In this study, we report a label-free bone marrow white blood cell classification framework that captures the three-dimensional (3D) refractive index (RI) distributions of individual cells and analyzes with deep learning. Without using labeling or staining processes, 3D RI distributions of individual white blood cells were exploited for accurate profiling of their subtypes. Powered by deep learning, our method used the high-dimensional information of the WBC RI tomogram voxels and achieved high accuracy. The results show >99 % accuracy for the binary classification of myeloids and lymphoids and >96 % accuracy for the four-type classification of B, T lymphocytes, monocytes, and myelocytes. Furthermore, the feature learning of our approach was visualized via an unsupervised dimension reduction technique. We envision that this framework can be integrated into existing workflows for blood cell investigation, thereby providing cost-effective and rapid diagnosis of hematologic malignancy.