Extracting and summarizing white matter hyperintensities using supervised segmentation methods in Alzheimer's disease risk and aging studies

• Published in: Human brain mapping Vol. 35; no. 8; pp. 4219 - 4235
• Main Authors: Ithapu, Vamsi, Singh, Vikas, Lindner, Christopher, Austin, Benjamin P., Hinrichs, Chris, Carlsson, Cynthia M., Bendlin, Barbara B., Johnson, Sterling C.
• Format: Journal Article
• Language: English
• Published: New York, NY Blackwell Publishing Ltd 01.08.2014; Wiley-Liss; John Wiley & Sons, Inc; John Wiley and Sons Inc
• Subjects: Aged; Aged, 80 and over; Aging - pathology; Alzheimer Disease - pathology; Artificial Intelligence; Biological and medical sciences; Brain - pathology; Cognitive Dysfunction - pathology; Cohort Studies; Degenerative and inherited degenerative diseases of the nervous system. Leukodystrophies. Prion diseases; Female; Humans; Investigative techniques, diagnostic techniques (general aspects); Linear Models; Magnetic Resonance Imaging - methods; Male; Medical sciences; Middle Aged; Nervous system; Neurology; Radiodiagnosis. Nmr imagery. Nmr spectrometry; random forests; Risk; segmentation; Signal Processing, Computer-Assisted; Support Vector Machine; support vector machines; White Matter - pathology; white matter hyperintensities; Nervous system diseases; Senescence; support vector machines; Radiodiagnosis; Segmentation; Image processing; Alzheimer disease; white matter hyperintensities; random forests; White matter; Cerebral disorder; Central nervous system disease; Risk factor; Degenerative disease; Vector; Hyperintensity; segmentation
• ISSN: 1065-9471; 1097-0193; 1097-0193
• DOI: 10.1002/hbm.22472

Precise detection and quantification of white matter hyperintensities (WMH) observed in T2‐weighted Fluid Attenuated Inversion Recovery (FLAIR) Magnetic Resonance Images (MRI) is of substantial interest in aging, and age‐related neurological disorders such as Alzheimer's disease (AD). This is mainly because WMH may reflect co‐morbid neural injury or cerebral vascular disease burden. WMH in the older population may be small, diffuse, and irregular in shape, and sufficiently heterogeneous within and across subjects. Here, we pose hyperintensity detection as a supervised inference problem and adapt two learning models, specifically, Support Vector Machines and Random Forests, for this task. Using texture features engineered by texton filter banks, we provide a suite of effective segmentation methods for this problem. Through extensive evaluations on healthy middle‐aged and older adults who vary in AD risk, we show that our methods are reliable and robust in segmenting hyperintense regions. A measure of hyperintensity accumulation, referred to as normalized effective WMH volume, is shown to be associated with dementia in older adults and parental family history in cognitively normal subjects. We provide an open source library for hyperintensity detection and accumulation (interfaced with existing neuroimaging tools), that can be adapted for segmentation problems in other neuroimaging studies. Hum Brain Mapp 35:4219–4235, 2014. © 2014 Wiley Periodicals, Inc.