MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122177 A) filed by Vellore Institute Oftechnology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'multi-modal ai system for skin disease diagnosis.'
Inventor(s) include Dr. E. S. Madhan; and Ms. S Chopsy Priyasarayu.
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 computer-implemented method for training a multi-modal artificial intelligence system for skin disease classification. The method includes training a Vision Transformer model using dermatological images to generate image-based predictions, training a BERT-based natural language processing model using patient-reported symptom descriptions to generate text-based predictions, and training an ensemble learning module to combine the image-based and text-based predictions to generate unified predictions for skin disease classification. The training data includes dermatological images paired with corresponding symptom descriptions. The system processes dermatological images through patch-based feature extraction and applies self-attention mechanisms to capture global image dependencies, while the BERT-based model tokenizes symptom descriptions and applies bidirectional attention mechanisms to understand contextual relationships between symptom descriptors."
Disclaimer: Curated by HT Syndication.
