MUMBAI, India, Aug. 24 -- Intellectual Property India has published a patent application (202641097864 A) filed by Dr. K. Arun Kumar; Dr. Thirumal G.; G. Sri Lavanya; Dr. Kammula Sunil Kumar; and Dr. Nur Alom Talukdar on August 13, 2026, for A System And Method For Quantum-Enhanced Brain Tumor Prediction Using Adaptive Hybrid Classical-Quantum Deep Learning And Explainable Artificial Intelligence.

Inventors include Dr. K. Arun Kumar; Dr. Thirumal G.; G. Sri Lavanya; Dr. Kammula Sunil Kumar; and Dr. Nur Alom Talukdar.

The application for the patent was published on August 21, 2026, under issue no. 34/2026.

Abstract: The present invention provides a system and method for quantum-enhanced brain tumor prediction using adaptive hybrid classical-quantum deep learning and explainable artificial intelligence. Brain MRI images are preprocessed and supplied to a classical deep learning feature extraction module for generating hierarchical feature representations. An adaptive feature selection and routing module evaluates the representations and selectively directs features through a classical computational pathway, quantum computational pathway, or hybrid pathway. Selected features are dimensionally reduced and encoded into quantum states before processing through one or more parameterized quantum circuits to generate quantum-derived representations. The quantum-derived and classical representations are combined using a hybrid feature fusion module and supplied to a prediction module for generating a brain tumor prediction and associated confidence value. An explainable artificial intelligence module generates an interpretable representation identifying image regions and feature contributions associated with the prediction. An adaptive optimization module further optimizes the classical, routing, quantum, fusion, and prediction parameters. The invention provides selective quantum processing of relevant deep features together with interpretable prediction for computer-aided brain tumor analysis.

Disclaimer: Curated by HT Syndication.