MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202621030429 A) filed by Ahmedabad University, Ahmedabad, Gujarat, on March 13, for 'systems and methods for segmentation of anomaly regions in multi-modal three-dimensional images of an organ.'
Inventor(s) include Jani, Harman Amitkumar; Raval, Mehul Shirishchandra; and Bhalodiya, Jayendra Maganbhai.
The application for the patent was published on May 1, under issue no. 18/2026.
According to the abstract released by the Intellectual Property India: "Disclosed is a system (102) for segmentation of anomaly regions in multi-modal three-dimensional (3D) images of an organ. A preprocessing module (210) receives multi-modal 3D images and applies preprocessing operations. A segmenting module (212) includes a generator sub-module (218) to generate predicted segmentation masks corresponding to anomaly sub-regions, and a discriminator sub-module (220) to classify anomaly sub-regions as real-class or synthetic-class based on the plurality of the multi-modal 3D images and the plurality of predicted segmentation masks. A validating module (214) configured to generate a similarity score based on an overlap between the plurality of predicted segmentation masks and a plurality of predefined ground truth masks, and validate an accuracy of each of the plurality of predicted segmentation masks based on the similarity score. Moreover, a generating module (216) configured to generate one or more segmented anomaly regions by aggregating the plurality of predicted segmentation masks based on the validation."
Disclaimer: Curated by HT Syndication.
