Premium
Cognitive decline prediction using an MRI‐based classifier of arteriolar sclerosis and small vessel atherosclerosis
Author(s) -
Makkinejad Nazanin,
Evia Arnold M,
Tamhane Ashish A,
Bennett David A.,
Schneider Julie A.,
Arfanakis Konstantinos
Publication year - 2020
Publication title -
alzheimer's and dementia
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 6.713
H-Index - 118
eISSN - 1552-5279
pISSN - 1552-5260
DOI - 10.1002/alz.041563
Subject(s) - ex vivo , medicine , pathology , in vivo , hyperintensity , postmortem studies , cohort , magnetic resonance imaging , dementia , leukoaraiosis , cognitive decline , multiple sclerosis , psychology , neuroscience , radiology , biology , psychiatry , disease , microbiology and biotechnology
Background Arteriolar sclerosis and small vessel atherosclerosis are two age‐related neuropathologies that are common in older adults and have been linked to cognitive decline and dementia. Definitive diagnosis of either pathology is only possible at autopsy. The purpose of this work was to develop a model that predicts the presence of arteriolar sclerosis or atherosclerosis based on in‐vivo MRI and basic demographic features. The model was first developed based on ex‐vivo MRI and pathology data from a large community‐based cohort of older adults and was then translated in‐vivo. The performance of the model was assessed both ex‐vivo and in‐vivo. Method Cerebral hemispheres were obtained from 727 participants of the Rush Memory and Aging Project (MAP) and Religious Orders Study (ROS), two longitudinal cohort studies of aging (Figure 1). A brain hemisphere from each participant was imaged ex‐vivo on a clinical 3T MRI scanner, while immersed in 4% formaldehyde solution. Following ex‐vivo MRI, all hemispheres underwent neuropathologic examination by a board‐certified neuropathologist blinded to clinical and imaging findings. The volume of white matter hyperintensities per lobe and regional white matter R 2 values were extracted from the ex‐vivo MRI data and used as features in a logistic regression classifier to predict arteriolar sclerosis or small vessel atherosclerosis. The classifier was then translated to in‐vivo using linear mixed‐effects models, and was tested on in‐vivo 3T MRI of 405 ROS and MAP participants (Figure 2). In‐vivo assessment was performed by testing the association of the classification confidence score with the change in cognition two years after baseline MRI, using Pearson’s correlation. Result The ex‐vivo classifier of arteriolar sclerosis or small vessel atherosclerosis achieved an average area under the receiver operating characteristic curve AUC=0.73 (Figure 3). In‐vivo testing showed that the in‐vivo classification confidence score was associated with a two‐year decline in working memory (p=0.008), semantic memory (p=0.026), and perceptual speed (p=0.036) following baseline in‐vivo MRI. Conclusion A novel MRI‐based classifier was developed for predicting the presence of arteriolar sclerosis or small vessel atherosclerosis in‐vivo. This classifier may have broad clinical implications including refined participant selection and enhanced monitoring of the treatment response in clinical drug and prevention trials.