Proceedings of the First International Conference on Information Science and Electronic Technology

3D-DWT Improves Prediction of AD and MCI

Authors
Shuihua Wang, Yi Chen, Yudong Zhang, Zhengchao Dong, Elizabeth Lee, Preetha Phillips
Corresponding Author
Shuihua Wang
Available Online March 2015.
DOI
https://doi.org/10.2991/iset-15.2015.16How to use a DOI?
Keywords
Discrete wavelet transform, Magnetic resonance imaging, Multiclass kernel support vector machine, Cross validation, Alzheimer's disease, Mild cognitive impairment
Abstract
In order to predict subjects with Alzheimer's disease (AD) and mild cognitive impairment (MCI) from normal elder controls (NC) more accurately, we compared two different kinds of discrete wavelet transform (DWT) based feature extraction techniques: multi-slice 2D-DWT and 3D-DWT. The dataset contained the magnetic resonance (MR) images of 178 subjects consisting of 97 NCs, 57 MCIs, and 24 ADs. We constructed two multiclass kernel support vector machine (MKSVM) classifiers based on multislice 2D-DWT features and 3D-DWT features, respectively. 5-fold cross validation was employed to obtain the out-of-sample estimate. Each classifier runs 10 times. Welch’s t-test showed that the mean of the overall accuracy by 3D-DWT was higher than that of multislice 2D-DWT, and the difference was statistically significant (p=0.0146).
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Proceedings
First International Conference on Information Science and Electronic Technology (ISET 2015)
Part of series
Advances in Computer Science Research
Publication Date
March 2015
ISBN
978-94-62520-50-9
DOI
https://doi.org/10.2991/iset-15.2015.16How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Shuihua Wang
AU  - Yi Chen
AU  - Yudong Zhang
AU  - Zhengchao Dong
AU  - Elizabeth Lee
AU  - Preetha Phillips
PY  - 2015/03
DA  - 2015/03
TI  - 3D-DWT Improves Prediction of AD and MCI
BT  - First International Conference on Information Science and Electronic Technology (ISET 2015)
PB  - Atlantis Press
UR  - https://doi.org/10.2991/iset-15.2015.16
DO  - https://doi.org/10.2991/iset-15.2015.16
ID  - Wang2015/03
ER  -