Abstract

Acute Myeloid Leukemia (AML) is a hematological disease that is defined by the fast growth of aberrant myeloid precursor cells in the blood and bone marrow, which disrupts normal hematopoiesis. Treatment and prognosis are influenced by the early detection of this deadly illness and its appropriate classification. Therefore, utilizing the Human Leukemia Cytomorphology Collection dataset, which comprises leukemic and normal single-cell images of Acute Myeloid Leukemia (AML) type, this research suggests a deep learning-based hybrid model for automated leukemia detection and classification.  By taking morphological characteristics and genetic abnormalities into account, leukemic cells have been distinguished. The features in this study are extracted using MobileNetV2, ResNet-101, and VGG-16. Then, feature-level stacking is performed using the Support Vector Machine and Random Forest classifiers for final classification using Principal Component Analysis (PCA).   Utilising image segmentation, normalisation, data augmentation, and data oversampling techniques, the pipeline improves data quality and corrects class imbalance. Additionally, t-distributed Stochastic Neighbour Embedding (t-SNE), which shows the extracted features used for the detection of leukemia subtypes, and Gradient-Weighted Class Activation Mapping (Grad-CAM) images help with interpretability by highlighting important decision areas. The suggested study achieved 98.35% accuracy, 95.87% precision, 95.84% sensitivity, 98.97% specificity, and 95.74% F1-Score. Along with the trial results, a comparison of the four separate frameworks, viz., MobileNetV2, ResNet-101, VGG-16, and Vision Transformer, has also been carried out. The comparison shows that the proposed model outperforms the other frameworks.  The outcomes show that the suggested model has the capability to be used a reliable means for the prompt identification of AML and its subtypes.

Keywords

Acute Myeloid Leukemia, Genetic Abnormalities, Mutation, Hematological Disorder, Cytomorphology, Stacking, Feature Extraction,

Downloads

Download data is not yet available.

References

  1. E. Aby, S. Salaji, K. K. Anilkumar, T. Rajan, A review on leukemia detection and classification using Artificial Intelligence-based techniques. Computers and Electrical Engineering, 118(B), (2024) 109446. https://doi.org/10.1016/j.compeleceng.2024.109446
  2. K. Venkatesh, S. Pasupathy, S.P. Raja, Acute myeloid leukemia multi-classification using enhanced few-shot learning technique. Scalable Computing: Practice and Experience, 23(4), (2022) 377–388. https://doi.org/10.12694/scpe.v23i4.2048
  3. M.A. Alsalem, A.A. Zaidan, B.B. Zaidan, M. Hashim, H.T. Madhloom, N.D. Azeez, S. Alsyisuf, A review of the automated detection and classification of acute leukaemia: Coherent taxonomy, datasets, validation and performance measurements, motivation, open challenges and recommendations. Computer Methods and Programs in Biomedicine, 158, (2018) 93–112. https://doi.org/10.1016/j.cmpb.2018.02.005
  4. X. Parisi, J.R. Bledsoe, Diagnosis of pediatric acute myeloid leukemia and mixed-phenotype acute leukemia. Diagnostic Histopathology, 31(10),(2025) 531-563. https://doi.org/10.1016/j.mpdhp.2025.07.001
  5. National Cancer Institute. (2017) Cancer stat facts: Acute myeloid leukemia (AML), SEER, [Online]. Available: https://seer.cancer.gov/statfacts/html/amyl.html.
  6. L. Faivdullah, F. Azahar, Z.Z. Htike, W.N. Naing, Leukemia detection from blood smears. Journal of Medical and Bioengineering, 4(6), (2015) 488–491.
  7. H.S. Newton, M.A. Dobrovolskaia, Immunophenotyping: Analytical approaches and role in preclinical development of nanomedicines. Advanced Drug Delivery Reviews, 185, (2022) 114281. https://doi.org/10.1016/j.addr.2022.114281
  8. A. Kumar, V. Tilak, A. Ali. Cytogenetic analysis of chronic myeloid leukemia in an eastern Indian population. International Journal of Clinical and Medical Education Research, 2(2), (2023) 37–42.
  9. A. Sahu, P.K. Das, I. Paul, S. Meher, A hybrid deep learning framework for automatic detection of brain tumours using different modalities. IEEE Transactions on Emerging Topics in Computational Intelligence, 9(2), (2025) 1216–1225. https://doi.org/10.1109/TETCI.2024.3442889
  10. S. Dodia, A.B., P.A. Mahesh, Recent advancements in deep learning based lung cancer detection: A systematic review. Engineering Applications of Artificial Intelligence, 116, (2022) 105490. https://doi.org/10.1016/j.engappai.2022.105490
  11. E.H. Aktekin, M.B. Çöteli, A. Erbay, N. Yazici, A prospective study for the examination of peripheral blood smear samples in pediatric population using artificial intelligence. Turkish Journal of Medical Sciences, 55(2), (2025) 386–397. https://doi.org/10.55730/1300-0144.5982
  12. C. Matek, S. Schwarz, K. Spiekermann, and C. Marr, Human-level recognition of blast cells in acute myeloid leukaemia with convolutional neural networks. Nature Machine Intelligence, 1, (2019) 538–544. https://doi.org/10.1038/s42256-019-0101-9
  13. C. Matek, S. Krappe, C. Münzenmayer, T. Haferlach, C. Marr, Highly accurate differentiation of bone marrow cell morphologies using deep neural networks on a large image dataset, Blood. The Journal of the American Society of Hematology, 138(20), (2021) 1917-1927. https://doi.org/10.1182/blood.2020010568
  14. J.N. Kather, J. Krisam, P. Charoentong, T. Luedde, E. Herpel, C.A. Weis, T. Gaiser, A. Marx, N.A. Valous, D. Ferber, L. Jansen, Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study. PLoS Medicine, 16(1), (2019) e1002730. https://doi.org/10.1371/journal.pmed.1002730
  15. E. Arvaniti, K.S. Fricker, M. Moret, N. Rupp, T. Hermanns, C. Fankhauser, N. Wey, P.J. Wild, J.H. Rueschoff, M. Claassen, Automated Gleason grading of prostate cancer tissue microarrays via deep learning. Scientific reports, 8, (2018) 12054. https://doi.org/10.1038/s41598-018-30535-1
  16. G. Campanella, M.G. Hanna, L. Geneslaw, A. Miraflor, V. Werneck Krauss Silva, K.J. Busam, E. Brogi, V.E. Reuter, D.S. Klimstra, T.J. Fuchs, Clinical grade computational pathology using weakly supervised deep learning on whole slide images. Nature medicine, 25(8), (2019) 1301-1309. https://doi.org/10.1038/s41591-019-0508-1
  17. M.F. Pittenger, C. Kerr. (2014) Stem Cells, Tissue Engineering (Second Edition), 23–65. https://doi.org/10.1016/B978-0-12-420145-3.00002-X
  18. Q. Cai, H. Lan, Y. Deng, B. Xian, Z. Luo, J. Li, Z. Liao, Flow cytometry in acute myeloid leukemia and detection of minimal residual disease. Clinica Chimica Acta, 564, (2025) 119945. https://doi.org/10.1016/j.cca.2024.119945
  19. College of American Pathologists, What’s new in AML classification: WHO 2022 vs. International Consensus Classification. [Online]. Available: https://www.cap.org/member-resources/articles/whats-new-in-aml-classification-who-2022-vs-international-consensus-classification
  20. X. Zhang, J. Sun, W. Yu, J. Jin, Current views on the genetic landscape and management of variant acute promyelocytic leukemia. Biomarker Research, 9(1), (2021) 33. https://doi.org/10.1186/s40364-021-00284-x
  21. G. Cavallaro, S. Salmoiraghi, R. Cavagna, C. Pavoni, C. Belotti, M. Milani, E. Oldani, M. Frigeni, T. Intermesoli, A. Grassi, R. Bassan, Clinical impact of tyrosine kinases related mutations in NPM1 mutated acute myeloid leukaemia: A report from the Northern Italy Leukaemia Group (NILG) multicentre randomized trial 02/06, Leukemia Research, 153, (2025) 107702. https://doi.org/10.1016/j.leukres.2025.107702
  22. R.A.H. Abo Elwafa, M.M. ElBordiny, A. Deghedy, A. Elghandour, E.T. Ammar, The fusion genes and their relation with genetic variants in Egyptian AML patients. Asian Pacific Journal of Cancer Prevention: APJCP, 26 (3), (2025) 1069–1078. https://doi.org/10.31557/APJCP.2025.26.3.1069
  23. M. Gerritsen, R. Knops, B.L. Mandos, M. Decker, T. Ripperger, B.A. van der Reijden, J.H. Martens, J.H. Jansen, Acute myeloid leukemia associated RUNX1 variants induce aberrant expression of transcription factor TCF4. Leukemia, 39(2), (2025) 520–523. https://doi.org/10.1038/s41375-024-02470-w
  24. F. Lagunas-Rangel, V. Chávez-Valencia, M. Gómez-Guijosa, C. Cortés-Penagos, Acute myeloid leukemia—Genetic alterations and their clinical prognosis. International journal of hematology-oncology and stem cell research, 11(4), (2017) 328–329.
  25. V. Acharya, V. Ravi, T.D. Pham, C. Chakraborty, Peripheral blood smear analysis using automated computer-aided diagnosis system to identify acute myeloid leukemia. IEEE Transactions on Engineering Management, 70(8), (2023) 2760–2773. https://doi.org/10.1109/TEM.2021.3103549
  26. J. Rawat, A. Singh, J. Virmani, J.S. Devgun, Computer assisted classification framework for prediction of acute lymphoblastic and acute myeloblastic leukemia. Biocybernetics and Biomedical Engineering, 37(4), (2017) 637–654. https://doi.org/10.1016/j.bbe.2017.07.003
  27. T. Jiang, J.L. Gradus, A.J. Rosellini, Supervised machine learning: A brief primer. Behavior Therapy, 51(5), (2020) 675–687. https://doi.org/10.1016/j.beth.2020.05.002
  28. K.L. Narayanan, R.S. Krishnan, Y.H. Robinson, S. Vimal, T.A. Rashid, C. Kaushal, M.M. Hassan, Enhancing acute leukemia classification through hybrid fuzzy C means and random forest methods. Measurement: Sensors, 39, (2025) 101876. https://doi.org/10.1016/j.measen.2025.101876
  29. M. Shaheen, R. Khan, R.R. Biswal, M. Ullah, A. Khan, M.I. Uddin, M. Zareei, A. Waheed, Acute myeloid leukemia (AML) detection using AlexNet model, Complexity, 2021, (2021) 1–8. https://doi.org/10.1155/2021/6658192
  30. J. Zhao, M. Zhang, Z. Zhou, J. Chu, F. Cao, Automatic detection and classification of leukocytes using convolutional neural networks. Medical & biological engineering & computing, 55(8), (2017) 1287–1301. https://doi.org/10.1007/s11517-016-1590-x
  31. K. Liu, J. Hu, Classification of acute myeloid leukemia M1 and M2 subtypes using machine learning. Computers in Biology and Medicine, 147, (2022) 105741. https://doi.org/10.1016/j.compbiomed.2022.105741
  32. W. Yu, J. Chang, C. Yang, L. Zhang, H. Shen, Y. Xia, J. Sha, Automatic classification of leukocytes using deep neural network. In 2017 IEEE 12th international conference on ASIC (ASICON), IEEE, Guiyang, China, (2017) 1041–1044. https://doi.org/10.1109/ASICON.2017.8252657
  33. B. Subrahmanyeswara Rao, Accurate leukocoria predictor based on deep VGG-net CNN technique. IET Image Processing, 14(10), (2020) 2241–2248. https://doi.org/10.1049/iet-ipr.2018.6656
  34. N. Veeraiah, Y. Alotaibi, A.F. Subahi, MayGAN: Mayfly optimization with generative adversarial network-based deep learning method to classify leukemia from blood smear images. Computer Systems Science and Engineering, 46(2), (2023) 2039–2058. https://doi.org/10.32604/csse.2023.036985
  35. K. Venkatesh, S. Pasupathy, S.P. Raja, Acute myeloid leukemia multi-classification using enhanced few-shot learning technique. Scalable Computing: Practice and Experience, 23(4), (2022) 377–388. https://doi.org/10.12694/scpe.v23i4.2048
  36. L. Boldú, A. Merino, A. Acevedo, A. Molina, J. Rodellar, A deep learning model (ALNet) for the diagnosis of acute leukaemia lineage using peripheral blood cell images. Computer Methods and Programs in Biomedicine, 202, (2021) 105999. https://doi.org/10.1016/j.cmpb.2021.105999
  37. R. Agrawal, S. Satapathy, G. Bagla, K. Rajakumar. (2019) Detection of white blood cell cancer using image processing. In 2019 International Conference on Vision Towards Emerging Trends in Communication and Networking (ViTECoN), Vellore, India, 1–6. https://doi.org/10.1109/ViTECoN.2019.8899602
  38. F. Qin, N. Gao, Y. Peng, Z. Wu, S. Shen, A. Grudtsin, Fine-grained leukocyte classification with deep residual learning for microscopic images. Computer methods and programs in biomedicine, 162, (2018) 243–252. https://doi.org/10.1016/j.cmpb.2018.05.024
  39. N. Rohaziat, M.R.M. Tomari, W.N.W. Zakaria, (2022) White blood cells type detection using YOLOv5. In 2022 IEEE 5th international symposium in robotics and manufacturing automation (ROMA), IEEE, 1–6. https://doi.org/10.1109/ROMA55875.2022.9915690
  40. J.N. Eckardt, J.M. Middeke, S. Riechert, T. Schmittmann, A.S. Sulaiman, M. Kramer, K. Sockel, F. Kroschinsky, U. Schuler, J. Schetelig, C. Röllig, Deep learning detects acute myeloid leukemia and predicts NPM1 mutation status from bone marrow smears. Leukemia, 36(1), (2022) 111–118. https://doi.org/10.1038/s41375-021-01408-w
  41. L. Zare, M. Rahmani, N. Khaleghi, S. Sheykhivand, S. Danishvar, Automatic detection of acute leukemia (ALL and AML) utilizing customized deep graph convolutional neural networks. Bioengineering, 11(7), (2024) 644. https://doi.org/10.3390/bioengineering11070644
  42. N.K. Ramesh, V. Kadappa, R.D.D. Veerabhaskar, D.R. Sirigiri, P.T. Sreedhar, Deep learning architectures for detection of acute myeloid leukemia. International Journal of Computational Science and Engineering (IJCSE), 28(3), (2025) 278–291.
  43. V.J. Ramya, S. Lakshmi, Acute myelogenous leukemia detection using optimal neural network based on fractional black-widow model. Signal, Image and Video Processing, 16(1), (2022) 229–238. https://doi.org/10.1007/s11760-021-01976-5
  44. A.E. Aby, S. Salaji, K.K. Anilkumar, T. Rajan, Classification of acute myeloid leukemia by pre-trained deep neural networks: A comparison with different activation functions. Medical Engineering & Physics, 135, (2025) 104277. https://doi.org/10.1016/j.medengphy.2024.104277
  45. H. Patel, H. Shah, G. Patel, A. Patel, Hematologic cancer diagnosis and classification using machine and deep learning: State-of-the-art techniques and emerging research directives. Artificial Intelligence in Medicine, 152, (2024) 102883. https://doi.org/10.1016/j.artmed.2024.102883
  46. P.K. Das, A. Sahu, S. Meher, R. Panda, A. Abraham, Enhanced detection of acute leukemia: A hybrid machine learning framework with adaptive weight-optimized level set evolution. Engineering Applications of Artificial Intelligence, 161, Part C, (2025) 112244. https://doi.org/10.1016/j.engappai.2025.112244
  47. M. Hehr, A. Sadafi, C. Matek, P. Lienemann, C. Pohlkamp, T. Haferlach, K. Spiekermann, C. Marr, Explainable AI identifies diagnostic cells of genetic AML subtypes. PLOS Digit. Health, 2(3), (2023) e0000187. https://doi.org/10.1371/journal.pdig.0000187
  48. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L.C. Chen, (2018) MobilenetV2: Inverted residuals and linear bottlenecks, In Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, USA, 4510–4520. https://doi.org/10.1109/CVPR.2018.00474
  49. M.S A.P.U, Comparative Analysis of Suitability of Deep Learning Models in Quality Assurance of Fabrics. International Research Journal of Multidisciplinary Technovation, 7(4), (2025) 41–57. https://doi.org/10.54392/irjmt2544
  50. Q. Zhu, H. Zhuang, M. Zhao, S. Xu, R. Meng, A study on expression recognition based on improved MobileNetV2 network. Scientific Reports, 14(1), (2024) 8121.
  51. R. Shah, J. Shastri, M.H. Bohara, B.Y. Panchal, P. Goel. (2022) Detection of different types of blood cells: A comparative analysis. In 2022 IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE),IEEE, Ballari, India, 1–6. https://doi.org/10.1109/ICDCECE53908.2022.9793132
  52. S.T. Krishna, H.K. Kalluri, Deep learning and transfer learning approaches for image classification. International Journal of Recent Technology and Engineering (IJRTE), 7(5S4), (2019) 427–432.
  53. R. Kumari, J. Wasim, A deep learning approach for human facial expression recognition using residual network–101. Journal of Current Science and Technology. 13(3), (2023) 517–532. 2023. https://doi.org/10.59796/jcst.V13N3.2023.2152
  54. LearnDataSci, (2023) Hands-on transfer learning with Keras, [Online]. https://www.learndatasci.com/tutorials/hands-on-transfer-learning-keras/
  55. N. Syam, R. Kaul, Random forest, bagging, and boosting of decision trees, in Machine Learning and Artificial Intelligence in Marketing and Sales: Essential Reference for Practitioners and Data Scientists. Emerald Publishing Ltd., (2021) 139–182.
  56. M.A. Shames, M.Y. Kamil, Early Diagnosis of Lung Infection via Deep Learning Approach. International Research Journal of Multidisciplinary Technovation, 6(3), (2024) 216–224. https://doi.org/10.54392/irjmt24316