Meeting Banner
Abstract #2053

Improved Identification of MCI Converters and Non-Converters using Voxel-Based Morphometry and Low-Rank Plus Sparse Matrix Decomposition

Xiuyuan Wang1,2, Steven H. Baete1,2, Ying-Chia Lin1,2, Ricardo Otazo1, and Fernando E. Boada1,2

1Center for Advanced Imaging Innovation and Research (CAI2R), NYU School of Medicine, New York, NY, United States, 2Center for Biomedical Imaging, Department of Radiology, NYU School of Medicine, New York, NY, United States

Early identification of mild cognitive impairment (MCI) patients presents significant challenges due to mild symptoms and low sensitivity of the algorithms proposed for MCI identification. In this study we employed low-rank plus sparse (L+S) matrix decomposition for identifying gray matter volume differences in bilateral hippocampi between MCI patients who converted to Alzheimer’s disease within 18 months and MCI patients who did not. The L+S decomposition identifies features that are common across subjects while minimizing the influence of individual variabilities and outliers. Sensitivity and accuracy are greatly improved and voxel-wise differences that couldn’t be assessed by previous analyses are also identified.

This abstract and the presentation materials are available to members only; a login is required.

Join Here