Deep Learning Based Blood Cell Identification and Subtype Classification

Precise identification and counting of blood cells, including Red Blood Cells (RBCs), White Blood Cells (WBCs), and Platelets, are essential in medical diagnostics. Conventional approaches depend on human procedures, however current progress in deep learning provides more efficient options. This research introduces a thorough method for analysing blood cells, utilizing advanced neural network-based structures for both counting blood cells and classifying WBCs. The BCCD dataset is used to improve accuracy and overcome obstacles such as low resolution and overlapping cells by applying different preprocessing techniques. An optimised VGG16 model with Keras is used to classify several types of WBCs by including normalization and data augmentation approaches. The results of the experiment demonstrate the efficacy of the proposed methodology, indicating a positive potential for strengthening diagnostic accuracy and efficiency in clinical practice, ultimately improving patient care standards.