MUMBAI, India, Sept. 7 -- Intellectual Property India has published a patent application (202641100199 A) filed by Saveetha Institute Of Medical And Technical Sciences on August 19, 2026, for Bloodcelbuddy.
Inventors include Gowrabathuni Mohit Tej; Dr. Sathish Kumar; and Dr Ramya Mohan.
The application for the patent was published on September 04, 2026, under issue no. 36/2026.
Abstract: The present invention relates to a system and method for automated analysis of white blood cells (WBCs) using artificial intelligence integrated. into a mobile application, herein referred to as BloodCelBuddy. This work was carried out as a medical project under the guidance of Dr. Swetha. P ( Department of Pathology), who provided the clinical requirements and datasets necessary for development. Traditional manual counting of WBCs is time-consuming, error-prone, and dependent on skilled laboratory personnel. The disclosed invention provides a hybrid solution comprising a manual counter module and an AI-powered image analysis module, enabling both cross-verification and reliable classification of WBCs into five categories: Neutrophils, Lymphocytes, Monocytes, Eosinophils, and Basophils. The system architecture includes an Android-based frontend developed in Java, a Python Flask backend, and a machine learning model trained on datasets refined through Roboflow. The application allows secure user authentication, real-time image input, and automatic generation of WBC reports with percentage distributions. Experimental validation achieved high accuracy (86%) and close agreement (-87.5%) with manual counts, demonstrating clinical relevance. The invention reduces human effort, minimizes diagnostic errors, and delivers rapid blood cell analysis directly through a smartphone platform. Future scalability includes integration with additional blood parameters, cloud-based analysis, and compatibility with hospital information systems, thereby offering a novel and practical advancement in digital hematology diagnostics.
Disclaimer: Curated by HT Syndication.
