Skip to main content

Advertisement

Springer Nature Link
Log in

Leukocyte subtype classification with multi-model fusion

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Accurate classification of leukocytes is crucial for the diagnosis of hematologic malignancies, particularly leukemia. However, traditional leukocyte classification methods are time-consuming and subject to subjective interpretation by examiners. To address this issue, we aimed to develop a leukocyte classification system capable of accurately classifying 11 leukocyte classes, which would aid radiologists in diagnosing leukemia. Our proposed two-stage classification scheme involved a multi-model fusion based on ResNet for rough leukocyte classification, which focused on shape features, followed by fine-grained leukocyte classification using support vector machine for lymphocytes based on texture features. Our dataset consisted of 11,102 microscopic leukocyte images of 11 classes. Our proposed method achieved accurate leukocyte subtype classification with high levels of accuracy, sensitivity, specificity, and precision of 97.03 ± 0.05, 96.76 ± 0.05, 99.65 ± 0.05, and 96.54 ± 0.05, respectively, in the test set. The experimental results demonstrate that the leukocyte classification model based on multi-model fusion can effectively classify 11 leukocyte classes, providing valuable technical support for enhancing the performance of hematology analyzers.

Graphical abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Döhner H, Wei AH, Appelbaum FR et al (2022) Diagnosis and management of AML in adults: 2022 recommendations from an international expert panel on behalf of the ELN. Blood 140(12):1345–1377

    Article  PubMed  Google Scholar 

  2. Jain RK, Hong DS, Naing A et al (2015) Novel phase I study combining G1 phase, S phase, and G2/M phase cell cycle inhibitors in patients with advanced malignancies. Cell Cycle 14(21):3434–3440

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Evans C, Orf K, Horvath E et al (2015) Impairment of neutrophil oxidative burst in children with sickle cell disease is associated with heme oxygenase-1. Haematologica 100(12):1508–1516

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Chan YK, Tsai MH, Huang DC et al (2010) Leukocyte nucleus segmentation and nucleus lobe counting. BMC Bioinforms 11(1):558–576

  5. Shao H, Gao W, Zhang Q et al (2020) Transfer learning for identifying morphological heterogeneity of neutrophils nuclei in hematological diseases based on nuclei semantic segmentations of bone marrow smear. Blood 136(Suppl 1):1–1

  6. Pollyea DA, Schowinsky JT (2016) Atypical chronic myeloid leukemia and chronic neutrophilic leukemia. Curr Opin Hematol 23(1):129–136

  7. Yu T C, Chou W C, Yeh C Y et al (2019) Automatic bone marrow cell identification and classification by deep neural network. Blood 134(Suppl 1):2084–2084

  8. Schwede M, Gotlib J, Shomali W (2021) Diagnosis and management of neutrophilic myeloid neoplasms. Clin Adv Hematol Oncol : H&O 19(7):450–459

    Google Scholar 

  9. Hauser RG, Esserman D, Beste LA et al (2021) A machine learning model to successfully predict future diagnosis of chronic myelogenous leukemia with retrospective electronic health records data. Am J Clin Pathol 156(6):1142–1148

  10. Shipley JL, Butera JN (2009) Acute myelogenous leukemia. Exp Hematol 37(6):649–58

  11. Montgomery ND, Dunphy CH, Mooberry M et al (2013) Diagnostic complexities of eosinophilia. Arch Pathol Lab Med 137(2):259–269

    Article  PubMed  Google Scholar 

  12. Goasguen JE, Bennett JM, Bain BJ et al (2020) The role of eosinophil morphology in distinguishing between reactive eosinophilia and eosinophilia as a feature of a myeloid neoplasm. Br J Haematol 191(3):497–504

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  13. Morsia E, Reichard K, Pardanani A et al (2020) WHO defined chronic eosinophilic leukemia, not otherwise specified (CEL, NOS): a contemporary series from the Mayo Clinic. Am J Hematol 95(7):E172–E174

    Article  PubMed  Google Scholar 

  14. Siow W, Matthey F, Bain BJ (2021) Eosinophil morphology in the reactive eosinophilia of Hodgkin lymphoma. Br J Haematol 192(2):296–297

  15. King RL, Tan B, Craig FE et al (2021) Reactive eosinophil proliferations in tissue and the lymphocytic variant of hypereosinophilic syndrome 2019 Society for Hematopathology/European Association for Haematopathology workshop report. Am J Clin Pathol 155(2):211–238

    Article  PubMed  Google Scholar 

  16. Valent P, Sotlar K, Blatt K et al (2017) Proposed diagnostic criteria and classification of basophilic leukemias and related disorders. Leukemia 31(4):788–797

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  17. Hallek M, Al-Sawaf O (2021) Chronic lymphocytic leukemia: 2022 update on diagnostic and therapeutic procedures. Am J Hematol 96(12):1679–1705

    Article  PubMed  Google Scholar 

  18. Chan A, Kumar P, Gao Q et al (2021) Abnormal B-lymphoblasts in myelodysplastic syndromes and myeloproliferative neoplasms other than chronic myeloid leukemia. Cytometry Part B: Clin Cytom 1–10

  19. Aldoss I, Capelletti M, Park J et al (2019) Acute lymphoblastic leukemia as a clonally unrelated second primary malignancy after multiple myeloma. Leukemia 33(1):266–270

    Article  CAS  PubMed  Google Scholar 

  20. Allegra A, Musolino C, Tonacci A et al (2020) Clinico-biological implications of modified levels of cytokines in chronic lymphocytic leukemia: a possible therapeutic role. Cancers 12(2):524–550

  21. Patnaik MM, Tefferi A (2020) Chronic Myelomonocytic leukemia: 2020 update on diagnosis, risk stratification and management. Am J Hematol 95(1):97–115

    Article  CAS  PubMed  Google Scholar 

  22. Tremblay D, Rippel N, Feld J et al (2021) Contemporary risk stratification and treatment of chronic myelomonocytic leukemia. Oncologist 26(5):406–421

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  23. Katz SG, Edappallath S, Xu ML (2021) IRF8 is a reliable monoblast marker for acute monocytic leukemias. Am J Surg Pathol 45(10):1391–1398

    Article  PubMed  Google Scholar 

  24. Sharma S, Gupta S, Gupta D et al (2022) Deep learning model for the automatic classification of white blood cells. Comput Intell Neurosci 2022:7384131

    Article  PubMed  PubMed Central  Google Scholar 

  25. Siddique MAI, Aziz AZB, Matin A (2020) An improved deep learning based classification of human white blood cell images. 2020 11th International Conference on Electrical and Computer Engineering (ICECE), pp. 149–152

  26. Ghosh S, Majumder M, Kudeshia A (2021) LeukoX: leukocyte classification using Least Entropy Combiner (LEC) for ensemble learning. IEEE Trans Circuits Syst II Express Briefs 68(8):2977–2981

    Google Scholar 

  27. Balasubramanian K, Ananthamoorthy NP, Ramya K (2022) An approach to classify white blood cells using convolutional neural network optimized by particle swarm optimization algorithm. Neural Comput Appl 34(18):16089–16101

    Article  Google Scholar 

  28. Zhang X, Zhao S (2019) Blood cell image classification based on image segmentation preprocessing and CapsNet network model. Journal of Medical Imaging and Health Informatics 9(1):159–166

  29. Yao J, Huang X, Wei M et al (2021) High-efficiency classification of white blood cells based on object detection. J Healthc Eng 2021:1615192

    Article  PubMed  PubMed Central  Google Scholar 

  30. Elhassan TA, Mohd Rahim MS, Siti Zaiton MH et al (2023) Classification of atypical white blood cells in acute myeloid leukemia using a two-stage hybrid model based on deep convolutional autoencoder and deep convolutional neural network. Diagnostics (Basel) 13(2):196–216

  31. Zhai Q, Fan B, Zhang B et al (2022) Automatic white blood cell classification based on whole-slide images with a deeply aggregated neural network. J Med Biol Eng 42(1):126–137

    Article  Google Scholar 

  32. Wang D, Hwang M, Jiang WC et al (2021) A deep learning method for counting white blood cells in bone marrow images. BMC Bioinforma 22(Suppl 5):94

    Article  CAS  Google Scholar 

  33. Acevedo A, Alferez S, Merino A et al (2019) Recognition of peripheral blood cell images using convolutional neural networks. Comput Methods Programs Biomed 180:105020

    Article  PubMed  Google Scholar 

  34. Dong N, Feng Q, Zhai M et al (2022) A novel feature fusion based deep learning framework for white blood cell classification. J Ambient Intell Humaniz Comput 1–13

  35. Chen H, Liu J, Hua C et al (2022) Accurate classification of white blood cells by coupling pre-trained ResNet and DenseNet with SCAM mechanism. BMC Bioinforms 23(1):1–20

  36. Malkawi A, Al-Assi R, Salameh T et al (2020) White blood cells classification using convolutional neural network hybrid system. In: 2020 IEEE 5th Middle East and Africa Conference on Biomedical Engineering (MECBME) pp 1–5

  37. Cinar AC, Tuncer SA (2021) Classification of lymphocytes, monocytes, eosinophils, and neutrophils on white blood cells using hybrid Alexnet-GoogleNet-SVM. SN Appl Sci 3(4):1–11

  38. Togacar M, Ergen B, Comert Z (2020) Classification of white blood cells using deep features obtained from Convolutional Neural Network models based on the combination of feature selection methods. Appl Soft Comput 97:106810

  39. Iqbal N, Mumtaz R, Shafi U et al (2021) Gray level co-occurrence matrix (GLCM) texture based crop classification using low altitude remote sensing platforms. PeerJ Comput Sci 7(8):e536

  40. Mishra S, Majhi B, Sa PK et al (2017) Gray level co-occurrence matrix and random forest based acute lymphoblastic leukemia detection. Biomed Signal Process Control 33:272–280

    Article  Google Scholar 

  41. Dasariraju S, Huo M, McCalla S (2020) Detection and classification of immature leukocytes for diagnosis of acute myeloid leukemia using random forest algorithm. Bioengineering 7(4):120

  42. Boldu L, Merino A, Acevedo A et al (2021) A deep learning model (ALNet) for the diagnosis of acute leukaemia lineage using peripheral blood cell images. Comput Methods Programs Biomed 202:105999

    Article  PubMed  Google Scholar 

  43. Roy R, Ameer P (2022) Identification of white blood cells for the diagnosis of acute myeloid leukemia. Int J Imaging Syst Technol 32(4):1307–1317

  44. Long F, Peng JJ, Song W et al (2021) BloodCaps: a capsule network based model for the multiclassification of human peripheral blood cells. Comput Methods Programs Biomed 202:105972

    Article  PubMed  Google Scholar 

  45. Wang Q, Bi S, Sun M et al (2019) Deep learning approach to peripheral leukocyte recognition. PLoS One 14(6):e0218808

Download references

Acknowledgements

The authors declare no competing interests. This article does not involve with any animals or human participants. The study was partially supported by project grants from the National Natural Science Foundation of China (82260358 and 81460273).

Author information

Author notes

  1. Yingying Ding and Xuehui Tang contributed to this work equally.

Authors and Affiliations

  1. School of Life & Environmental Science, Guilin University of Electronic Technology, Guilin, 541004, China

    Yingying Ding, Shuchao Chen & Hongbo Chen

  2. Shenzhen Institute of Beihang University, Shenzhen, 518063, China

    Xuehui Tang & Yuan Zhuang

  3. Affiliated Hospital of Guilin Medical University, Guilin, 541001, China

    Junjie Mu, Shanshan Liu & Sihao Feng

Authors
  1. Yingying Ding
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Xuehui Tang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Yuan Zhuang
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Junjie Mu
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Shuchao Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Shanshan Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

  7. Sihao Feng
    View author publications

    You can also search for this author inPubMed Google Scholar

  8. Hongbo Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding authors

Correspondence to Sihao Feng or Hongbo Chen.

Additional information

Publisher's note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ding, Y., Tang, X., Zhuang, Y. et al. Leukocyte subtype classification with multi-model fusion. Med Biol Eng Comput 61, 2305–2316 (2023). https://doi.org/10.1007/s11517-023-02830-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-023-02830-1

Keywords