Intellectual Property India Publishes Patent Application for 'AI-Powered Bone Fracture Detection System With Vision Transformer And Cnn Deep Learning Models For Medical Imaging' Filed by Easwari Engineering College; and Srm Institute Of Science And Technology

MUMBAI, India, Feb. 27 -- Intellectual Property India has published a patent application (202641017321 A) filed by Easwari Engineering College; and Srm Institute Of Science And Technology, Chennai, Tamil Nadu, on Feb. 17, for 'ai-powered bone fracture detection system with vision transformer and cnn deep learning models for medical imaging.'

Inventor(s) include Mugilan M V; S S Priyadharshini; Jershin A J; and Dr. G. Vishnu Priya.

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: "This invention relates to an automated deep learning-based system for bone fracture detection and analysis designed to enhance diagnostic accuracy and reduce evaluation time in emergency and orthopedic care. The system employs a hybrid Vision Transformer (ViT-base-patch16-224) and Convolutional Neural Network architecture to capture global spatial relationships and local structural features from X-ray and CT images. Implemented using PyTorch and optimized with Human Evolutionary Optimization Algorithms (HEOA), the model delivers robust and high-confidence fracture detection across various bone types. UNet++ with ResNet34 enables precise fracture segmentation, while YOLOv11n supports real-time fracture localization. Grad-CAM visualization improves interpretability by highlighting critical decision regions. An integrated Streamlit interface provides real-time results, confidence scores, and automated diagnostic reports, supporting clinicians with fast, accurate, and explainable fracture assessment."

Disclaimer: Curated by HT Syndication.