BiLSTM Classifier-Driven Framework for Early Detection and Classification of Alzheimer’s Disease from MRI Imaging

In a medical and technological stage of development, medical images are a big part of everyday lives. Alzheimer’s disease (AD) is the most common form of dementia, a neurological condition that primarily affects elderly people and has an uncertain etiologic. The first clinical sign of AD is selective memory impairment, and while some of its symptoms can be reduced with current medications, there is currently no cure. Magnetic resonance imaging (MRI) of the brain is used to assess patients who have AD. This paper proposes an innovative approach for the detection of Alzheimer’s disease from MRI images, incorporating advanced techniques. Initially, an Adaptive Median Filter (AMF) is applied to the MRI images to remove noise, ensuring high quality input data. Next, the images are segmented using K means clustering, allowing for the separation of relevant regions associated with AD. Features are then extracted from the segmented images using the Scale Invariant Feature Transform (SIFT), capturing key patterns for further analysis. Finally, a Bidirectional Long Short Term Memory (BiLSTM) framework is proposed as a hybrid model to enhance the classification of AD images, leveraging both forward and backward temporal information to overcome challenges in MRI analysis. The assessment of proposed work using python software reveals that the proposed framework with BiLSTM classifier ranks with improved accuracy of 97.8 % when compared to the other techniques.