Alzheimer's disease classification using hybrid loss Psi-Net segmentation and a new hybrid network model.

Alzheimer's disease (AD) is a type of brain disorder that is becoming more prevalent worldwide. It is a progressive and irreversible condition that gradually impairs memory and cognitive abilities, eventually making it difficult to perform even basic tasks. While the symptoms may not be noticeable until the disease has progressed significantly, early diagnosis can help slow its progression. Unfortunately, there is currently no cure for AD, and although medications and therapies can help manage its symptoms, they cannot reverse the disease. This article proposes a SpinalNet-Rider Neural Network (Spinal-RideNN) algorithm for AD classification. The Spinal-RideNN is formed by the SpinalNet and Rider Neural Network (RideNN) mixture. Here, an input brain image is forwarded to the preprocessing stage. The preprocessing is done by the Kalman filter and Rate of Interest (ROI) extraction. Then, the image segmentation is accomplished by Psi-Net. Later, feature extraction is done for extracting the Speeded Up Robust Features (SURF), the Haralick features, and the Local Binary Pattern (LBP). Eventually, the AD classification is done by using Spinal-RideNN. Furthermore, the Spinal-RideNN is evaluated by using evaluation measures like sensitivity, specificity, accuracy, Positive Predictive Value (PPV) as well as Negative Predictive Value (NPV) and it obtained the best values of 0.948, 0.928, and 0.909correspondingly.