Shape-Attributes of Brain Structures as Biomarkers for Alzheimer’s Disease
Name
Shape-attributes.pdf
Size
735.33 KB
Format
Adobe PDF
Checksum (MD5)
e032e71c1e0140f461061c9e782eefcd
Author(s)
Glozman, Tanya
Solomon, Justin
Pestilli, Franco
Guibas, Leonidas
Date Issued
January 2017
Journal
Journal of Alzheimer's Disease
Publisher
IOS Press
Citation
Glozman, Tanya et al. "Shape-Attributes of Brain Structures as Biomarkers for Alzheimer’s Disease." Journal of Alzheimer's Disease 56, 1 (January 2017): 287-295 © 2017 IOS Press and the authors
Version
Final published version
Abstract
We describe a fully automatic framework for classification of two types of dementia based on the differences in the shape of brain structures. We consider Alzheimer’s disease (AD), mild cognitive impairment of individuals who converted to AD within 18 months (MCIc), and normal controls (NC). Our approach uses statistical learning and a feature space consisting of projection-based shape descriptors, allowing for canonical representation of brain regions. Our framework automatically identifies the structures most affected by the disease. We evaluate our results by comparing to other methods using a standardized data set of 375 adults available from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Our framework is sensitive to identifying the onset of Alzheimer’s disease, achieving up to 88.13% accuracy in classifying MCIc versus NC, outperforming previous methods.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-NonCommercial 4.0 International
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.3233/jad-160900
