Rider Cat Optimized Alzheimer's Disease and MCI Prediction Using Deep Attention BiLSTM and CRDF

The early detection and accurate diagnosis of Alzheimer's Disease (AD) are critical for effective treatment and management. The study proposes a hybrid method based on deep learning and machine learning techniques for the early prediction of AD and Mild Cognitive Impairment (MCI) from Magnetic Resonance Imaging. The method involves skull stripping, Weiner filtering, segmentation using DABiLSTM, feature extraction using DTCWT, and feature selection using RCO. Finally, the CRDF classifier is used to classify the images into five groups. The proposed model achieved an accuracy of 98.58% on the ADNI 2 dataset, suggesting its potential for more efficient and accurate diagnosis of AD and MCI.