MUMBAI, India, Nov. 2 -- Intellectual Property India has published a patent application (202541040612 A) filed by Dr Dilshad Umar on April 27, 2025, for Artificial Intelligence System For Automated Skeletal Age And Growth Prediction Using Hand-Wrist Radiographs.
Inventors include Dr Dilshad Umar; Dr Subramanya Shetty; Dr Sandeep Shetty; and Dr Mubeena E.
The application for the patent was published on October 30, 2026, under issue no. 44/2026.
Abstract: The present invention relates to an artificial intelligence (AI)-based system for the automated estimation of skeletal maturity stages and growth potential using hand- wrist radiographs. The invention utilizes deep convolutional neural networks (CNNs) to classify digital hand-wrist images into distinct skeletal stages (S1 to S11), based on the Fishman Skeletal Maturity Indicators (FSMI). A particular emphasis is placed on developing and training the AI model using datasets representative of the Indian pediatric and adolescent population, thereby addressing the recognized limitations of existing skeletal assessment systems which are predominantly based on Western demographic data. The system includes an integrated preprocessing module for standardizing radiographic inputs, involving normalization of brightness, contrast, orientation, and resolution, to ensure robust and reproducible predictions across varying image qualities. The CNN model is configured to perform multi-class classification to assign the appropriate skeletal maturity stage, while an auxiliary neural network is designed to predict the estimated growth remaining for the individual. This dual output skeletal stage classification and residual growth estimation enables clinicians to make well-informed decisions regarding the timing and nature of orthopedic and orthodontic interventions. The system is intended for seamless integration into clinical workflows, allowing radiographs to be uploaded through a user-friendly interface that rapidly returns automated predictions. The invention significantly reduces the need for manual interpretation, thereby minimizing inter-observer variability and improving diagnostic reliability. Furthermore, it accelerates clinical decision-making by providing near-instantaneous results, making it suitable for both high-volume hospital settings and specialized orthodontic or pediatric practices. By offering population-specific training, real-time analysis, and growth prediction capabilities, the invention provides a comprehensive, objective, and scalable solution for skeletal maturity assessment. This technology has wide applicability in orthodontics, pediatrics, forensic sciences, and longitudinal growth research. The system enhances the precision of growth-related treatment planning and supports personalized patient care by offering rapid, reliable, and reproducible skeletal age assessments
Disclaimer: Curated by HT Syndication.
