Using deep learning neural networks to identify subvariants of acute lymphoblastic leukemia

The possibilities of deep learning for the detection and classification of nucleated cells of subvariants of acute lymphoblastic leukemia from digital images of bone marrow preparations without prior manual segmentation and feature extraction are investigated. During the study, a sample of 96 clinical cases is formed, including 9,468 images of nucleated cells from bone marrow preparations obtained using computer microscopy. The architecture of a single-stage neural network detector of the YOLO (You Only Look Once) family is used for the analysis, which significantly automated the process of cell detection and classification. The trained model demonstrates high overall accuracy — 0.98 in the test sample and 0.83 in the independent sample (48 clinical cases), which indicates a good generalizing ability and reliability of the presented method. The high sensitivity (1.0) for the B-cell subvariant and the specificity (0.83) for the T—cell emphasize the effectiveness and practical value of the proposed method in differential diagnosis, confirming its potential to improve diagnostic quality and accelerate data processing. Recommendations for use include the introduction of the developed model into scientific and clinical practice for further analysis and improvement in the course of research in the diagnosis of acute lymphoblastic leukemia.

1. Bagg A., Raess Ph.W., Rund D., Bhattacharya S., Wiszniewska J., Horowitz A., Jengehin D., Fan G., Huynh M., Sanogo A., Aviv I., Katz B.-Z. Modern Pathology, 2024, no. 9(37), pp. 100542, DOI: 10.1016/j.modpat.2024.100542.

2. Kreiss L., Jiang S., Li X., Xu S., Zhou K., Lee K., Muhlberg A., Kim K., Chaware A., Ando M., Barisoni L., Seung Ah.L., Zheng G., Lafata K., Friedrich O., Horstmeyer R. PhotoniX, 2023, no. 1(4), pp. 34, DOI: 10.1186/s43074-023-00113-4.

3. Frenkel M.A. Klinicheskaya onkogematologiya (Clinical Oncohematology), Moscow, 2007, рр. 306–319. (in Russ.)

4. Tupitsyn N.N. Klinicheskaya onkogematologiya (Clinical Oncohematology), Moscow, 2007, рр. 338–370. (in Russ.)

5. Frenkel M.A. Immunology of hematopoiesis, 2014, no. 1–2(12), pp. 18–41. (in Russ.)

6. Pronichev A.N., Polyakov E.V., Tupitsyn N.N., Frenkel M.A., Mozhenkova A.V. Journal of Physics: Conference Series, 2017, no. 1(784), pp. 012003, DOI: 10.1088/1742-6596/784/1/012003.

7. Anilkumar K.K., Manoj V.J., Sagi T.M. IRBM, 2022, no. 5(43), pp. 405–413, DOI: 10.1016/j.irbm.2021.05.005.

8. Akalın F., Yumuşak N. Afyon Kocatepe Üniversitesi Fen ve Mühendislik Bilimleri Dergisi, 2023, no. 4(23), pp. 941–954, DOI: 10.35414/akufemubid.1259929.

9. Gupta R., Gehlot S., Gupta A. Medical Engineering & Physics, 2022, vol. 103, рр. 103793, DOI: 10.1016/j.medengphy.2022.103793.

10. Nikitayev V.G., Pronichev A.N., Tupitsyn N.N., Selchuk V.Yu., Dmitrieva V.V., Palladina A.D., Polyakov E.V., Liberis K.A., Dzhokich M., Solomatin M.A., Nosova E.M. Journal of Physics: Conference Series, 2021, no. 1(2058), pp. 012043, DOI: 10.1088/1742-6596/2058/1/012043.

11. Chen Y., Zhang C., Chen B., Huang Y., Sun Y., Wang C., Fu X., Dai Y., Qin F., Peng Y., Gao Y. Computers in Biology and Medicine, 2024, vol. 170, рр. 107917, DOI: 10.1016/j.compbiomed.2024.107917.

12. Mustaqim T., Fatichah C., Suciati N. IEEE Access, 2023, vol. 11, рр. 16108–16127, DOI: 10.1109/ACCESS.2023.3245128.

13. Rehman A. et al. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Cham, Springer Nature Switzerland, 2024, рр. 553–563, DOI: 10.1007/978-3-031-72384-1_52.

14. Vieira G., Valle M.E. 2022 International Joint Conference on Neural Networks (IJCNN), IEEE, 2022, рр. 1–8, DOI: 10.1109/IJCNN55064.2022.9892036.

15. Jiang X., Hu Z., Wang S., Zhang Y. Cancers, 2023, no. 14(15), pp. 3608, DOI: 10.3390/cancers15143608.

16. Fazeli S., Samiei A., Lee T.D., Sarrafzadeh M. 11th International Conference on Healthcare Informatics (ICHI), IEEE, 2023, рр. 111–117, DOI: 10.1109/ICHI57859.2023.00025.

17. Nunes J.C.S., Linhares J.E.B.D.S., Postigo M.A.O., del Río D.G., Sobrinho A.M.F., & Torné I.G. IEEE Access, 2025, vol. 13, рр. 91911–91924, https://doi.org/10.1109/ACCESS.2025.3573277.

18. Ferreira F.R.T., do Couto L.M. J. Supercomput., 2025, vol. 81, рр. 410, https://doi.org/10.1007/s11227-024-06903-2.

19. Cheng Z., Li Y. Sensors, 2023, vol. 23, рр. 7640, https://doi.org/10.3390/s23177640.