Title: SliceNet-AD: slice selection-based convolution neural network model for classification of Alzheimer's disease

Authors: N. Vinutha; Santosh Pattar; P. Deepa Shenoy; K.R. Venugopal

Addresses: Department of Computer Science and Engineering, University Visvesvaraya College of Engineering, Bangalore University, Bengaluru, India ' Department of Computer Science and Engineering, University Visvesvaraya College of Engineering, Bangalore University, Bengaluru, India ' Department of Computer Science and Engineering, University Visvesvaraya College of Engineering, Bangalore University, Bengaluru, India ' Bangalore University, Bengaluru, India

Abstract: In recent days, a rapid advancement in imaging technologies has tremendously increased the collection of images in the medical field. These emerging technologies have also led the researchers to focus on computer aided diagnosis (CAD) using efficient machine learning and deep learning techniques. In this paper, we have proposed a framework for binary and multiclass classification of Alzheimer's disease (AD) using three-dimensional structural magnetic resonance images (sMRI) and clinical scores from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. The collected images are subjected to pre-processing using FMRIB Software Library. After pre-processing, the three dimensional grey matter tissues are obtained as an output from tissue segmentation comprises of many two dimensional slices. But, processing and training all the slices requires a lot of computational time. Therefore our aim is to employ convolutional neural network only on the significant slices and also to report the performance of the model. Experimental results prove that the proposed slice selection classification framework achieves better performance when fused with clinical scores.

Keywords: Alzheimer's disease; convolutional neural network; CNN; entropy; slice selection; structural magnetic resonance imaging; sMRI; computer aided diagnosis; CAD; Alzheimer's Disease Neuroimaging Initiative; ADNI.

DOI: 10.1504/IJIM.2021.115771

International Journal of Image Mining, 2021 Vol.4 No.1, pp.69 - 97

Received: 23 Aug 2020
Accepted: 06 Dec 2020
Published online: 21 Jun 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article