Tidarat Katsanook. White blood cells classification using machine learning and deep learning. Master's Degree(Data Science). Chiang Mai University. Library. : Chiang Mai University, 2025.
White blood cells classification using machine learning and deep learning
Abstract:
White blood cell classification plays a critical role in diagnosing and managing hematological and immune-related diseases. This study investigates the application of machine learning and deep learning techniques to automate and enhance the accuracy of WBC classification. Utilizing a comprehensive dataset comprising 50,000 labeled 2D images obtained from the University of North British Columbia, we developed robust classification models capable of distinguishing between four principal WBC types: eosinophils, lymphocytes, monocytes, and neutrophils. Our methodology includes image preprocessing, data augmentation, and feature extraction to enhance model performance. We implement classical machine learning models Decision Tree, Multinomial Logistic Regression, and Random Forest as well as deep learning methods based on Convolutional Neural Networks. Model evaluation is rigorously performed using standard metrics, including accuracy, precision, recall, and F1-score, to guide architecture optimization and validate performance.