Automated digital cytomorphology increases the reliability of bone marrow diagnostics
Authors:
D. Starostka 1; R. Doležílek 2; P. Miczková 1; J. Juráňová 3; K. Chasáková 1; D. Koláček 4
Published in:
Transfuze Hematol. dnes,31, 2025, No. 2, p. 66-80.
Category:
Review/Educational Papers
doi:
https://doi.org/10.48095/cctahd2025prolekare.cz12
Overview
Expert cytomorphological analysis with natural intra- and inter-expert variability remains one of the cornerstones of multidisciplinary diagnostics in haematology. Automated digital morphology using artificial intelligence represents a major transformational paradigm shift in bone marrow cytomorphology as it minimises subjectivity and variability in assessments. There are several analytical platforms for this method. In addition to speed and objectification of analysis, software advantages include instructive display of cellular context, offering alternative cell classification and cell size measurement and the ability to evaluate high cell counts and detailed assessment of megakaryopoiesis. Major limitations of this method include the quality of imaging and misclassification of cells, which can have critical diagnostic and clinical implications. Extensive validation of analytical equipment for digital bone marrow cytomorphology is necessary, particularly for the Caucasian population. Even in an era of disruptive technological developments, expertise consistently remains the cornerstone of morphologic diagnosis in haemato-oncology.
Keywords:
artificial intelligence – bone marrow – automated digital cytomorphology – cell classification – diagnostic haemato-oncology
Sources
1. Starostka D, Dolezilek R, Chasakova K. Artificial intelligence increases reliability in diagnostic hematooncology. J Clin Transl Pathol. 2023; 3 (3): 146–147. doi: 10.14218/JCTP.2023.00 015.
2. Zini G, Barbagallo O, Scavone F, Béné MC. Digital morphology in hematology diagnosis and education: The experience of the European LeukemiaNet WP10. Int J Lab Hematol. 2022; 44 (Suppl 1): 37–44. doi: 10.1111/ijlh.13908.
3. Xing Y, Liu X, Dai J, et al. Artificial intelligence of digital morphology analyzers improves the efficiency of manual leukocyte differentiation of peripheral blood. BMC Med Inform Decis Mak. 2023; 23 (1): 50. doi: 10.1186/s12911-023-02153-z.
4. Kratz A, Lee SH, Zini G, Riedl JA, Hur M, Machin S. International Council for Standardization in Haematology. Digital morphology analyzers in hematology: ICSH review and recommendations. Int J Lab Hematol. 2019; 41 (4): 437–447. doi: 10.1111/ijlh.13042.
5. Jin H, Fu X, Cao X, et al. Developing and preliminary validating an automatic cell classification system for bone marrow smears: a pilot study. J Med Syst. 20207; 44 (10): 184. doi: 10.1007/s10916-020-01654-y.
6. Walter W, Haferlach C, Nadarajah N, et al. How artificial intelligence might disrupt diagnostics in hematology in the near future. Oncogene. 2021; 40 (25): 4271–4280. doi: 10.1038/s41388-021-01861-y.
7. Lin E, Fuda F, Luu HS, et al. Digital pathology and artificial intelligence as the next chapter in diagnostic hematopathology. Semin Diagn Pathol. 2023; 40 (2): 88–94. doi: 10.1053/j.semdp.2023.02.001.
8. Starostka D, Doležílek R, Chasáková K, Miczková P, Kováč P. Umělá inteligence v cytomorfologii kostní dřeně: Morphogo a Scopio. Transfuze Hematol Dnes. 2024; 30 (1): 49–52.
9. Fu X, Fu M, Li Q, et al. Morphogo: an automatic bone marrow cell classification system on digital images analyzed by artificial intelligence. Acta Cytol. 2020; 64 (6): 588–596. doi: 10.1159/000509524.
10. Lv Z, Cao X, Jin X, Xu S, Deng H. High-accuracy morphological identification of bone marrow cells using deep learning-based Morphogo system. Sci Rep. 2023; 13 (1): 13364. doi: 10.1038/s41598-023-40424-x.
11. Tang G, Fu X, Wang Z, Chen M. A machine learning tool using digital microscopy (Morphogo) for the identification of abnormal lymphocytes in the bone marrow. Acta Cytol. 2021; 65 (4): 354–357. doi: 10.1159/000518 382.
12. Wang X, Wang Y, Qi C, et al. The application of Morphogo in the detection of megakaryocytes from bone marrow digital images with convolutional neural networks. Technol Cancer Res Treat. 2023; 22: 15330338221150069. doi: 10.1177/15330338221150069.
13. Chen P, Chen Xu R, Chen N, et al. Detection of metastatic tumor cells in the bone marrow aspirate smears by artificial intelligence (AI) -based Morphogo system. Front Oncol. 2021; 11: 742395. doi: 10.3389/fonc.2021.742395.
14. Katz BZ, Feldman MD, Tessema M, et al. Evaluation of Scopio Labs X100 Full Field PBS: The first high-resolution full field viewing of peripheral blood specimens combined with artificial intelligence-based morphological analysis. Int J Lab Hematol. 2021; 43 (6): 1408–1416. doi: 10.1111/ijlh.13681.
15. Bagg A, Raess P, Rund D, et al. Performance evaluation study of a novel digital microscopy system for the quantitative analysis of bone marrow aspirates. Blood. 2021; 138: 4000.
16. Lewis JE, Pozdnyakova O. Digital assessment of peripheral blood and bone marrow aspirate smears. Int J Lab Hematol. 2023; 45 Suppl 2: 50-58. doi: 10.1111/ijlh.14082.
17. Bagg A, Raess PW, Rund D, et al. Performance evaluation of a novel artificial intelligence-assisted digital microscopy system for the routine analysis of bone marrow aspirates. Mod Pathol. 2024; 37 (9): 100542. doi: 10.1016/j.modpat.2024.100542.
18. Sirinukunwattana K, Aberdeen A, Theissen H, et al. Artificial intelligence-based morphological fingerprinting of megakaryocytes: a new tool for assessing disease in MPN patients. Blood Adv. 2020; 4 (14): 3284–3294. doi: 10.1182/bloodadvances.2020002230.
19. Ryou H, Lomas O, Theissen H, Thomas E, Rittscher J, Royston D. Quantitative interpretation of bone marrow biopsies in MPN – What‘s the point in a molecular age? Br J Haematol. 2023; 203 (4): 523–535. doi: 10.1111/bjh.19154.
20. Belcic T, Cernelc P, Sever M. Artificial intelligence aiding in diagnosis of JAK2 V617F negative patients with WHO defined essential thrombocythemia. HemaSphere. 2019; 3 (S1): 998.
21. Zini G, Chiusolo P, Rossi E, et al. Digital morphology compared to the optical microscope: A validation study on reporting bone marrow aspirates. Int J Lab Hematol. 2024; 46 (3): 474–480. doi: 10.1111/ijlh.14238.
22. Chumachenko K, Iosifdis A, Gabbouj M. Feedforward neural networks initialization based on discriminant learning. Neural Netw. 2022; 146: 220–229.
23. Ehteshami Bejnordi B, Veta M, Johannes van Diest P, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA. 2017; 318 (22): 2199–2210. doi: 10.1001/jama.2017.14585.
24. Wu YY, Huang TC, Ye RH, et al. A hematologist-level deep learning algorithm (BMSNet) for assessing the morphologies of single nuclear balls in bone marrow smears: algorithm development. JMIR Med Inform. 2020; 8 (4): e15963. doi: 10.2196/15963.
25. Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017; 542 (7639): 115-118. doi: 10.1038/nature21056. Erratum in: Nature. 2017; 546 (7660): 686. doi: 10.1038/nature 22985.
26. Lewandowski K, Kurpierz K, Sledzinska A. External bone marrow cytological examination quality assurance (EQAhem) --summary after 6 years in Poland. Ann Hematol. 2015; 94 (10): 1741–1748. doi: 10.1007/s00277-015-2434-8.
27. Sasada K, Yamamoto N, Masuda, et al. Inter-observer variance and the need for standardization in the morphological classification of myelodysplastic syndrome. Leuk Res. 2018; 69: 54–59. doi: 10.1016/j.leukres.2018.04.003.
28. Naqvi K, Jabbour E, Bueso-Ramos C, et al. Implications of discrepancy in morphologic diagnosis of myelodysplastic syndrome between referral and tertiary care centers. Blood. 2011; 118 (17): 4690–4693. doi: 10.1182/blood- 2011-03-342642.
29. Tohyama K. Present status and perspective of laboratory hematology in Japan: On the standardization of blood cell morphology including myelodysplasia: On behalf of the Japanese Society for Laboratory Hematology. Int J Lab Hematol. 2018; 40 (Suppl 1): 120–125. doi: 10.1111/ijlh.12819.
30. Matsuda A, Germing U, Jinnai I, et al. Improvement of criteria for refractory cytopenia with multilineage dysplasia according to the WHO classification based on prognostic significance of morphological features in patients with refractory anemia according to the FAB classification. Leukemia. 2007; 21: 678–686.
31. Font P, Loscertales J, Soto C, et al. Interobserver variance in myelodysplastic syndromes with less than 5 % bone marrow blasts: unilineage vs. multilineage dysplasia and reproducibility of the threshold of 2 % blasts. Ann Hematol. 2015; 94 (4): 565–573. doi: 10.1007/s00277-014-2252-4.
32. Font P, Loscertales J, Benavente C, et al. Inter-observer variance with the diagnosis of myelodysplastic syndromes (MDS) following the 2008 WHO classification. Ann Hematol. 2013; 92 (1): 19–24. doi: 10.1007/s00277- 012-1565-4.
33. DeLima M, Albitar M, O‘Brien S, et al. Comparison of referring and tertiary cancer center physician‘s diagnoses in patients with leukemia. Am J Med. 1998; 104 (3): 246–251. doi: 10.1016/s0002-9343 (98) 00032-1.
34. Ratziu V, Hompesch M, Petitjean M, et al. Artificial intelligence-assisted digital pathology for non-alcoholic steatohepatitis: current status and future directions. J Hepatol. 2024; 80 (2): 335–351. doi: 10.1016/j.jhep.2023.10.015.
35. Ström P, Kartasalo K, Olsson H, et al. Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study. Lancet Oncol. 2020; 21 (2): 222–232. doi: 10.1016/S1470-2045 (19) 30738-7. Erratum in: Lancet Oncol. 2020; 21 (2): e70. doi: 10.1016/S1470-2045 (20) 30032-2.
36. Jonas RA, Weerakoon S, Fisher R, et al. Interobserver variability among expert readers quantifying plaque volume and plaque characteristics on coronary CT angiography: a CLARIFY trial sub-study. Clin Imaging. 2022; 91: 19–25. doi: 10.1016/j.clinimag.2022.08.005.
37. Lee Y, Alam MR, Park H, et al. Improved diagnostic accuracy of thyroid fine-needle aspiration cytology with artificial intelligence technology. Thyroid. 2024; 34 (6): 723–734. doi: 10.1089/thy.2023.0384.
38. Allende D, Elmessiry M, Hao W, et al. Inter-observer and intra-observer variability in the diagnosis of dysplasia in patients with inflammatory bowel disease: correlation of pathological and endoscopic findings. Colorectal Dis. 2014; 16 (9): 710–718; discussion 718. doi: 10.1111/codi.12667. Erratum in: Colorectal Dis. 2015; 17 (1): 92. Al-Qadasi, M [added].
39. Marzahl C, Aubreville M, Bertram CA, et al. Deep learning-based quantification of pulmonary hemosiderophages in cytology slides. Sci Rep. 2020; 10 (1): 9795. doi: 10.1038/s41598-020-65958-2.
40. Mühlhofer HM, Lenze U, Lenze F, et al. Inter- and intra-observer variability in biopsy of bone and soft tissue sarcomas. Anticancer Res. 2015; 35 (2): 961–966.
41. Briggs C, Longair I, Slavik M, et al. Can automated blood film analysis replace the manual differential? An evaluation of the CellaVision DM96 automated image analysis system. Int J Lab Hematol. 2009; 31 (1): 48–60. doi: 10.1111/j.1751-553X. 2007.01002.x.
42. Ceelie H, Dinkelaar RB, van Gelder W. Examination of peripheral blood films using automated microscopy; evaluation of Diffmaster Octavia and Cellavision DM96. J Clin Pathol. 2007; 60 (1): 72–79.
43. La Gioia A, Fiorini F, Fumi M, et al. A prolonged microscopic observation improves detection of underpopulated cells in peripheral blood smears. Ann Hematol. 2017; 96 (10): 1749–1754. doi: 10.1007/s00277-017-3073-z.
44. Chen P, Zhang L, Cao X, et al. Detection of circulating plasma cells in peripheral blood using deep learning-based morphological analysis. Cancer. 2024; 130 (10): 1884–1893. doi: 10.1002/cncr.35202.
45. Starostka D, Kvasnicka HM, Dolezilek R, et al. Morphogo: a revolution in bone marrow cytomorphology – first European data. Supplement Article. Int J Lab Hematol. 2024; 46: 3–121. https: //doi.org/10.1111/ijlh.14396.
46. Kimura K, Tabe Y, Ai T, et al. A novel automated image analysis system using deep convolutional neural networks can assist to differentiate MDS and AA. Sci Rep. 2019; 9 (1): 13385. doi: 10.1038/s41598-019-49942-z.
47. Brück OE, Lallukka-Brück SE, Hohtari HR, et al. Machine learning of bone marrow histopathology identifies genetic and clinical determinants in patients with MDS. Blood Cancer Discov. 2021; 2 (3): 238–249. doi: 10.1158/2643-3230.BCD-20-0162.
48. Haferlach T, Pohlcamp Ch, Heo I, et al. Automated peripheral blood cell differentiation using artificial intelligence—a study with more than 10,000 routine samples in a Specialized Leukemia Laboratory. Blood. 2021; 138 (Suppl. 1): 103. doi: 10.1182/blood-2021-152447.
PODÍL AUTORŮ NA PŘÍPRAVĚ RUKOPISU
DS, RD, PM – příprava rukopisu
JJ, KCH, DK – revize rukopisu
ČESTNÉ PROHLÁŠENÍ
Autoři práce prohlašují, že v souvislosti s tématem, vznikem a publikací tohoto článku nejsou ve střetu zájmů a vznik ani publikace článku nebyly podpořeny žádnou farmaceutickou ani biomedicínskou firmou.
PODĚKOVÁNÍ
Publikace vznikla s podporou institucionálního grantu IGS 2023 Nemocnice Havířov, p. o.
Do redakce doručeno dne: 20. 10. 2024.
Přijato po recenzi dne: 23. 4. 2025.
MUDr. David Starostka, Ph.D.
Laboratoř hematoonkologie
a klinické biochemie
Nemocnice Havířov, p. o.
Dělnická 1132/24
73601 Havířov
e-mail: david.starostka@nemhav.cz
Labels
Haematology Internal medicine Clinical oncologyArticle was published in
Transfusion and Haematology Today
2025 Issue 2
Most read in this issue
- Interdisciplinary recommendations for thrombophilia testing
- Outcomes of first-line treatment of non-Hodgkin and Hodgkin lymphomas in real-world practice – an analysis of patients treated at the Department of Haematooncology, University Hospital Ostrava, from 2013 to 2022
- Cardiovascular complications in multiple myeloma
- Automated digital cytomorphology increases the reliability of bone marrow diagnostics