MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202641043447 A) filed by Mrs. Priyadharshini C; Mrs. Sowmiya M; Mr. Sethupathy K B; Mrs. Durkadevi M; Mrs. Saranya R; and Mrs. Sowmiya P, Salem, Tamil Nadu, on April 5, for 'ai-powered imaging system for tumor detection and classification.'

Inventor(s) include Mrs. Priyadharshini C; Mrs. Sowmiya M; Mr. Sethupathy K B; Mrs. Durkadevi M; Mrs. Saranya R; and Mrs. Sowmiya P.

The application for the patent was published on April 17, under issue no. 16/2026.

According to the abstract released by the Intellectual Property India: "Early and accurate tumor detection plays a critical role in improving patient prognosis, treatment planning, and overall survival rates in oncology. Medical imaging modalities such as Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) are routinely used for tumor diagnosis; however, manual interpretation of these images is time-consuming and subject to inter-observer variability. To address these challenges, this research proposes an AI-powered imaging system based on deep convolutional neural networks (CNNs) for automated tumor detection and classification. The developed system is designed to learn discriminative spatial and textural features directly from medical images, enabling effective differentiation between benign and malignant tumors. The model was fully implemented and evaluated using a publicly available dataset comprising MRI and CT scans, which was further augmented to address class imbalance and enhance generalization capability. Advanced preprocessing techniques, including intensity normalization and data augmentation, were applied to improve robustness against variations in imaging conditions. The system achieved an overall classification accuracy of 95.2% in distinguishing benign from malignant tumors, along with high precision and recall values, indicating reliable and consistent diagnostic performance. These findings highlight the effectiveness of deep learning in capturing complex tumor characteristics that are often difficult to model using handcrafted features."

Disclaimer: Curated by HT Syndication.