A hybrid deep learning architectures and feature extraction techniques for alzheimer disease recognition.

Abstract

Alzheimer's disease (AD) is one of the common forms of dementia and is tremendously increasing throughout the world. There are many biomarkers currently available to detect the AD progression. In AD, brain cell death occurs, leading to memory loss, impaired calculation ability, and difficulty in remembering recent events. Early detection of AD is crucial for managing the symptoms and providing effective medical intervention. AD symptoms usually develop gradually and become worse over time, and interfere with daily activities. Hence, this research proposes the Fuzzy scoring based ResNet-Convolutional Neural Network (FS-ResNet CNN) to discriminate AD patients having AD, Mild Cognitive Impairment (MCI), and cognitively normal (CN) using a hybrid deep learning architecture to leverage more complete spatial information from the ADNI data. Initially, the pre-processing is carried out using the z-score normalization. To reduce the time complexity and to select the prominent features, the Adaptive Grey Wolf Optimization Algorithm (AGWOA), harnessing the swarm intelligence, has been proposed. Finally, the Hybrid Deep Learning Architecture is applied for the classification of AD. Specifically, the proposed method introduces a novel method known as the Fuzzy Scoring to optimize the network performance. Furthermore, the proposed FS-ResNet CNN model is computationally efficient, less sensitive to noise, and efficiently saves memory. Experimental results demonstrate the effectiveness of the proposed method on the ADNI dataset, showing high classification accuracy of 97.89%, surpassing the other state-of-the-art methods.