Intellectual Property India Publishes Patent Application for 'Deepmedscan: 3D CNN And Explainable Ai-Based Multi- Disease Detection In Chest CT Imaging' Filed by Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College; Mrs. S. Sri Nandhini Kowsalya; Mr. Balahariharan S; Mr. Manoj K; Mr. Narendran I; and Mr. Jaya Suriya B S

MUMBAI, India, Feb. 6 -- Intellectual Property India has published a patent application (202641007113 A) filed by Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College; Mrs. S. Sri Nandhini Kowsalya; Mr. Balahariharan S; Mr. Manoj K; Mr. Narendran I; and Mr. Jaya Suriya B S, Chennai, Tamil Nadu, on Jan. 24, for 'deepmedscan: 3d cnn and explainable ai-based multi- disease detection in chest ct imaging.'

Inventor(s) include Mrs. S. Sri Nandhini Kowsalya; Mr. Balahariharan S; Mr. Manoj K; Mr. Narendran I; and Mr. Jaya Suriya B S.

The application for the patent was published on Feb. 6, under issue no. 06/2026.

According to the abstract released by the Intellectual Property India: "The present invention discloses a computer-implemented system and method for automated, accurate, and explainable multi-disease detection from volumetric chest computed tomography (CT) images using three-dimensional convolutional neural networks (3D-CNNs) integrated with explainable artificial intelligence (XAI). The system processes complete three-dimensional chest CT volumes to preserve spatial and anatomical relationships across adjacent slices, enabling improved identification of pulmonary diseases including pneumonia, tuberculosis, pulmonary fibrosis, lung cancer, and viral infections such as COVID-19. The invention includes automated preprocessing of CT data comprising volumetric reconstruction, normalization, noise reduction, contrast enhancement, and lung region isolation to standardize heterogeneous imaging inputs. A 3D-CNN extracts hierarchical volumetric features for multi-class disease classification and generates disease probability scores. An explainable AI module produces visual heatmaps highlighting disease-relevant anatomical regions within the CT volume, enhancing transparency and clinical interpretability of the predictions. The system functions as a clinical decision support tool deployable in hospital, cloud, or telemedicine environments, reducing radiologist workload while improving diagnostic accuracy, reliability, and early disease detection."

Disclaimer: Curated by HT Syndication.