MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641061394 A) filed by G. Pullaiah College Of Engineering And Technology, Kurnool, Andhra Pradesh, on May 14, for 'system and method for real-time edge-ai medical image segmentation using lightweight convolutional neural networks.'
Inventor(s) include Dr M. Janardhan; N. Mahendra; N. Somanna; and Dr P. Suman Prakash.
The application for the patent was published on May 29, under issue no. 22/2026.
According to the abstract released by the Intellectual Property India: "The invention discloses a real-time edge-AI system for medical image segmentation using lightweight convolutional neural networks (CNNs). The system is designed for deployment on resource-constrained devices such as portable scanners, embedded diagnostic platforms, and point-of-care units. It comprises an image acquisition module, a preprocessing module, a lightweight CNN segmentation engine, and a visualization and reporting module. The CNN engine employs depthwise separable convolutions, quantization-aware training, and pruning techniques to achieve high segmentation accuracy with minimal computational overhead. The system enables real-time inference, delivering segmented medical images within milliseconds, thereby supporting time-critical applications such as surgical guidance, emergency diagnostics, and mobile healthcare. By eliminating reliance on cloud infrastructure, the invention enhances patient data privacy, reduces operational costs, and ensures portability. Its modular design allows seamless integration with existing medical imaging workflows. The invention addresses limitations of prior art by balancing accuracy, efficiency, and security, thereby enabling widespread adoption of edge-based medical AI solutions in diverse clinical environments."
Disclaimer: Curated by HT Syndication.
