Prediction of Alzheimer's Disease using Watershed Segmentation Algorithm

According to the WHO, Alzheimer's Disease (AD) is the primary cause of neurodegenerative diseases and a significant global health concern. A Wiener filter is employed for image preprocessing, serving as a non-linear normalization and blur reduction. For AD segmentation Watershed Segmentation divided into multiple layers to improve margin of brain inner and outer layer. Feature selection is performed using the Redundant Discrete Wavelet Transform (RDWT), which effectively removes multi-scale, non-redundant texture features from segmented images, thereby improving the distinction between malignant and benign lesions. CNNs are utilized for feature extraction, distinguishing cancerous from benign regions, while the FCAM facilitates real-time identification and localization of AD areas, ensuring precise classification. Early, mild, moderate, severe, and Mild Cognitive Impairment (MCI) are the stages into which the suggested system divides AD. Experimental results validate that our method achieves an accuracy of 97%, sensitivity of 96%, and specificity of 96%, showcasing its effectiveness Prediction.