. , 2005, AJNR. American journal of neuroradiology.

[12]  Víctor González-Castro,et al.  Reliability of an automatic classifier for brain enlarged perivascular spaces burden and comparison with human performance. , 2017, Clinical science.

[13]  Charles DeCarli,et al.  A priori collaboration in population imaging: The Uniform Neuro-Imaging of Virchow-Robin Spaces Enlargement consortium , 2015, Alzheimer's & dementia.

[14]  Raghav Mehta,et al.  M-net: A Convolutional Neural Network for deep brain structure segmentation , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[15]  Matthew D. Zeiler.  ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[16]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[17]  Albert Hofman,et al.  The potential for prevention of dementia across two decades: the prospective, population-based Rotterdam Study , 2015, BMC Medicine.

[18]  Peter R Luijten,et al.  Perivascular spaces on 7 Tesla brain MRI are related to markers of small vessel disease but not to age or cardiovascular risk factors , 2016, Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism.

[19]  Fuqiang Gao,et al.  Visible Virchow-Robin spaces on magnetic resonance imaging of Alzheimer's disease patients and normal elderly from the Sunnybrook Dementia Study. , 2014, Journal of Alzheimer's disease : JAD.

[20]  Wiro J. Niessen,et al.  Accuracy and reproducibility study of automatic MRI brain tissue segmentation methods , 2010, NeuroImage.

[21]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Anat Achiron,et al.  Sandlike appearance of Virchow-Robin spaces in early multiple sclerosis: a novel neuroradiologic marker. , 2002, AJNR. American journal of neuroradiology.

[23]  Marleen de Bruijne,et al.  3D regression neural network for the quantification of enlarged perivascular spaces in brain MRI , 2018, Medical Image Anal..

[24]  Stavros Stivaros,et al.  Potential surrogate markers of cerebral microvascular angiopathy in asymptomatic subjects at risk of stroke , 2009, European Radiology.

[25]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[26]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[27]  Daniel L Schwartz,et al.  MR Imaging-based Multimodal Autoidentification of Perivascular Spaces (mMAPS): Automated Morphologic Segmentation of Enlarged Perivascular Spaces at Clinical Field Strength. , 2017, Radiology.

[28]  N Purandare,et al.  Biomarkers of cerebrovascular disease in dementia. , 2007, The British journal of radiology.

[29]  PhilipR. Wenham,et al.  Apolipoprotein E genotyping by one-stage PCR , 1991, The Lancet.

[30]  Monique M. B. Breteler,et al.  Trends in stroke incidence rates and stroke risk factors in Rotterdam, the Netherlands from 1990 to 2008 , 2012, European Journal of Epidemiology.

[31]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[32]  C. Sudlow,et al.  Enlarged perivascular spaces and cerebral small vessel disease , 2013, International journal of stroke : official journal of the International Stroke Society.

[33]  Benjamin F. J. Verhaaren,et al.  Rating Method for Dilated Virchow–Robin Spaces on Magnetic Resonance Imaging , 2013, Stroke.

[34]  Nassir Navab,et al.  QuickNAT: Segmenting MRI Neuroanatomy in 20 seconds , 2018, ArXiv.

[35]  Aad van der Lugt,et al.  DETERMINANTS OF ENLARGED VIRCHOW-ROBIN SPACES: THE UNIVRSE CONSORTIUM , 2014, Alzheimer's & Dementia.

[36]  Andreas Charidimou,et al.  MRI-visible perivascular spaces: relationship to cognition and small vessel disease MRI markers in ischaemic stroke and TIA , 2013, Journal of Neurology, Neurosurgery & Psychiatry.

[37]  A. Hofman,et al.  The Rotterdam Scan Study: design update 2016 and main findings , 2015, European Journal of Epidemiology.

[38]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[39]  Anders M. Dale,et al.  An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest , 2006, NeuroImage.

[40]  R. Sacco,et al.  Perivascular Spaces Are Associated with Atherosclerosis: An Insight from the Northern Manhattan Study , 2013, American Journal of Neuroradiology.

[41]  O. Franco,et al.  The Rotterdam Study: 2018 update on objectives, design and main results , 2017, European Journal of Epidemiology.