MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641049590 A) filed by Koneru Lakshmaiah Education Foundation, Hyderabad, Telangana, on April 18, for 'an innovative deep learning approach for skin disease detection.'
Inventor(s) include Soujenya Voggu; Dr. Shadab Siddiqui; and Dr. A. Ramakrishna.
The application for the patent was published on May 1, under issue no. 18/2026.
According to the abstract released by the Intellectual Property India: "The present invention discloses an innovative system and method for automated detection and classification of skin diseases using a deep learning-based multi-modal framework. The system integrates clinical and dermoscopic images with patient-specific metadata to enhance diagnostic accuracy and reliability. A hybrid architecture comprising a convolutional neural network and a transformer-based model is employed for effective feature extraction and contextual analysis, while an attention-based fusion mechanism combines multiple data modalities. The invention further incorporates a skin tone adaptive normalization layer to ensure consistent performance across diverse populations and an explainable artificial intelligence module to provide visual and interpretable diagnostic outputs. Additionally, a federated learning framework is utilized to enable privacy-preserving model training. The system supports real-time deployment on mobile and cloud platforms, thereby facilitating accessible, scalable, and accurate skin disease diagnosis."
Disclaimer: Curated by HT Syndication.
