Pathologist-Like Explanations Unveiled: An Explainable Deep Learning System for White Blood Cell Classification

Despite of achieving remarkable accuracy, the capability of deep learning models for robust prediction of explanations remains largely unexplored in white blood cells (WBCs) classification. In this study, we introduce HemaX, an explainable deep neural network-based model that produces pathologist-like explanations using five attributes: granularity, cytoplasm color, nucleus shape, size relative to red blood cells, and nucleus to cytoplasm ratio (N:C), along with cell classification, localization, and segmentation. HemaX is trained and evaluated on a novel dataset, LeukoX, comprising 467 blood smear images encompassing ten (10) WBC types. The proposed model achieves impressive results, with an average classification accuracy of 81.08% and a Jaccard index of 89.16% for cell localization. HemaX successfully predicts the five explanations with a normalized mean square error of 0.0317 for N:C ratio and over 80% accuracy for the other four attributes. Through expert validations and multiple empirical analyses, we illustrate the robustness of HemaX towards both cell classification and explanation prediction.