MUMBAI, India, Feb. 13 -- Intellectual Property India has published a patent application (202641008770 A) filed by Pes College Of Engineering, Mandya, Karnataka, on Jan. 28, for 'hardware-integrated deep neural network system for automated breast cancer detection.'
Inventor(s) include Dr. Veena M.
The application for the patent was published on Feb. 13, under issue no. 07/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to a hardware-integrated medical device for automated detection of breast cancer using deep neural networks. The system comprises an image acquisition interface for receiving digital mammograms, tomosynthesis images or ultrasound frames, a hardware-implemented pre-processing module that performs geometry and intensity normalisation and artefact reduction, and a deep neural network inference engine running on dedicated accelerator hardware. The accelerator accesses memory storing pre-trained network parameters and produces lesion-probability information in the form of heat maps, region proposals and case-level risk scores. A system controller coordinates high-speed data transfer between modules, enforces safety policies and drives a medical-grade display that overlays analysis results on the original images. Structured diagnostic data are written back to hospital PACS/RIS systems over secure DICOM links. Hardware-level watchdogs, encryption and firmware verification provide reliability and cybersecurity. By binding deep learning analysis to specific processing hardware, the device delivers real-time clinical decision support."
Disclaimer: Curated by HT Syndication.
