Enhancing Blood Subtype Recognition Through Convolutional Neural Networks: Binary and Multi-Class Approaches

In order to help with disease and condition diagnosis, this research focuses on accurately classifying blood cell subtypes using Convolutional Neural Networks (CNNs). The principal aim is to develop a comprehensive and effective automated classification system for blood cell subtypes, which will aid medical practitioners in making prompt and precise diagnoses. The created CNN architecture links distinct features to particular blood cell subtypes by extracting them from visual data. By addressing both binary and multi-class classification scenarios, the study improves the CNN model's capacity to distinguish variations in blood cell properties. Based on metrics like accuracy, precision, recall, and F1-score, the proposed CNN architecture is reliable and has a great deal of potential for real-world medical applications.