MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202531129819 A) filed by National Institute Of Technology, Jamshedpur, Jharkhand, on Dec. 22, 2025, for 'a radiographic osteoporosis screening and classification system for early detection of bone density deterioration using knee x-ray images.'

Inventor(s) include Lipika Dinda; Jitesh Pradhan; Manish Raj; and B Ramachandra Reddy.

The application for the patent was published on Jan. 9, under issue no. 02/2026.

According to the abstract released by the Intellectual Property India: "The present invention relates to a radiographic osteoporosis screening and classification system is disclosed for early detection of bone density deterioration using standard knee X-ray images. the system receives digital radiographs and performs automated preprocessing including square padding, intensity normalization, noise reduction, and resolution standardization. a geometric segmentation module establishes a radiograph center, constructs a circumscribed hexagonal grid, and generates primary triangular sectors through a whirling-triangle radial subdivision; each sector is further partitioned according to the Golden Ratio to produce anatomically localized sub-triangular regions. from these regions, a handcrafted feature extraction module computes a compact set of discriminative descriptors including texture, statistical, frequency-domain, structural, and bone-quality measures. an attention-based neural classification module refines the resulting modular feature vector using adaptive feature weighting within a multilayer perceptron architecture to generate multiclass outputs representing Normal, Osteopenic, or Osteoporotic conditions. the system provides interpretable, lightweight, and anatomically informed screening capability and can operate solely on standard radiographic imagery without the need for bone densitometry equipment. a corresponding method for multiclass osteoporosis screening using knee radiographs is also described. to 6."

Disclaimer: Curated by HT Syndication.