Intellectual Property India Publishes Patent Application for A Quantum-Enhanced Deep Learning Framework For Breast Cancer Prediction, Classification And Diagnostic Decision Support

MUMBAI, India, Sept. 22 -- Intellectual Property India has published a patent application (202641107109 A) filed by Dr. Ghazala Sultan, Noida Institute Of Engineering And Technology; Dr. Etikala Aruna, Tkr College Of Engineering & Technology; G. Bruhaspathi, St. Martin'S Engineering College; Dr. Preeti Khanwalkar, Dayananda Sagar College Of Engineering; and E. Soumya, Koneru Lakshmaiah Education Foundation on September 06, 2026, for A Quantum-Enhanced Deep Learning Framework For Breast Cancer Prediction, Classification And Diagnostic Decision Support.

Inventors include Dr. Ghazala Sultan, Noida Institute Of Engineering And Technology; Dr. Etikala Aruna, Tkr College Of Engineering & Technology; G. Bruhaspathi, St. Martin'S Engineering College; Dr. Preeti Khanwalkar, Dayananda Sagar College Of Engineering; and E. Soumya, Koneru Lakshmaiah Education Foundation.

The application for the patent was published on September 18, 2026, under issue no. 38/2026.

Abstract: A Quantum-Enhanced Deep Learning Framework for Breast Cancer Prediction, Classification and Diagnostic Decision Support is disclosed. The framework receives breast cancer-related imaging and/or clinical data and performs preprocessing, deep feature extraction, multimodal feature fusion, and feature optimization. The optimized feature representation is encoded into quantum states using a quantum feature encoding mechanism and processed through a parameterized quantum circuit. Measurement outputs from the quantum circuit are supplied to a hybrid quantum-classical classification module for generating breast cancer predictions and/or risk classifications. A confidence estimation module determines prediction confidence, while an explainability module identifies influential image regions and/or clinical features associated with the prediction. A diagnostic decision-support module combines the prediction, confidence, and explanatory information to generate a clinician- oriented output. The framework provides an integrated classical-quantum computational architecture for breast cancer analysis and supports diagnostic decision-making through quantum-enhanced feature processing and explainable artificial intelligence.

Disclaimer: Curated by HT Syndication.