MUMBAI, India, Sept. 22 -- Intellectual Property India has published a patent application (202641105500 A) filed by Saveetha Institute Of Medical And Technical Sciences on September 02, 2026, for A Method And Apparatus For Early Diagnosis Of Kidney Tumors Based On Medical Image Processing.

Inventors include Rajagopal K; Dr. V. Sheeja Kumari; Vijayalakshmi R; and Dr Ramya Mohan.

The application for the patent was published on September 18, 2026, under issue no. 38/2026.

Abstract: The present invention relates to a method and apparatus for the early diagnosis of kidney tumors using advanced medical image processing techniques. The invention provides an automated diagnostic framework that analyzes kidney images obtained from medical imaging modalities such as computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound. The system applies image preprocessing techniques including noise filtering, normalization, and contrast enhancement to improve image quality for accurate analysis.The processed images are analyzed using artificial intelligence-based algorithms capable of extracting significant features related to kidney tissue abnormalities. A tumor detection and segmentation module identifies suspicious regions and isolates tumor areas from surrounding kidney tissues. Machine learning models are then used to classify the detected tumors and evaluate their malignancy probability.The invention further incorporates explainable artificial intelligence techniques to provide interpretable diagnostic results for clinicians. A cloud-based infrastructure allows remote access to diagnostic services and enables secure storage and processing of medical imaging data. Additionally, the system includes a selflearning mechanism that continuously improves model performance by learning from newly available clinical data. The proposed method and apparatus enhance early detection of kidney tumors, reduce diagnostic time, and assist healthcare professionals in making accurate clinical decisions

Disclaimer: Curated by HT Syndication.