MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541113026 A) filed by Bhavithira V; Dharshan K J; Jersil G M; Karthick B; and Abishek M, Coimbatore, Tamil Nadu, on Nov. 18, 2025, for 'optimal shiprouting system: a digital solution for efficient and sustainable maritime navigation.'

Inventor(s) include Bhavithira V; Dharshan K J; Jersil G M; Karthick B; and Abishek M.

The application for the patent was published on Jan. 9, under issue no. 02/2026.

According to the abstract released by the Intellectual Property India: "Pneumonia is a severe respiratory infection that poses a major global health concern, especially among children and the elderly. Traditional diagnostic approaches rely on manual interpretation of chest X-rays by radiologists, which can be time-consuming, subjective, and prone to human error. This project introduces an artificial intelligence-based solution for automated pneumonia detection using deep learning and computer vision techniques. A Convolutional Neural Network (CNN) model based on the VGG19 architecture is employed to classify chest X-ray images into two categories: Pneumonia and Normal. The model is trained and fine-tuned on a publicly available Kaggle data-set, with pre-processing techniques such as normalization and data augmentation applied to enhance model performance and generalization. The proposed model achieves an impressive test accuracy of approximately 95%, proving its reliability in identifying pneumonia-affected lungs. To improve model transparency and interpretability, Grad-CAM (Gradient-weighted Class Activation Mapping) is used to visualize the specific lung regions that influenced the modef s decision. Furthermore, the project includes the deployment of the trained model through a Streamlit-based web application, enabling users to upload chest X-ray images and instantly receive predictions along with heat-map visualizations. This integration of Al and healthcare aims to assist radiologists in early diagnosis, reduce diagnostic delays, and improve clinical decision-making efficiency. By combining high accuracy, explainability, and accessibility, the system highlights the transformative potential of deep learning in medical diagnostics and represents a significant step toward practical Al-assisted healthcare solutions."

Disclaimer: Curated by HT Syndication.