Intellectual Property India Publishes Patent Application for 'Hybrid Classical Quantum Machine Learning System For Multi Class Lung Disease Detection And Pneumonia Severity Classification Using Chest X-Ray Images' Filed by Seshadri Rao Gudlavalleru Engineering College; Dr. T. Nagamani; Bollu Snigdha; Dongara Yaswanth; Garikipati Tripura; and Goli Prabhas

MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641047814 A) filed by Seshadri Rao Gudlavalleru Engineering College; Dr. T. Nagamani; Bollu Snigdha; Dongara Yaswanth; Garikipati Tripura; and Goli Prabhas, Gudlavalleru, Andhra Pradesh, on April 15, for 'hybrid classical quantum machine learning system for multi class lung disease detection and pneumonia severity classification using chest x-ray images.'

Inventor(s) include Seshadri Rao Gudlavalleru Engineering College; Dr. T. Nagamani; Bollu Snigdha; Dongara Yaswanth; Garikipati Tripura; and Goli Prabhas.

The application for the patent was published on May 1, under issue no. 18/2026.

According to the abstract released by the Intellectual Property India: "This project proposal presents an innovative hybrid classical-quantum machine learning framework for automated multi-class lung disease detection and conditional pneumonia severity classification using chest X-ray images. Addressing the global challenge of respiratory diseases such as pneumonia, tuberculosis, and COVID-19-where rapid and accurate diagnosis is critical - the project aims to develop a scalable diagnostic system that integrates EfficientNet-B0-based deep feature extraction with a Variational Quantum Circuit (VQC) for quantum-enhanced feature transformation. The proposed two-stage architecture first performs multi-class disease classification across five categories: Normal, Viral Pneumonia, Bacterial Pneumonia, Tuberculosis, and COVID-19. Upon detection of pneumonia, a second stage activates region-based severity analysis to classify cases into Mild, Moderate, or Severe levels. This conditional mechanism improves computational efficiency while aligning with clinical decision workflows. The system provides a scalable, automated, and clinically deployable diagnostic framework that combines classical deep learning with quantum-enhanced learning to support improved medical image analysis and structured healthcare decision-making."

Disclaimer: Curated by HT Syndication.