MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541123243 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 6, 2025, for 'hybrid deep learning system for pulmonary embolism detection in ct scans.'
Inventor(s) include Dr. Kalaavathi B; and Mr. Bandaru Akshar.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a system for automated pulmonary embolism detection in computed tomography scans. The system includes a data preprocessing module configured to convert medical imaging files to a format suitable for neural network processing, a convolutional neural network (FIG. 1) configured to extract spatial features from individual computed tomography scan slices, a sequential processing module configured to analyze temporal dependencies across multiple computed tomography scan slices using the extracted spatial features, and a dual classification architecture. The dual classification architecture includes a first classifier configured to generate slice-level predictions for individual computed tomography slices, and a second classifier configured to generate patient-level predictions by aggregating information across multiple slices. The system is configured for multi-label classification of pulmonary embolism characteristics."
Disclaimer: Curated by HT Syndication.
