Intellectual Property India Publishes Patent Application for 'A System And Method For Tuberculosis Diagnosis In Low-Resource Healthcare Settings Using Adaptive Convolutional Neural Networks With Domain Adaptation Techniques' Filed by Graphic Era Hill University, Dehradun; and Graphic Era

MUMBAI, India, Feb. 6 -- Intellectual Property India has published a patent application (202511132248 A) filed by Graphic Era Hill University, Dehradun; and Graphic Era, Dehradun, Uttarakhand, on Dec. 26, 2025, for 'a system and method for tuberculosis diagnosis in low-resource healthcare settings using adaptive convolutional neural networks with domain adaptation techniques.'

Inventor(s) include Rudra Nautiyal; Shubham Mahara; Rahul Kandwal; Dr. Chandradeep Bhatt; and Dr. Anupam Singh.

The application for the patent was published on Feb. 6, under issue no. 06/2026.

According to the abstract released by the Intellectual Property India: "The invention discloses a diagnostic system for tuberculosis in resource-constrained healthcare environments by integrating adaptive convolutional neural networks with domain adaptation techniques. The system comprises a data collection module (10) for acquiring high-quality chest X-ray images and clinical notes, an image degradation module (20) to simulate lower image quality through noise, motion blur, resolution reduction, and uneven brightness, and a clinical notes translation module (30) that uses natural language processing to localize foreign clinical information. A CNN-based model training module (40) implements a dual-stage training process with initial training on high-quality images followed by fine-tuning using domain-adapted data. The evaluation and prediction module (50) assesses model performance via multiple metrics, while the deployment integration module (60) ensures seamless distribution of diagnostic outputs via mobile or cloud-based platforms."

Disclaimer: Curated by HT Syndication.