Comparison of an automated digital cell morphology analysis system with manual counting

Juan Jiao; Xin Yin; Jiali Ma; Yinglong Xia; Jianxia Xu; Shaozhe Zhao; Jie Liu

doi:10.1002/ila2.10

iLABMED 2023, 1(1): 22-28 https://doi.org/10.1002/ila2.10

Original Article |

Open Access | Issue | Published: 17 May 2023

Comparison of an automated digital cell morphology analysis system with manual counting

Show Author's Information Hide Author's Information Juan Jiao^¹, Xin Yin^², Jiali Ma^¹, Yinglong Xia^¹, Jianxia Xu^¹, Shaozhe Zhao^¹, Jie Liu^¹(

)

Department of Clinical Laboratory, The Seventh Medical Center, Chinese PLA General Hospital, Beijing, China

Department of Public Health, Shanxi Medical University, Jinzhong, Shanxi, China

Keywords:

comparison, CSFA800, manual counting, morphological classification

Cite this article:

Jiao J, Yin X, Ma J, et al. Comparison of an automated digital cell morphology analysis system with manual counting. iLABMED, 2023, 1(1): 22-28. https://doi.org/10.1002/ila2.10

Download citation

EndNote(RIS)

BibTeX

293

Views

Downloads

Citations

Crossref

N/A

WoS

N/A

Scopus

N/A

CSCD

Abstract Full text About this article

Abstract

Background

Bionovation's CSFA800 is a new automated digital cell imaging analyzer. We evaluated the performance of the CSFA800 by comparing it with artificial peripheral blood white blood cell counting.

Methods

According to inclusion and exclusion criteria, 131 randomly selected samples (77 abnormal samples and 54 normal samples) were compared. Correlations between automated and manual counting results were analyzed. Manual counting was carried out according to the guidelines of the Association of Clinical and Laboratory Standards.

Results

Counts of neutrophils, lymphocytes, monocytes, eosinophils, basophils, and immature granulocytes obtained from CSFA800 and artificial methods were linearly and positively correlated, with R values of 0.73, 0.65, 0.24, 0.2, 0.4, and 0.63, respectively, all p < 0.05. Therefore, correlations between CSFA800 and manual counting are acceptable. Compared with the DI‐60 Automated Digital Cell Morphology System (DI‐60; Sysmex), CSFA800 is more efficient and can analyze 20,000 cells in 1 min. However, the overall accuracy of CSFA800 is not as good as DI‐60, although its counting performance is better for basophils.

Conclusions

The performance of CSFA800 for WBC counts is acceptable, and it displayed good performance for neutrophils, lymphocytes, and immature granulocytes. Compared to DI‐60, CSFA800 is more efficient but has slightly lower overall accuracy. To some extent, CSFA800 is helpful to optimize the clinical laboratory workflow and improve the working efficiency of inspectors.

Full text

Abstract

Full text

Outline

About this article

Comparison of an automated digital cell morphology analysis system with manual counting

Show Author's information Hide Author's Information Juan Jiao^¹, Xin Yin^², Jiali Ma^¹, Yinglong Xia^¹, Jianxia Xu^¹, Shaozhe Zhao^¹, Jie Liu^¹(

)

Department of Clinical Laboratory, The Seventh Medical Center, Chinese PLA General Hospital, Beijing, China

Department of Public Health, Shanxi Medical University, Jinzhong, Shanxi, China

Abstract

Background

Bionovation's CSFA800 is a new automated digital cell imaging analyzer. We evaluated the performance of the CSFA800 by comparing it with artificial peripheral blood white blood cell counting.

Methods

Results

Conclusions

Keywords: comparison, CSFA800, manual counting, morphological classification

References(25)

[1]

Khan S, Sajjad M, Hussain T, Ullah A, Imran AS. A review on traditional machine learning and deep learning models for WBCs classification in blood smear images. IEEE Access. 2021;9:10657–73. https://doi.org/10.1109/ACCESS.2020.3048172

DOI Google Scholar

[2]

Koo T, Kim MH, Jue MS. Automated detection of superficial fungal infections from microscopic images through a regional convolutional neural network. PLoS One. 2021;16(8):e0256290. https://doi.org/10.1007/s11517‐016‐1590‐x

DOI Google Scholar

[3]

Fan H, Zhang F, Xi L, Li Z, Liu G, Xu Y, et al. LeukocyteMask: an automated localization and segmentation method for leukocyte in blood smear images using deep neural networks. J Biophot. 2019;12(7):e201800488. https://doi.org/10.1002/jbio.201800488

DOI Google Scholar

[4]

Kutlu H, Avci E, Özyurt F. White blood cells detection and classification based on regional convolutional neural networks. Med Hypotheses. 2020;135:109472. https://doi.org/10.1016/j.mehy.2019.109472

DOI Google Scholar

[5]

Kumar R, Joshi S, Dwivedi A. CNN‐SSPSO: a hybrid and optimized CNN approach for peripheral blood cell image recognition and classification. Int J Pattern Recogn Artif Intell. 2020;35(05):2157004. https://doi.org/10.1142/S0218001421570044

DOI Google Scholar

[6]

Shahin AI, Guo Y, Amin KM, Sharawi AA. White blood cells identification system based on convolutional deep neural learning networks. Comput Methods Progr Biomed. 2019;168:69–80. https://doi.org/10.1016/j.cmpb.2017.11.015

DOI Google Scholar

[7]

Yao X, Sun K, Bu X, Zhao C, Jin Y. Classification of white blood cells using weighted optimized deformable convolutional neural networks. Artif Cell Nanomed Biotechnol. 2021;49(1):147–55. https://doi.org/10.1016/j.asoc.2020.106810

DOI Google Scholar

[8]

Bain BJ. Structure and function of red and white blood cells. Medicine. 2017;45(4):187–93. https://doi.org/10.1016/j.mpmed.2017.01.011

DOI Google Scholar

[9]

Ma L, Shuai R, Ran X, Liu W, Ye C. Combining DC‐GAN with ResNet for blood cell image classification. Med Biol Eng Comput. 2020;58(6):1251–64. https://doi.org/10.1007/s11517‐020‐02163‐3

DOI Google Scholar

[10]

Negm AS, Hassan OA, Kandil AH. A decision support system for acute leukaemia classification based on digital microscopic images. Alex Eng J. 2018;57(4):2319–32. https://doi.org/10.1016/j.aej.2017.08.025

DOI Google Scholar

[11]

Yao J, Huang X, Wei M, Han W, Xu X, Wang R, et al. High‐efficiency classification of white blood cells based on object detection. J Healthc Eng. 2021;2021:1615192. https://doi.org/10.1155/2021/1615192

DOI Google Scholar

[12]

Warnat‐Herresthal S, Perrakis K, Taschler B, Becker M, Baßler K, Beyer M, et al. Scalable prediction of acute myeloid leukemia using high‐dimensional machine learning and blood transcriptomics. iScience. 2020;23(1):100780. https://doi.org/10.1016/j.isci.2019.100780

DOI Google Scholar

[13]

He J, Baxter SL, Xu J, Xu J, Zhou X, Zhang Kl, et al. The practical implementation of artificial intelligence technologies in medicine. Nat Med. 2019;25(1):30–6. https://doi.org/10.1038/s41591‐018‐0307‐0

DOI Google Scholar

[14]

Ngiam KY, Khor W. Big data and machine learning algorithms for health‐care delivery. Lancet Oncol. 2019;20(5):e262–e273. https://doi.org/10.1016/S1470‐2045(19)30149‐4

DOI Google Scholar

[15]

Kim HN, Hur M, Kim H, Kim SW, Moon HW, Yun YM, et al. Performance of automated digital cell imaging analyzer Sysmex DI‐60. Clin Chem Lab Med. 2017;56(1):94–102. https://doi.org/10.1515/cclm‐2017‐0132

DOI Google Scholar

[16]

Rosetti M, Massari E, Poletti G, Dorizzi RM. Could the UKNEQAS program “Manual Differential Blood Count” be performed by the use of an automated digital morphology analyzer (Sysmex DI‐60)? A feasibility study. Clin Chem Lab Med. 2021;59(4):e161–e164. https://doi.org/10.1515/cclm‐2020‐0627

DOI Google Scholar

[17]

Takemura H, Ai T, Kimura K, Nagasaka K, Takahashi T, Tsuchiya K, et al. Evaluation of cell count and classification capabilities in body fluids using a fully automated Sysmex XN equipped with high‐sensitive Analysis (hsA) mode and DI‐60 hematology analyzer system. PLoS One. 2018;13(4):e0195923. https://doi.org/10.1371/journal.pone.0195923

DOI Google Scholar

[18]

Kweon OJ, Lim YK, Lee MK, Kim HR. Red and white blood cell morphology characterization and hands‐on time analysis by the digital cell imaging analyzer DI‐60. PLoS One. 2022;17(4):e0267638. https://doi.org/10.1371/journal.pone.0267638

DOI Google Scholar

[19]

Nam M, Yoon S, Hur M, Lee GH, Kim H, Park M, et al. Digital morphology analyzer Sysmex DI‐60 vs. manual counting for white blood cell differentials in leukopenic samples: a comparative assessment of risk and turnaround time. Ann Lab Med. 2022;42(4):398–405. https://doi.org/10.3343/alm.2022.42.4.398

DOI Google Scholar

[20]

Lee SY, Lee HT, Kwoun WJ, Lee YS, Ahn JY. Evaluating the performance of the Sysmex DI‐60 automated cell image analyzer for the differential analysis of leukocytes. Lab Med Qual Assur. 2020;42(2):70–6. https://doi.org/10.15263/jlmqa.2020.42.2.70

DOI Google Scholar

[21]

Akoglu H. User's guide to correlation coefficients. Turk J Emerg Med. 2018;18(3):91–3. https://doi.org/10.1016/j.tjem.2018.08.001

DOI Google Scholar

[22]

DOI Google Scholar

[23]

Khatami A, Khosravi A, Nguyen T, Lim CP, Nahavandi S. Medical image analysis using wavelet transform and deep belief networks. Expert Syst Appl. 2017;86:190–8. https://doi.org/10.1016/j.eswa.2017.05.073

DOI Google Scholar

[24]

Handelman, GS, Kok, HK, Chandra, RV, Razavi, AH, Lee, MJ, Asadi H. eDoctor: machine learning and the future of medicine. J Intern Med. 2018;284(6): 603–19. https://doi.org/10.1111/joim.12822

DOI Google Scholar

[25]

Acevedo A, Alférez S, Merino A, Puigví L, Rodellar J. Recognition of peripheral blood cell images using convolutional neural networks. Comput Methods Progr Biomed. 2019;180:105020. https://doi.org/10.1016/j.cmpb.2019.105020

DOI Google Scholar

About this article

Publication history

Acknowledgements

Rights and permissions

Publication history

Received: 05 February 2023

Accepted: 03 April 2023

Published: 17 May 2023

Issue date: June 2023

Copyright

Acknowledgements

ACKNOWLEDGMENTS

We thank Zhiqiang Zhang (Beijing Hanyuan Pharmaceutical Technology Co., LTD) for the comments on the content of the article, and we would like to thank all participants who participated in the study for their time and involvement.

Rights and permissions

This is an open access article under the terms of the Creative Commons Attribution‐NonCommercial‐NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non‐commercial and no modifications or adaptations are made.