A novel conversion prediction method of MCI to AD based on longitudinal dynamic morphological features using ADNI struct
- PDF / 3,227,932 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 99 Downloads / 168 Views
ORIGINAL COMMUNICATION
A novel conversion prediction method of MCI to AD based on longitudinal dynamic morphological features using ADNI structural MRIs Man Guo1 · Yongchao Li1 · Weihao Zheng2 · Keman Huang3 · Li Zhou4 · Xiping Hu1,5 · Zhijun Yao1 · Bin Hu1 Received: 18 December 2019 / Revised: 3 May 2020 / Accepted: 5 May 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
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, leaveone-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. Keywords Mild cognitive impairment · Dynamic morphological features · Elastic network · Magnetic resonance imaging
Introduction
Electronic supplementary material The online version of this article (https://doi.org/10.1007/s00415-020-09890-5) contains supplementary material, which is available to authorized users. * Xiping Hu [email protected]; [email protected] * Zhijun Yao [email protected] * Bin Hu [email protected] 1
College of Information Science and Engineering, Lanzhou University, Lanzhou, China
2
College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China
3
MIT Sloan School of Management, Cambridge, US
4
National University of Defense Technology, Changsha, China
5
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
Mild cognitive impairment (MCI) is an intermediate state between normal aging and dementia [1]. Studies have shown that MCI subjects tend to progress to probable Alzheimer’s disease (AD) at a rate of 10–15% each year [2]. MCI can be divided into two subtypes, converting MCI and non-converting MCI. The MCI converter (MCI-C) indicates the group of patients who is likely to progress to AD in a short period of time, but the MCI non converter (MCI-NC) remains stable for a certain period of time, with smaller risk of conversion to AD than the fo
Data Loading...
