Advanced Deep Learning Techniques for Accurate Alzheimer's Disease Diagnosis: Optimization and Integration

Early detection of the Alzheimer's disease (AD) treatment is required to stop its progression. The doctors can begin their preventive treatment with the earliest possible detection. They insist that Alzheimer's is detected sooner and must be fast, accurate process. As a result, the focus of this work is on developing an automated framework to identify whether or not Alzheimer's disease exists using sagittal magnetic resonance images(MRI), which are seldom used in such tasks. This paper uses the convolutional neural network (CNN) as well as long short-term memory (LSTM)) to detect and categorise early-stage Alzheimier disease. MRI images are first passed to the pre-processing operation for removing noise in an image using median filtering technique. This will help in segmenting the image using binary segmentation after applying median filter. After that the classification model CNN and LSTM is executed where classifying process performed in better manner. And The bayesian optimization used here to improve quality of parameter. The performance matrices of accuracy, precision, recall and F-measure are used to justify the results obtained. Obtained results are discussed together with the state-of-the-art techniques. This relative study was obvious proofs the proposed model is suitable for irdentifying and clasiification of Alzheimer's disease.