MUMBAI, India, March 13 -- Intellectual Property India has published a patent application (202641024386 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on March 1, for 'a medical image processing system for early-stage detection of diabetic neuropathy from foot ulcer images.'
Inventor(s) include Dr. Muthunagai S U; Nivitha K; and Srisha G S.
The application for the patent was published on March 13, under issue no. 11/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to a medical image processing system and method for early-stage detection of diabetic neuropathy using foot ulcer images. The 5 system comprises an image acquisition module for obtaining RGB ulcer images, a preprocessing module for resizing, normalization, and augmentation, and a convolutional neural network (CNN) feature extractor for identifying local pathological characteristics such as lesion texture, boundaries, deformation, and color variations. A refined spatio-temporal attention module applies spatial 10 attention to emphasize clinically significant ulcer regions, channel attention to prioritize neuropathy-related tissue features, and multi-scale feature fusion to preserve detailed and high-level representations. The refined features are further processed by a Vision Transformer encoder to capture long-range spatial dependencies and generate global contextual representations. A classification 15 module produces a diagnostic output indicating the presence or absence of diabetic neuropathy, along with a confidence score for clinical decision support. The hybrid CNN-transformer architecture improves diagnostic accuracy, reduces variability in assessment, and supports deployment in telemedicine platforms for remote, non-invasive neuropathy screening."
Disclaimer: Curated by HT Syndication.
