MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641078623 A) filed by Sr University on June 25, 2026, for A Secure Decentralized Deep Learning Architecture For Early Melanoma Prediction And Cross-Institutional Medical Data Processing.
Inventors include B. Grace; Dr. C Madan Kumar; and Dr. Padmalaya Nayak.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: A secure decentralized deep learning architecture for early melanoma prediction and cross-institutional medical data processing. The architecture integrates medical data acquisition, preprocessing, lesion segmentation, feature extraction, federated learning, secure model aggregation, explainable artificial intelligence, and blockchain-based security mechanisms. Dermatological images and clinical records are analyzed using advanced deep learning models while preserving patient privacy through encrypted federated learning without sharing raw medical data. The system generates accurate melanoma risk assessments, diagnostic recommendations, and interpretable clinical insights. The invention improves diagnostic accuracy, privacy preservation, cybersecurity, interoperability, scalability, and collaborative healthcare intelligence across distributed healthcare institutions.
Disclaimer: Curated by HT Syndication.
