MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202611057150 A) filed by Sharda University on May 05, 2026, for Skin Disease Prediction And Visual Diagnostic Interpretation Using Explainable Artificial Intelligence.
Inventors include Jatin Kumar; and Dr. Kanika Singla.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: The present invention discloses a method for automated skin disease prediction based on explainable artificial intelligence. The method comprises receiving an input, pre-processing the image by resizing, normalization, and enhancement, and extracting hierarchical features using a trained convolutional neural network. A probability distribution across predefined skin disease classes is generated to determine a predicted disease label and confidence score. An explainable artificial intelligence module executes one or more explanation techniques including local feature attribution, Shapley-value contribution analysis, and gradient-based activation mapping. The output from the one or more explanation techniques are combined to generate a unified visual diagnostic interpretation overlay, which is transmitted along with the predicted label and confidence score for display on a communication device (102). FIG. 3
Disclaimer: Curated by HT Syndication.
