Deep Learning Ensemble for Multiclass Recognition of Mature Leukocytes in Acute Myeloid Leukemia (AML)

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

DOI: https://doi.org/10.5753/eniac.2025.14377

Abstract

Manual classification of leukocytes in blood smear images is subjective, time-consuming, and prone to errors, especially in high-demand clinical contexts. In this context, this study proposes a Convolutional Neural Network (CNN)-based approach for multiclass classification of mature leukocytes to support the diagnosis of Acute Myeloid Leukemia (AML). Eight pre-trained CNNs were evaluated on a dataset of 30,929 images from six cellular subtypes. An ensemble model with majority voting (MobileNetV2, ResNet101, and MobileNet) achieved an accuracy of 93.18%. The results highlight the potential of CNNs and ensemble strategies for automated leukocyte identification in AML-related hematological examinations.

References

Acevedo, A., Merino, A., Alférez, S., Molina, , Boldú, L., and Rodellar, J. (2020). A dataset of microscopic peripheral blood cell images for development of automatic recognition systems. Data in Brief, 30:105474.

American Cancer Society (2024). Key statistics for acute myeloid leukemia (aml). [link]. Accessed: 2025-03-16.

Asghar, R., Kumar, S., and Mahfooz, A. (2023). Classification of blood cells using deep learning models. arXiv preprint arXiv:2308.06300. Accessed: 2025-03-16.

Boldú, L., Merino, A., Acevedo, A., Molina, , 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.

Clark, K., Vendt, B., Smith, K., Freymann, J., Kirby, J., Koppel, P., and et al. (2013). The cancer imaging archive (tcia): maintaining and operating a public information repository. Journal of Digital Imaging.

Dietterich, T. G. (2000). Ensemble methods in machine learning. In International Workshop on Multiple Classifier Systems, pages 1–15. Springer.

Ding, Y., Tang, X., Zhuang, Y., Mu, J., Chen, S., Liu, S., Feng, S., and Chen, H. (2023). Leukocyte subtype classification with multi-model fusion. Medical & Biological Engineering & Computing, 61:2305–2316.

Doi, K. (2005). Current status and future potential of computer-aided diagnosis in medical imaging. The British Journal of Radiology, 78:S3–S19.

Dwivedi, A. K. (2018). Artificial neural network model for effective cancer classification using microarray gene expression data. Neural Computing and Applications, 29(12):1545–1554.

Döhner, H., Estey, E. H., Amadori, S., Appelbaum, F. R., Buchner, T., Burnett, A. K., and et al. (2010). Diagnosis and management of acute myeloid leukemia in adults: recommendations from an international expert panel, on behalf of the european leukemianet. Blood, 115:453–474.

Labati, R. D., Piuri, V., and Scotti, F. (2011). All-idb: the acute lymphoblastic leukemia image database for image processing. In IEEE International Conference on Image Processing (ICIP).

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. 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.

Sidhom, J.-W., Siddarthan, I. J., Lai, B.-S., Luo, A., Hambley, B. C., Bynum, J., and 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.-H., and Kwon, K.-R. (2018). Leukemia blood cell image classification using convolutional neural network. International Journal of Computer Theory and Engineering, 10:54–58.

Travlos, G. S. (2006). Normal structure, function, and histology of the bone marrow. Toxicologic Pathology, 34(5):548–565.