Intellectual Property India Publishes Patent Application for 'Automated Brain Tumor Detection And Segmentation System Using Densenet121 And U-Net Architectures' Filed by Vellore Institute Of Technology

MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122159 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'automated brain tumor detection and segmentation system using densenet121 and u-net architectures.'

Inventor(s) include Dr. Madhu Viswanatham V; Mr. Edupuganti Shanmuk Sri Srujan Chowdary; Mr. Settipalli Bramara Pranav; and Mr. Paleru Reshwanth Chowdary.

The application for the patent was published on Jan. 2, under issue no. 01/2026.

According to the abstract released by the Intellectual Property India: "The present disclosure provides an automated brain tumor detection and segmentation system comprising a data preprocessing module configured to receive magnetic resonance imaging (MRI) scans and apply preprocessing operations to generate standardized input images, a DenseNet121 classification network (10) configured to receive the standardized input images and classify each image as tumor-present or tumor-absent using densely connected convolutional layers with feature reuse capabilities, a U-Net segmentation network (20) comprising an encoder-decoder architecture with skip connections configured to receive images classified as tumor-present from the DenseNet121 classification network and generate pixel-wise segmentation masks delineating tumor boundaries, a performance evaluation module (30) configured to calculate classification metrics for the DenseNet121 classification network and segmentation metrics for the U-Net segmentation network, and wherein the DenseNet121 classification network and the U-Net segmentation network are integrated in a unified processing pipeline."

Disclaimer: Curated by HT Syndication.