Platelet Detection System Using Image

Abstract

Accurate identification and counting of platelets are essential for diagnosing and monitoring various medical conditions, including thrombocytopenia and thrombocytosis. Traditional manual counting methods, such as using a hemocytometer, are time-consuming, prone to human error, and require skilled professionals. To address these issues, this study proposes an automated Platelet Area System that uses image processing and machine learning techniques. The system analyzes high-resolution blood smear images from the BCCD dataset, which are preprocessed to enhance quality and isolate platelets from other blood cells. Leveraging YOLOv8 a state-of-the-art object detection model the system accurately detects and counts platelets, ensuring reliable and precise results. Furthermore, the framework is integrated into an intuitive web interface, allowing healthcare professionals and researchers to upload images and receive automated platelet counts in real time. This solution offers a rapid, versatile, and efficient alternative to manual counting, improving diagnostic accuracy while reducing labor and time requirements. Ultimately, by automating platelet detection, the framework holds the potential to significantly enhance healthcare workflows and support better clinical decision-making.