Deep CNN Based Multi-class Classification of Alzheimer’s Disease using MRI

Abstract

In the recent years, deep learning has gained huge fame in solving problems from various fields including medical image analysis. This thesis proposes a deep convolutional neural network based pipeline for the diagnosis of Alzheimer’s disease and its stages using magnetic resonance imaging (MRI) scans. Alzheimer’s disease causes permanent damage to the brain cells associated with memory and thinking skills. The diagnosis of Alzheimer’s in elderly people is quite difficult and requires a highly discriminative feature representation for classification due to similar brain patterns and pixel intensities. Deep learning techniques are capable of learning such representations from data. In this thesis, a 4-way classifier is implemented to classify Alzheimer’s (AD), mild cognitive impairment (MCI), late mild cognitive impairment (LMCI) and healthy persons. Experiments are performed using ADNI dataset on a high performance graphical processing unit based system and new state-of-the-art results are obtained for multiclass classification of the disease. Results are examined for two state-of-the-art models i.e. googLeNet and ResNet-152. An optimized and dedicated model is also proposed which is based on incorporating residual learning in shallow networks. Experiments are performed in three phases with both learning from scratch and fine-tuning techniques. The acquired results outperformed other techniques for both binary and multiclass classification. The proposed technique results in a prediction accuracy of 99.9% by using proposed optimized model, which is a significant increase in accuracy as compared to the previous studies and clearly reveals the effectiveness of the proposed method.