MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202641115610 A) filed by Jayaraju Gaddala on September 26, 2026, for Privacy-Preserving Explainable Ai System For Real-Time Skin Lesion Classification On Raspberry Pi 5.
Inventors include Pothula. Hima Bindu; Dr. D. Uma Devi; Dr. Satyakeerthigorripati; Dr. G. J. Sunny Deol; Balakrishna Bangaru; and Akhila. Ravi.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: A privacy-preserving explainable artificial intelligence system classifies skin lesion images in real time on a Raspberry Pi 5. A camera or dermoscopic imaging device connected to the Raspberry Pi 5 supplies the lesion image. The Raspberry Pi 5 checks the image quality, preprocesses the image and runs a compact classification model that assigns the lesion to one of a set of predetermined categories, with a confidence value where available. An explainability module marks the image regions that contributed to the result, for example as a heatmap or overlay. During normal operation the captured image and intermediate data stay on the device, so identifiable images need not be sent to an external server. A local user interface shows the result, confidence value and explanation together. Because acquisition, classification and explanation run on one device at the point of capture, the principal workflow does not need a continuous network connection.
Disclaimer: Curated by HT Syndication.
