1 January 2021 in BME Frontiers
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 ( ): 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.
1 September 2022 in Annals of Laboratory Medicine
Hyun-Young Kim, M.D., In Young Yoo, M.D., Dae Jin Lim, M.T., Hee-Jin Kim, M.D., Sun-Hee Kim, M.D., Sang Eun Yoon, M.D., Seok Jin Kim, M.D., Duck Cho, M.D., and Kihyun Kim, M.D.. Ann Lab Med 2022;42:558-65. https://doi.org/10.3343/alm.2022.42.5.558
1 January 2026 in Journal of Korean Medical Science
Park MS, et al. J Korean Med Sci. 2025 Sep;41:e5. https://doi.org/10.3346/jkms.2026.41.e5
1 September 2020 in Annals of Laboratory Medicine
Epidemiological studies of monoclonal B-cell lymphocytosis (MBL) have been conducted in limited geographical regions. Little is known about the prevalence of MBL in Asia. We investigated the prevalence and immunophenotypic characteristics of MBL in Koreans who had idiopathic lymphocytosis (lymphocyte count >4.0x 10(9)/L) and were >= 40 years of age. A total of 105 leftover peripheral blood samples met these criteria among those from 73,727 healthy individuals who visited the Health Promotion Center, Samsung Medical Center, Korea, from June 2018 to August 2019. The samples were analyzed using eight-color flow cytometry with the following monoclonal antibodies: CD45, CD5, CD10, CD19, CD20, CD23, and kappa and lambda light chains. The overall prevalence of MBL in the study population was 2.9% (3/105); there was one case of chronic lymphocytic leukemia (CLL)-like MBL (CD5(+)CD23(-)), one case of atypical CLL-like MBL (CD5(+)CD23(-)), and one case of CD5(-) MBL with a lambda restriction pattern. This is the first study on the MBL prevalence in an East Asian population, and it reveals a relatively low prevalence of MBL in healthy Korean individuals with lymphocytosis.