Improved Alzheimer's Detection with a Modified Multi-Focus Attention Mechanism using Computational Techniques

Abstract: Alzheimer disease is a common type of dementia which shrinks the brain cells and eventually causes death. It disturbs the life quality of patients with progressive symptoms such as memory loss, conversation, etc. It is vital to identify the disease earlier to get precise treatment. Besides, it is significant to locate the forms of Alzheimer's such as AD (Alzheimer Disease), CN (Cognitive Normal), and MCI (Mild Cognitive Impairment). Traditionally, manual screening of Alzheimer's is carried out by qualified physicians, which is a time-consuming mechanism, expensive, and prone to human error. To resolve the issue, several conventional researches attempted to attain better efficiency in the Alzheimer classification but were limited through accuracy, speed, and inefficacy. To address the challenge of classifying Alzheimer's in its various forms (AD, CN, and MCI), the proposed system utilizes the Modified Multi-Focus Attention and Hierarchical Scalerated Convolutional Neural Network (HSCN) mechanisms within the ResNet-101 model. The system undergoes testing with custom datasets such as OASIS, AIBL, and ADNI, and the classification performance is assessed using efficiency factors to gauge the effectiveness of the research. Background: Alzheimer is a century-old disease, still there is no concrete method to diagnose the disease. Many time diagnosis takes large time and the patient has been referred to many doctors. Objective: The objective of the study is to create a prediction model using deep learning which will be able to classify the patient into three different classes, CN, MCI,, and AD. The model is trained on hetero dataset, ADNI, AIBL,, and OASIS. Method: For the deep learning model, we have used Resnet 101 in which the convolution layer is changed to Hierarchical Scalerated CNN and the bottleneck layer is changed to modified multi-focus attention. The preprocessing of the image is also done as the initial step of process. Results: Our model accuracy is more than 99% for all three datasets used for the research. Conclusion: The model is trained for MRI from different datasets, the same model should be used for PET scans for Alzheimer's diagnosis, and the same model can be used to diagnose other disease patients which will be very useful for mankind.