Alzheimer's Disease Detection Using Extreme Learning Machine, Complex Dual Tree Wavelet Principal Coefficients and Linear Discriminant Analysis

作者：Jha Debesh; Alam Saruar; Pyun Jae Young; Lee Kun Ho; Kwon Goo Rak^*

来源：Journal of Medical Imaging and Health Informatics, 2018, 8(5): 881-890.

DOI：10.1166/jmihi.2018.2381

• Alzheimer's Disease
• Computer-Aided Diagnosis
• Dual-Tree Complex Wavelet Transform
• Principal Component Analysis
• Linear Discriminant Analysis
• Extreme Learning Machine
• Alzheimer's Disease Neuroimaging Initiative
• Open Access Series of Imaging Studies

The early detection and classification of Alzheimer's disease (AD) are important clinical support tasks for medical practitioners in customizing patient treatment programs to have better manage the development and progression of these diseases. Efforts are being made to diagnose these neurodegenerative disorders in the early stages. Efficient early categorization of the AD and mild Cognitive Impairment (MCI) from HC is necessary as prompt preventive care could assist to mitigate risk factors. For analysis and prognosis of disease, Magnetic resonance imaging (MRI). In this paper, we proposed a novel computer-aided diagnosis (CAD) cascade model to discriminate patients with the AD from healthy controls using dual-tree complex wavelet transforms (DTCWT), principal component analysis, linear discriminant analysis, and extreme learning machine (ELM). The proposed method obtained accuracy of 90.26 +/- 1.17, a specificity of 90.20 +/- 1.56 and sensitivity of 90.27 +/- 1.29 on the Alzheimer's disease Neuroimaging Initiative (ADNI) dataset and accuracy of 95.72 +/- 1.54, a sensitivity of 96.59 +/- 2.34 and specificity of 93.03 +/- 1.67 on the Open Access Series of Imaging Studies (OASIS) dataset. The proposed method is effective and superior to the existing models.

• 出版日期2018-6