Multi-Class Classification of Immature Leukocytes in AML Blood Smears Using an Ensemble of CNNs

• Ana V. S. Coelho UFPI
• Leonardo P. Sousa UFPI
• Nicole E. M. Silvestre UFPI
• Maíla L. Claro IFPI
• André M. Santana UFPI
• Rodrigo M. S. Veras UFPI

DOI: https://doi.org/10.5753/eniac.2025.14441

Abstract

Acute Myeloid Leukemia (AML) is a neoplasm characterized by the abnormal proliferation of immature leukocytes, whose identification is essential for diagnosis. This study evaluated the use of Convolutional Neural Networks (CNNs) for the automatic classification of five cell subtypes in blood smear images. Eight pre-trained architectures were tested using data augmentation, crossvalidation, and transfer learning. Based on the top four networks, four majority voting committees were formed, with the best-performing one achieving an accuracy of 88.49% and outperforming individual models. The results indicate the potential of the approach to support AML diagnosis.

References

Agaian, S., Madhukar, M., and Chronopoulos, A. T. (2018). A new acute leukaemia automated classification system. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 6(3):303–314.

American Cancer Society (2025). Key statistics for acute myeloid leukemia (aml). [link]. Accessed on: 29 Mar. 2025.

Berrar, D. (2019). Cross-validation. In Ranganathan, S., Gribskov, M., Nakai, K., and Schönbach, C., editors, Encyclopedia of Bioinformatics and Computational Biology, pages 542–545. Academic Press, Oxford.

Boldú, L., Merino, A., Acevedo, A., Molina, A., and Rodellar, J. (2021). A deep learning model (alnet) for the diagnosis of acute leukaemia lineage using peripheral blood cell images. Computer Methods and Programs in Biomedicine, 202:105999.

Chennamadhavuni, A., Iyengar, V., Mukkamala, S. K. R., and Shimanovsky, A. (2023). Leukemia. StatPearls [Internet]. Available at: [link].

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

Dietterich, T. G. (2000). Ensemble methods in machine learning. In International workshop on multiple classifier systems, pages 1–15. Springer.

LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature, 521(7553):436–444.

Matek, C., Schwarz, S., Spiekermann, K., and Marr, C. (2019). Human-level recognition of blast cells in acute myeloid leukaemia with convolutional neural networks. Nature Machine Intelligence, 1(11):538–544.

Mumuni, A.-R. and Mumuni, F. (2022). Data augmentation: A comprehensive survey of modern approaches. Array, 16:100258.

Powers, D. M. W. (2020). Evaluation: from precision, recall and f-measure to roc, informedness, markedness and correlation.

Rahman, J. and Ahmad, M. (2023). Detection of acute myeloid leukemia from peripheral blood smear images using transfer learning in modified cnn architectures. pages 447–459.

Rosenfield, G. H. and Fitzpatrick-Lins, K. (1986). A coefficient of agreement as a measure of thematic classification accuracy. Photogrammetric Engineering and Remote Sensing.

Santos, M., Bertemes, W., de Souza, , Andrades, M., Barros, D., and Patto, V. (2022). Algoritmos de aprendizado de máquina para classificação de células nucleadas do sangue periférico - uma experiência do projeto hemovision. In Anais da X Escola Regional de Informática de Goiás, pages 130–140. SBC.

Saultz, J. N. and Garzon, R. (2016). Acute myeloid leukemia: a concise review. Journal of Clinical Medicine, 5(3):33.

Sidhom, J.-W., Siddarthan, I. J., Lai, B. S., Luo, A., Hambley, B. C., Bynum, J., Duffield, A. S., Streiff, M. B., Moliterno, A. R., Imus, P., et al. (2021). Deep learning for diagnosis of acute promyelocytic leukemia via recognition of genomically imprinted morphologic features. NPJ Precision Oncology, 5(1):38.

Sousa, L. P., Silva, R. R. V., Claro, M. L., Araújo, F. H. D., Borges, R. N., Machado, V. P., and Veras, R. M. S. (2025). Ensemble of cnns for enhanced leukocyte classification in acute myeloid leukemia diagnosis. In Paes, A. and Verri, F. A. N., editors, Intelligent Systems, pages 399–413, Cham. Springer Nature Switzerland.

Tajbakhsh, N., Shin, J. Y., Gurudu, S. R., Hurst, R. T., Kendall, C. B., Gotway, M. B., and Liang, J. (2016). Convolutional neural networks for medical image analysis: Full training or fine tuning? IEEE transactions on medical imaging, 35(5):1299–1312.

Thanh, T. T. P., Vununu, C., Atoev, S., Lee, S.-W., and Kwon, K.-R. (2018). Leukemia blood cell image classification using convolutional neural network. International Journal of Computer Theory and Engineering, 10:54–58.

Vogado, L. H. S., Veras, R. M. S., and Aires, K. R. T. (2021). Leuknet: Um modelo de rede neural convolucional para o diagnóstico de leucemia. In Anais do Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS), pages 85–90. Sociedade Brasileira de Computação.

Yamamoto, J. F. and Goodman, M. T. (2008). Patterns of leukemia incidence in the united states by subtype and demographic characteristics, 1997–2002. Cancer Causes & Control, 19(4):379–390.