A novel conversion prediction method of MCI to AD based on longitudinal dynamic morphological features using ADNI structural MRIs
Name
415_2020_9890_ReferencePDF.pdf
Size
1.34 MB
Format
Adobe PDF
Checksum (MD5)
81920ca106badee91ad0330deeabe102
Author(s)
Guo, Man
Li, Yongchao
Zheng, Weihao
Huang, Keman
Zhou, Li
Hu, Xiping
Yao, Zhijun
Hu, Bin
Date Issued
June 4, 2020
Publisher
Springer Berlin Heidelberg
Version
Author's final manuscript
Abstract
Abstract
Mild cognitive impairment (MCI) is a pre-existing state of Alzheimer's disease (AD). An accurate prediction on the conversion from MCI to AD is of vital clinical significance for potential prevention and treatment of AD. Longitudinal studies received widespread attention for investigating the disease progression, though most studies did not sufficiently utilize the evolution information. In this paper, we proposed a cerebral similarity network with more progression information to predict the conversion from MCI to AD efficiently. First, we defined the new dynamic morphological feature to mine longitudinal information sufficiently. Second, based on the multiple dynamic morphological features the cerebral similarity network was constructed by sparse regression algorithm with optimized parameters to obtain better prediction performance. Then, leave-one-out cross-validation and support vector machine (SVM) were employed for the training and evaluation of the classifiers. The proposed methodology obtained a high accuracy of 92.31% (Sensitivity = 100%, Specificity = 82.86%) in a three-year ahead prediction of MCI to AD conversion. Experiment results suggest the effectiveness of the dynamic morphological feature, serving as a more sensitive biomarker in the prediction of MCI conversion.
MIT Department
Sloan School of Management
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s00415-020-09890-5
