Automatic Early Detection of Alzheimer‟s Disease based on 2D-VMD and Deep Convolutional Neural Network
Bhanja Kishor Swain1, Susanta Kumar Rout2, Renu Sharma3
1Bhanja Kishor Swain, Department of Electrical Engineering, Siksha „O‟ Anusandhan Deemed to be University, Bhubaneswar, India.
2Susanta Kumar Rout*, Department of Electrical and Electronics Engineering, Siksha „O‟ Anusandhan Deemed to be University, Bhubaneswar, India.
3Dr. Renu Sharma, Department of Electrical Engineering, Siksha „O‟ Anusandhan Deemed to be University, Bhubaneswar, India.
Manuscript received on September 23, 2019. | Revised Manuscript received on October 15, 2019. | Manuscript published on October 30, 2019. | PP: 6964-6969 | Volume-9 Issue-1, October 2019 | Retrieval Number: A2134109119/2019©BEIESP | DOI: 10.35940/ijeat.A2134.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper, the classification of normal controls (NC), very mild cognitive impairment and the early stage of Alzheimer’s disease (AD) known as mild cognitive impairment (MCI) from magnetic resonance imaging (MRI) is proposed, based on the two dimensional variational mode decomposition (2D-VMD) and deep convolutional neural network (DCNN). The 2D-VMD is applied to decompose the MRI scans into a discrete number of band limited intrinsic mode functions (BLIMFs). The automatic feature extraction, selection and optimization are performed using the proposed DCNN. The classification accuracy and learning speed of the 2D-VMD-DCNN method are compared with DCNN by taking the MRI data as input. The superior classification accuracy of the proposed 2D-VMD-DCNN method over DCNN method as well as other recently introduced prevalent methods is the major advantage for analyzing the biomedical images in the field of health care.
Keywords: Alzheimer’s disease (AD), Magnetic resonance imaging (MRI), Deep convolutional neural network (DCNN), Two-dimensional variational mode decomposition (2D-VMD).