Identification of cell morphology parameters from automatic hematology analyzers to predict the peripheral blood CD34-positive cell count after mobilization

The Application of Morphogo in the Detection of Megakaryocytes from Bone Marrow Digital Images with Convolutional Neural Networks

The evaluation of megakaryocytes is an important part of the work up on bone marrow smear examination. It has significance in the differential diagnosis, therapeutic efficacy assessment, and predication of prognosis of many hematologic diseases. The process of manual identification of megakaryocytes are tedious and lack of reproducibility; therefore, a reliable method of automated megakaryocytic identification is urgently needed. Three hundred and thirty-three bone marrow aspirate smears were digitized by Morphogo system. Pathologists annotated megakaryocytes on the digital images of marrow smears are applied to construct a large dataset for testing the system's predictive performance. Subsequently, we obtained megakaryocyte count and classification for each sample by different methods (system-automated analysis, system-assisted analysis, and microscopic examination) to study the correlation between different counting and classification methods. Morphogo system localized cells likely to be megakaryocytes on digital smears, which were later annotated by pathologists and the system, respectively. The system showed outstanding performance in identifying megakaryocytes in bone marrow smears with high sensitivity (96.57%) and specificity (89.71%). The overall correlation between the different methods was confirmed the high consistency (r ≥ 0.7218, R² ≥ 0.5211) with microscopic examination in classifying megakaryocytes. Morphogo system was proved as a reliable screen tool for analyzing megakaryocytes. The application of Morphogo system shows promises to advance the automation and standardization of bone marrow smear examination.

Correlation between peripheral blood automated hematopoietic progenitor cell counts and flow cytometric CD34+ cell counts differs according to diagnosis in patients undergoing autologous peripheral blood stem cell transplantation

BACKGROUND

An automated hematopoietic progenitor cell count measurement in Sysmex XN analyzer (XN-HPC) has been developed to assist flow cytometry CD34⁺ cell count measurement, which requires technical expertise and a long turnaround time. Here, we evaluated the correlation between XN-HPC count and flow cytometric CD34⁺ cell count in pre-harvest peripheral blood (PB) samples from patients undergoing autologous peripheral blood stem cell (PBSC) transplantation according to diagnosis and investigated the possible cause of the decreased correlation in plasma cell neoplasm patients.

MATERIALS AND METHODS

We retrospectively included 399 patient data that had matched PB XN-HPC count and CD34⁺ cell count of PB and apheresis product from Samsung Medical Center (SMC) and the Hematopoietic Stem Cell (HSC) registry. We assessed the diagnostic accuracy and the potential cutoff values of XN-HPC count for predicting adequate PBSC collection.

RESULTS

The PB XN-HPC count was 1.6 and 1.3-fold higher than the CD34⁺ cell count in SMC (25.0 vs 15.9/μl) and the HSC registry (20.0 vs 15.2/μl), respectively. Overall the correlation between the PB XN-HPC and CD34⁺ cell count was moderate (SMC, r = 0.71; HSC registry, r = 0.66). A significant proportional and systemic bias with overestimation of XN-HPC count were noted in the plasma cell neoplasm patients in both SMC and the HSC registry. However, no significant difference in correlation was observed according to myeloma-related laboratory parameters in plasma cell neoplasm patients.

CONCLUSION

Our results suggest that XN-HPC count should be interpreted cautiously in cancer patients undergoing autologous PBSC transplantation, especially in those with plasma cell neoplasm.

Diagnostic and prognostic utility of WBC counts and cell population data in patients with COVID-19

Introduction

Early diagnosis and identification of potential critical cases for timely treatment are crucial for COVID‐19 patients. The aim of this study was to analyze the diagnostic and prognostic implications of WBC and cell population data (CPD) abnormalities related to COVID‐19 at disease onset.

Methods

Baseline WBC counts and CPD data were analyzed in one hundred COVID‐19 patients presenting to emergency department and subsequently discharged (n=49), admitted (n=51) or deceased (n=22), and in 47 healthy subjects.

Results

Lymphopenia and eosinopenia were observed in all COVID‐19 patients, with more intensity in the admitted and deceased groups, that also presented increased WBC and neutrophil counts. On CPD analysis, COVID‐19 was associated with increased volume of neutrophils, lymphocytes, and monocytes, whereas conductivity was decreased for neutrophils and increased for lymphocytes. The ROC curve analysis showed good performance for lymphocyte counts in predicting COVID‐19 diagnosis (AUC=0.858), for neutrophil counts in predicting admission for COVID‐19 (AUC=0.744) and for monocytes volume in predicting COVID‐19 diagnosis (AUC=0.837).

Conclusion

WBC counts and CPD parameters at disease onset in COVID‐19 patients can improve diagnostic characterization and aid in the discrimination between severe and nonsevere presentations.

Assessment of haematopoietic progenitor cell counting with the Sysmex® XN-1000 to guide timing of apheresis of peripheral blood stem cells

BACKGROUND

Successful peripheral blood stem cell (PBSC) collection depends on optimal timing of apheresis, as usually determined by flow cytometry CD34-positive (⁺) cell count in peripheral blood (PB). Since this method is costly and labour-intensive, we evaluated the use of the Hematopoietic Progenitor Cell count programme on a Sysmex^® XN haematologic analyser (XN-HPC) as a rapid and inexpensive alternative for predicting CD34⁺ cell count in PB samples.

MATERIALS AND METHODS

Haematopoietic progenitor cell and CD34⁺ cell counts were compared using 273 PB samples collected from 78 healthy donors and 72 patients who underwent PBSC transplantation. We assessed the effectiveness of the XN-HPC in safely predicting pre-harvest CD34⁺ counts. The most efficient cut-off values of XNHPC were identified. We also evaluated the imprecision (coefficient of variation, CV) and functional sensitivity.

RESULTS

Imprecision of the XN-HPC count was <6.3% on daily measurement of three levels of quality control material. Functional sensitivity was 8.9×10⁶/L. A cut-off value of ≥62×10⁶/L XN-HPC for multiple myeloma (MM) patients and ≥30×10⁶/L for all other subjects had both 100% specificity and 100% positive predictive value for identifying samples with CD34⁺ cells ≥20×10⁶/L. An XN-HPC threshold of <13×10⁶/L identified preharvest CD34⁺ cell count <10×10⁶/L with 100% sensitivity and 100% negative predictive value.

DISCUSSION

The XN-HPC is a fast, easy and inexpensive test that can safely improve apheresis workflow thus possibly replacing other more expensive CD34 counts currently performed and promoting optimal timing of PBSC collection.

Rapid prediction of stem cell mobilization using volume and conductivity data from automated hematology analyzers

BACKGROUND

Rapid analytics to predict circulating hematopoietic stem cells are valuable for optimal management of mobilization, particularly for the use of newer and costly mobilization agents such as plerixafor.

STUDY DESIGN AND METHODS

We used stepwise, linear multiple regression modeling applied to cell population data collected by routine hematology analyzers (Beckman Coulter DxH 800) on patients undergoing autologous stem cell collection (n = 131). Beta coefficients were used to derive a formula for a stem cell index (SCI). We then tested the correlation of SCI with stem cell counts and performance of the SCI as a predictor of poor mobilization with external validation in a separate cohort (n = 183).

RESULTS

The SCI correlated strongly with CD34 counts by flow cytometry (r = 0.8372 in the development cohort, r = 0.8332 in the external validation cohort) and compares favorably with other rapid stem cell enumerating technologies. In the external validation cohort, the SCI performed well as a predictor (receiver operating characteristic area under the curve, 0.9336) of poor mobilization (CD34 count < 10), with a sensitivity of 72% and a specificity of 93%. When prevalence of poor mobilization was 33%, this resulted in a positive predictive value of 83% and a negative predictive value of 87%. The SCI also showed promise in tracking responses to plerixafor administration.

CONCLUSION

The findings demonstrate the utility of the cell population data collected by hematology analyzers to provide rapid data beyond standard complete blood counts, particularly for stem cell count prediction, requiring no additional reagents, specimen, or instrumentation.