MUMBAI, India, Jan. 8 -- Intellectual Property India has published a patent application (202511104255 A) filed by Lovely Professional University, Phagwara, Punjab, on Oct. 29, 2025, for 'system for classifying pulmonary diseases from chest x-ray images.'
Inventor(s) include Dr. Suresh Mani; Rishi Chopra; Dr. Megha Mehta; and Dr. Rajesh Verma.
The application for the patent was published on Dec. 12, under issue no. 50/2025.
According to the abstract released by the Intellectual Property India: "A system for classifying pulmonary diseases from chest X-ray images 101 comprising a lightweight Multiscale Fusion Network, configured to extract multiscale semantic features from input images, a secondary feature extraction 103 network comprising a ResNet50 architecture to generate complementary feature representations, Fusion Block comprising a self-calibrated convolution module, configured to enhance receptive field adaptability and refine contextual features, and an Attention Feature Fusion mechanism to selectively weight and combine multiscale feature maps, an activation module comprising an MFReLU activation function, configured to reduce memory access time during inference, and a fusion module 104, configured to adaptively combine features produced by the Multiscale Fusion Network and ResNet50 network, the system classifies chest X-ray images 101 into pulmonary disease categories including pneumonia, tuberculosis, and COVID-19, providing high classification 105 accuracy, improved processing efficiency, and robust performance across diverse datasets, suitable for real-time and resource-constrained environments."
Disclaimer: Curated by HT Syndication.