脳 сосудистые пространства (PVS)の拡大におけるAIベースの定量化と視覚的評価の比較分析：MESAコホート
Morgan F Torres1, Sokratis Charisis1, Tanweer Rashid1
1From the Neuroimage Analytics Laboratory (NAL) and the Biggs Institute Neuroimaging Core (BINC), Glenn Biggs Institute for Alzheimer's & Neurodegenerative Diseases (M.F.T., S.C., T.R., S.R.B., S.S., M.H.), and the Department of Neurology (S.C., S.S.), University of Texas Health Science Center at San Antonio, San Antonio, TX, USA; the Department of Radiology (K.D.H., C.T.W.), and the Department of Internal Medicine (J.E.T., T.M.H.), Wake Forest School of Medicine, Winston-Salem, NC, USA; the Department of Radiology (J.B.W., I.M.N., C.D.) and the Center for Biomedical Image Computing and Analytics (I.M.N., C.D.), Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA; the Department of Neurology (R.R.), School of Medicine, Boston University, Boston, MA, USA; the Vanderbilt Memory and Alzheimer's Center (T.H.), Vanderbilt University Medical Center, Nashville, TN, USA; and the Department of Epidemiology and Cardiovascular Health Research Unit (S.R.H.), University of Washington, Seattle, WA, USA.
Background And Purpose:
Enlarged perivascular spaces (PVS) are fluid-filled spaces surrounding small cerebral vessels. Current PVS research has been limited by the absence of efficient and scalable quantification tools. We compared visual ratings versus AI-based quantification in identifying associations of PVS with vascular risk factors and cognitive performance.
Materials And Methods:
This cross-sectional study included 235 participants from the Multi-Ethnic Study of Atherosclerosis who had undergone brain MRI and had available both visual ratings and AI-derived PVS quantification. Visual ratings were performed by an expert neuroradiologist (KDH) using a semiquantitative scale. AI-derived counts were based on a fully-automated deep learning algorithm. Visual and AI-derived counts were grouped into four a priori-defined anatomic locations: basal ganglia, frontoparietal cerebrum, midbrain, and cerebellum. The relationships of PVS counts with demographic characteristics, vascular risk factors, and global and domain-specific cognitive scores were examined using ordinal logistic regression (for ordinal categorical outcomes) and linear regression (for continuous outcomes) models.
Results:
Mean age (standard deviation) was 72.1 (6.8) years; 95 (40%) participants were men; and 126 (54%) self-reported as Black. Means (SD) of AIderived regional PVS counts were 63.7 (24.6) for basal ganglia, 414.9 (167.5) for frontoparietal cerebrum, and 9.8 (4.4) for midbrain. On visual ratings, the most prevalent count category for each region was 11-20 for basal ganglia (40%), 21-40 (31%) for frontoparietal cerebrum, and 1-5 (83%) for midbrain. For basal ganglia PVS, while both methods were associated with older age and White race/ethnicity, AI-derived counts exhibited additional associations with higher systolic blood pressure (β, 0.20; 95% CI, 0.05-0.36) and diabetes (β, 11.51; 95% CI, 3.48-19.55), as well as poorer global cognition (β, -0.012; 95% CI, -0.023 to -0.0004), delayed memory (β, -0.005; 95% CI, -0.010 to -0.0005) and attention/processing speed (β, -0.005; 95% CI, -0.009 to -0.001) cognitive performance.
Conclusions:
In this cross-sectional study, AI-derived PVS quantification was more sensitive in detecting associations with vascular risk factors and cognitive outcomes than traditional visual ratings. AI-based quantification may aid in the analysis of large-scale epidemiological data, advancing PVS research.
Abbreviations:
PVS＝ perivascular spaces; MRI＝ magnetic resonance imaging; SVD＝ small vessel disease; MESA＝ Multi-Ethnic Study of Atherosclerosis; AI＝ artificial intelligence; FLAIR＝ fluid-attenuated inversion recovery; ROI＝ regions of interest; WHR＝ waist-to-hip ratio; SBP＝ systolic blood pressure; β＝ unstandardized beta coefficient; CI＝ confidence interval; OR＝ odds ratio.
