MUMBAI, India, Feb. 27 -- Intellectual Property India has published a patent application (202641018318 A) filed by Malla Reddy Engineering College For Women; and Malla Reddy University, Hyderabad, Telangana, on Feb. 18, for 'system and method for explainable skin cancer detection using grad-cam and risk-aware recommendations.'
Inventor(s) include Y. Madhaveelatha; Geetha Reddy Yenna; Venkata Kunapareddy Naganjaneyulu; Vishnu Kumar Mishra; Angadi Swaruparani; K. V. Siva Prasad Reddy; Nadendla Beulah Elizabeth; and L. Surendra.
The application for the patent was published on Feb. 27, under issue no. 09/2026.
According to the abstract released by the Intellectual Property India: "Skin cancer remains one of the most common and life threatening cancers worldwide, underscoring the need for early and accurate diagnosis. The present invention discloses a system and method for explainable skin cancer detection using Convolutional Neural Networks (CNNs) enhanced with Gradient Weighted Class Activation Mapping (Grad CAM) and risk aware recommendations. Dermoscopic images are preprocessed and classified into multiple lesion categories, with Grad CAM generating heatmaps that visually highlight regions influencing predictions. A risk aware module stratifies cases into low, moderate, or high risk levels, providing actionable medical guidance. Diagnostic outputs are compiled into a dynamic report containing the uploaded image, Grad CAM visualization, predicted lesion type, risk level, and recommended next steps. By combining accuracy, interpretability, and usability, the invention delivers a transparent and patient centric diagnostic aid applicable in hospitals, telemedicine platforms, and research laboratories."
Disclaimer: Curated by HT Syndication.
