Diagnosis of Alzheimer's disease with Sobolev gradient‐based optimization and 3D convolutional neural network. (19th June 2019)

• Record Type: Journal Article
• Authors: Goceri, Evgin
• Is Part Of: International journal for numerical methods in biomedical engineering. Volume 35:Number 7(2019)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-06-19
• Subjects: Alzheimer's disease -- automatic diagnosis -- CNN -- deep learning -- stochastic gradient descent; Biomedical engineering -- Periodicals; Imaging systems in medicine -- Periodicals; Numerical analysis -- Periodicals; Engineering mathematics -- Periodicals; 610.28
• DOI: 10.1002/cnm.3225
• Languages: English
• ISSNs: 2040-7939

Abstract

Abstract: Alzheimer's disease is a neuropsychiatric, progressive, also an irreversible disease. There is not an effective cure for the disease. However, early diagnosis has an important role for treatment planning to delay its progression since the treatments have the most impact at the early stage of the disease. Neuroimages obtained by different imaging techniques (for example, diffusion tensor‐based and magnetic resonance‐based imaging) provide powerful information and help to diagnose the disease. In this work, a deeply supervised and robust method has been developed using three dimensional features to provide objective and accurate diagnosis from magnetic resonance images. The main contributions are (a) a new three dimensional convolutional neural network topology; (b) a new Sobolev gradient‐based optimization with weight values for each decision parameters; (c) application of the proposed topology and optimizer to diagnose Alzheimer's disease; (d) comparisons of the results obtained from the recent techniques that have been implemented for Alzheimer's disease diagnosis. Experimental results and quantitative evaluations indicated that the proposed network model is able to achieve to extract desired features from images and provides automated diagnosis with 98.06% accuracy. Abstract : A new method was developed in this work for automated diagnosis of Alzheimer's disease. The main contributions are: (a) a new three dimensional convolutional neural network topology; (b) a new Sobolev gradient‐based optimization with adaptive weight values; (c) application of the proposed network and optimizer to diagnose Alzheimer's disease; (d) comparison of the results obtained by the state‐of‐the‐art techniques applied to diagnose Alzheimer's disease. Results indicated that the proposed model can achieve feature extraction and diagnosis efficiently (98.06% accuracy).