ALZHEIMER'S DISEASE DETECTION USING DEEP LEARNING

Computer Engineering

Alzheimer's disease (AD) is a progressive neurodegenerative disorder that poses a significant challenge to public health. Early and accurate detection of AD is crucial for effective intervention and management. This study proposes a novel approach for Alzheimer's detection utilizing deep learning techniques applied to medical imaging data. The research focuses on the development of a deep neural network architecture tailored for the analysis of neuroimaging data, such as magnetic resonance imaging (MRI) and positron emission tomography (PET) scans. The proposed model leverages the power of convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to capture spatial and temporal patterns in brain images, respectively. To enhance the robustness and generalization of the model, transfer learning techniques are employed, utilizing pre-trained neural networks on large-scale datasets. The dataset used for training and evaluation comprises a diverse collection of images from individuals with varying degrees of cognitive impairment, including those with preclinical symptoms and healthy controls. The evaluation of the proposed deep learning model is conducted on a separate test dataset, demonstrating promising results in terms of sensitivity, specificity, and overall accuracy. Additionally, the model's interpretability is explored through visualization techniques to identify key regions and features contributing to the classification.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.