Objective and Impact Statement. We propose a rapid and accurate blood cell identification method exploiting deep learning and label-free refractive index (RI) tomography. Our computational approach that fully utilizes tomographic information of bone marrow (BM) white blood cell (WBC) enables us to not only classify the blood cells with deep learning but also quantitatively study their morphological and biochemical properties for hematology research. Introduction. Conventional methods for examining blood cells, such as blood smear analysis by medical professionals and fluorescence-activated cell sorting, require significant time, costs, and domain knowledge that could affect test results. While label-free imaging techniques that use a specimen’s intrinsic contrast (e.g., multiphoton and Raman microscopy) have been used to characterize blood cells, their imaging procedures and instrumentations are relatively time-consuming and complex. Methods. The RI tomograms of the BM WBCs are acquired via Mach-Zehnder interferometer-based tomographic microscope and classified by a 3D convolutional neural network. We test our deep learning classifier for the four types of bone marrow WBC collected from healthy donors (n=10): monocyte, myelocyte, B lymphocyte, and T lymphocyte. The quantitative parameters of WBC are directly obtained from the tomograms. Results. Our results show >99% accuracy for the binary classification of myeloids and lymphoids and >96% accuracy for the four-type classification of B and T lymphocytes, monocyte, and myelocytes. The feature learning capability of our approach is visualized via an unsupervised dimension reduction technique. Conclusion. We envision that the proposed cell classification framework can be easily integrated into existing blood cell investigation workflows, providing cost-effective and rapid diagnosis for hematologic malignancy.

Background Minimal residual disease (MRD) is an important prognostic factor for evaluating a deeper treatment response in patients with multiple myeloma (MM). We evaluated the clinical utility of next-generation flow (NGF)-based MRD assessment in a heterogeneous MM patient population. Methods Patients with suspected morphological remission after or during MM treatment were prospectively enrolled. In total, 108 bone marrow samples from 90 patients were analyzed using NGF-based MRD assessment according to the EuroFlow protocol, and progression-free survival (PFS) was evaluated according to the International Myeloma Working Group response status, cytogenetic risk, and MRD status. Results The overall MRD-positive rate was 31.5% (34/108 samples), and MRD-positive patients showed a lower PFS than MRD-negative patients ( P =0.005). MRD-positive patients showed inferior PFS than MRD-negative in patients with stringent complete remission (sCR)/complete remission ( P =0.014) and high-risk cytogenetic abnormalities ( P =0.016). MRD was assessed twice in 18 patients with a median interval of 12 months. Sustained MRD negativity was only observed in patients with sustained sCR, and their PFS was superior to that of patients who were not MRD-negative ( P =0.035). Conclusions Clinical application of NGF-based MRD assessment can provide valuable information for predicting disease progression in patients with MM in remission, including those with high-risk cytogenetic abnormalities.