MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641076497 A) filed by Cvr College Of Engineering on June 20, 2026, for Deep Learning System For Medical Image Segmentation.
Inventor includes Dr. N. Subhash Chandra.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: The current invention relates to a system and method for automated medical image segmentation using an optimized M-Net deep learning architecture coupled with nature-based hyperparameter optimization techniques. Artificial Hummingbird Optimization, Hippopotamus Optimization, and Monarch Butterfly Optimization are some of the nature-based optimization techniques used by the current invention to automatically set up the most optimum values of learning rate, number of epochs and batch size during training. Preprocessed medical images are fed to optimized M-Net network for the automatic segmentation of anatomical structures and pathologies. In addition to enhancing segmentation accuracy and Dice Similarity Coefficient, the current invention ensures fast convergence and robustness while minimizing hyperparameter optimization effort.
Disclaimer: Curated by HT Syndication.
