MUMBAI, India, Sept. 22 -- Intellectual Property India has published a patent application (202611091873 A) filed by Maharishi Markandeshwar Deemed To Be University on July 29, 2026, for A Hybrid Deep Learning-Based System And Method For Kidney Lesion Segmentation And Multi-Class Diagnosis Using Ensemble Neural Networks.
Inventors include Ritu Aggarwal; and Eshaan Aggarwal.
The application for the patent was published on September 18, 2026, under issue no. 38/2026.
Abstract: The present invention relates to a hybrid deep learning-based system and method for automated diagnosis of kidney lesions from medical images. The system comprises an image acquisition module, a preprocessing module, a segmentation module, a feature extraction module, an ensemble prediction engine, a feature fusion module, a disease classification module, and a report generation module. Medical images are preprocessed and segmented to identify kidney lesion regions, followed by extraction of local and global image features. The extracted features are processed using an ensemble of pretrained deep learning models including ZFNet, ENet, SpinalZFNet, and LSTM to classify kidney abnormalities into normal, kidney cyst, kidney stone, and kidney tumour categories. The invention improves lesion detection accuracy, enhances feature representation through ensemble learning, and generates automated diagnostic reports to assist clinicians in early and reliable diagnosis of kidney diseases.
Disclaimer: Curated by HT Syndication.
