MUMBAI, India, July 30 -- Intellectual Property India has published a patent application (202641088090 A) filed by Vellore Institute Of Technology on July 19, 2026, for System And Method For Early Alzheimer’s Disease Detection Using Explainable Ai With Adaptive Transformer–resnet Feature Fusion And Pso-Optimized Classification.
Inventors include Navamani Tm; and Aryalopa Malla.
The application for the patent was published on July 24, 2026, under issue no. 30/2026.
Abstract: The present invention discloses an Explainable Artificial Intelligence (XAI)-based system and method for early detection and multi-stage classification of Alzheimer’s Disease using MRI brain images. The system comprises a pre-processing module configured to perform skull stripping, noise reduction, normalization, and region-of- interest localization, followed by a hybrid feature extraction module integrating a Residual Neural Network (ResNet) and a Vision Transformer (ViT) to capture complementary local and global neuroimaging features. An adaptive feature fusion mechanism generates discriminative feature representations that are processed by a Particle Swarm Optimization-based Support Vector Machine (PSO-SVM) classifier for optimized disease-stage classification. The system categorizes MRI images into No Impairment, Very Mild Impairment, Mild Impairment, and Moderate Impairment stages. Further, Grad-CAM and SHAP-based explainability modules provide visual and feature-level interpretations of predictions. The invention generates an automated clinical decision-support report comprising disease stage, confidence score, affected brain regions, and diagnostic explanations.
Disclaimer: Curated by HT Syndication.
