Intellectual Property India Publishes Patent Application for 'A Starfish Optimization Algorithm Tuned Deep Learning System For Automated Detection And Classification Of Pancreatic Ductal Adenocarcinoma Using Medical Imaging Data' Filed by Koneru Lakshmaiah Education Foundation

MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641048610 A) filed by Koneru Lakshmaiah Education Foundation, Hyderabad, Telangana, on April 16, for 'a starfish optimization algorithm tuned deep learning system for automated detection and classification of pancreatic ductal adenocarcinoma using medical imaging data.'

Inventor(s) include Lynnet Alice Ezra; and Dr. G. Anna Lakshmi.

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: "The present invention discloses an intelligent system for automated detection and classification of Pancreatic Ductal Adenocarcinoma (PDAC) using optimized deep learning techniques. The system integrates advanced image processing and deep learning models with a Starfish Optimization Algorithm (SFOA) for hyperparameter tuning. Medical imaging data, particularly Computed Tomography (CT) images, are subjected to pre-processing steps including normalization, contrast enhancement, resizing, and dataset balancing. Feature extraction and classification are performed using multiple pre-trained convolutional neural network models such as MobileNetV3, EfficientNetB0, VGG16, and ResNet50V2. The SFOA algorithm enhances model performance by optimizing parameters such as learning rate, dropout, and kernel size. The proposed system achieves improved accuracy and reliability in detecting pancreatic tumors, thereby reducing diagnostic errors. The invention provides a robust, scalable, and efficient solution for early-stage cancer detection, supporting clinical decision-making and improving patient survival outcomes."

Disclaimer: Curated by HT Syndication.