FEW-SHOT LEARNING FOR AML CELL CLASSIFICATION USING PROTOTYPICAL
Keywords:
Few shots learning, Acute myeloid leukemia, Prototypical networks, ClassificationAbstract
Accurate blood cell classification is crucial for diagnosing Acute Myeloid Leukemia (AML) but limited medical data poses challenges for traditional machine learning models. This study presents a Few-Shot Learning (FSL) framework utilizing a Prototypical Network architecture with a ResNet-34 backbone to classify AML blood cell types from microscopic images. In this study, we utilize datasets consisting of 15 morphologically distinct cell classes. A 15-way, 5-shot, 5-query episodic setup was adopted to simulate data-scarce conditions. Evaluation via 5-fold cross-validation yielded strong performance, with an average accuracy of 97.76%, precision of 98.78%, recall of 96.55%, and F1-score of 97.76%. FSL training times were consistent (4.22–4.26 minutes per fold), and t-SNE along with confusion matrices confirmed the model’s ability to distinguish similar cell types. To validate the approach, its performance was compared with a conventional supervised CNN using the same ResNet-34 backbone. The FSL model outperformed the CNN across all metrics such as accuracy (98.32% vs. 77.25%), precision (98.55% vs. 76.87%), recall (98.31% vs. 78.66%), and F1-score (98.33% vs. 75.26%), while also requiring far less training time (~4.24 min/fold vs. ~420 min total). These results highlight the promise of FSL based methods for accurate, efficient, and scalable hematologic diagnostics in data limited settings.
References
P. Han Yu, Z. Yan Zhang, Y. Yuan Kang, P. Huang, C. Yang, and H. Naranmandura, “Acute myeloid leukemia with t(8;21) translocation: Molecular pathogenesis, potential therapeutics and future directions,” Biochem Pharmacol, vol. 233, p. 116774, Mar. 2025, doi: 10.1016/J.BCP.2025.116774.
Z. Koolivand, F. Bahreini, E. Rayzan, and N. Rezaei, “Inducing apoptosis in acute myeloid leukemia; mechanisms and limitations,” Heliyon, vol. 11, no. 1, p. e41355, Jan. 2025, doi: 10.1016/J.HELIYON.2024.E41355.
R. F. Schlenk, “Acute myeloid leukemia: introduction to a series highlighting progress and ongoing challenges,” Feb. 01, 2023, Ferrata Storti Foundation. doi: 10.3324/haematol.2022.280803.
D. Chen, S. Bansal, A. Mitchell, A. M. Tierens, A. G. X. Zeng, and J. E. Dick, “Isomarker: An Explainable Machine Learning Framework for Identification of Cell State Markers in Acute Myeloid Leukemia,” Blood, vol. 144, no. Supplement 1, p. 1542, Nov. 2024, doi: 10.1182/BLOOD-2024-210986.
D. Malani et al., “Implementing a Functional Precision Medicine Tumor Board for Acute Myeloid Leukemia,” Cancer Discov, vol. 12, no. 2, pp. 388–401, Feb. 2022, doi: 10.1158/2159-8290.CD-21-0410.
M. S. Alim et al., “Integrating convolutional neural networks for microscopic image analysis in acute lymphoblastic leukemia classification: A deep learning approach for enhanced diagnostic precision,” Systems and Soft Computing, vol. 6, p. 200121, Dec. 2024, doi: 10.1016/J.SASC.2024.200121.
B. Priscilla et al., “AML-685 Leveraging Machine Learning for Rapid and Accurate Diagnosis of Acute Leukemia,” Clin Lymphoma Myeloma Leuk, vol. 24, p. S330, Sep. 2024, doi: 10.1016/S2152-2650(24)01232-1.
H. Yin et al., “Classification of normal, AML, and ALL bone marrow smears based on deep learning and hyperspectral microscopic imaging,” Sens Actuators B Chem, vol. 438, p. 137800, Sep. 2025, doi: 10.1016/J.SNB.2025.137800.
M. A. Alsalem et al., “A review of the automated detection and classification of acute leukaemia: Coherent taxonomy, datasets, validation and performance measurements, motivation, open challenges and recommendations,” Comput Methods Programs Biomed, vol. 158, pp. 93–112, May 2018, doi: 10.1016/J.CMPB.2018.02.005.
R. Saikia, R. Deka, A. Sarma, N. H. Singh, M. A. Khan, and S. S. Devi, “VNLU-Net: Visual Network with Lightweight Union-net for Acute Myeloid Leukemia Detection on Heterogeneous Dataset,” Biomed Signal Process Control, vol. 107, p. 107840, Sep. 2025, doi: 10.1016/J.BSPC.2025.107840.
S. Das et al., “Marine Predators Algorithm with Deep Learning-Based Leukemia Cancer Classification on Medical Images,” CMES - Computer Modeling in Engineering and Sciences, vol. 141, no. 1, pp. 893–916, Aug. 2024, doi: 10.32604/CMES.2024.051856.
T. Zhang and G. Xue, “Fuzzy attention-based deep neural networks for acute lymphoblastic leukemia diagnosis,” Appl Soft Comput, vol. 171, p. 112810, Mar. 2025, doi: 10.1016/J.ASOC.2025.112810.
H. M. Rai et al., “Deep Learning for Leukemia Classification: Performance Analysis and Challenges Across Multiple Architectures,” Fractal and Fractional, vol. 9, no. 6, 2025, doi: 10.3390/fractalfract9060337.
J. N. Eckardt et al., “Deep learning detects acute myeloid leukemia and predicts NPM1 mutation status from bone marrow smears,” Leukemia, vol. 36, no. 1, pp. 111–118, Jan. 2022, doi: 10.1038/s41375-021-01408-w.
J. E. Lewis, L. A. D. Cooper, D. L. Jaye, and O. Pozdnyakova, “Automated Deep Learning-Based Diagnosis and Molecular Characterization of Acute Myeloid Leukemia Using Flow Cytometry,” Modern Pathology, vol. 37, no. 1, p. 100373, Jan. 2024, doi: 10.1016/J.MODPAT.2023.100373.
H. M. Rai et al., “Deep Learning for Leukemia Classification: Performance Analysis and Challenges Across Multiple Architectures,” Fractal and Fractional, vol. 9, no. 6, p. 337, May 2025, doi: 10.3390/fractalfract9060337.
T. F. Isaka, J. Courtney, and C. Wynne, “Addressing Class Imbalance Issues in Haematological Images using Repeat Factor Sampling,” in ICAAI 2024 - Conference Proceedings of the 2024 8th International Conference on Advances in Artificial Intelligence, Association for Computing Machinery, Inc, Mar. 2025, pp. 21–27. doi: 10.1145/3704137.3704141.
D. S. Depto, M. M. Rizvee, A. Rahman, H. Zunair, M. S. Rahman, and M. R. C. Mahdy, “Quantifying imbalanced classification methods for leukemia detection,” Comput Biol Med, vol. 152, p. 106372, Jan. 2023, doi: 10.1016/J.COMPBIOMED.2022.106372.
B. H. M. van der Velden, H. J. Kuijf, K. G. A. Gilhuijs, and M. A. Viergever, “Explainable artificial intelligence (XAI) in deep learning-based medical image analysis,” Jul. 01, 2022, Elsevier B.V. doi: 10.1016/j.media.2022.102470.
O. Elharrouss, Y. Akbari, N. Almadeed, and S. Al-Maadeed, “Backbones-review: Feature extractor networks for deep learning and deep reinforcement learning approaches in computer vision,” Comput Sci Rev, vol. 53, p. 100645, Aug. 2024, doi: 10.1016/J.COSREV.2024.100645.
E. Pachetti and S. Colantonio, “A systematic review of few-shot learning in medical imaging,” Artif Intell Med, vol. 156, p. 102949, Oct. 2024, doi: 10.1016/J.ARTMED.2024.102949.
A. Ouahab and O. Ben Ahmed, “ProtoMed: Prototypical networks with auxiliary regularization for few-shot medical image classification,” Image Vis Comput, vol. 154, Feb. 2025, doi: 10.1016/j.imavis.2024.105337.
G. Işık and İ. Paçal, “Few-shot classification of ultrasound breast cancer images using meta-learning algorithms,” Neural Comput Appl, vol. 36, no. 20, pp. 12047–12059, Jul. 2024, doi: 10.1007/s00521-024-09767-y.
H. M. Imran, M. A. Al Asad, T. A. Abdullah, S. I. Chowdhury, and M. Alamin, “Few Shot Learning for Medical Imaging: A Review of Categorized Images,” in 2023 IEEE 7th Conference on Information and Communication Technology (CICT), 2023, pp. 1–7. doi: 10.1109/CICT59886.2023.10455365.
T. Dissanayake, Y. George, D. Mahapatra, S. Sridharan, C. Fookes, and Z. Ge, “Few-Shot Learning for Medical Image Segmentation: A Review and Comparative Study,” ACM Comput. Surv., Jun. 2025, doi: 10.1145/3746224.
Y. Ge, Y. Guo, S. Das, M. A. Al-Garadi, and A. Sarker, “Few-shot learning for medical text: A review of advances, trends, and opportunities,” J Biomed Inform, vol. 144, p. 104458, Aug. 2023, doi: 10.1016/J.JBI.2023.104458.
T. Dissanayake, Y. George, D. Mahapatra, S. Sridharan, C. Fookes, and Z. Ge, “Few-Shot Learning for Medical Image Segmentation: A Review and Comparative Study,” ACM Comput. Surv., Jun. 2025, doi: 10.1145/3746224.
E. Pachetti and S. Colantonio, “A systematic review of few-shot learning in medical imaging,” Artif Intell Med, vol. 156, p. 102949, Oct. 2024, doi: 10.1016/J.ARTMED.2024.102949.
C. , S. S. , M. C. , & S. K. Matek, “A Single-cell Morphological Dataset of Leukocytes from AML Patients and Non-malignant Controls [Data set],” The Cancer Imaging Archive, 2019, doi: https://doi.org/10.7937/tcia.2019.36f5o9ld.
J. Snell, K. Swersky, and R. Zemel, “Prototypical networks for few-shot learning,” in Proceedings of the 31st International Conference on Neural Information Processing Systems, in NIPS’17. Red Hook, NY, USA: Curran Associates Inc., 2017, pp. 4080–4090.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. doi: 10.1109/CVPR.2016.90.
S. Caltagirone and D. Frincke, “ADAM: Active Defense Algorithm and Model,” Aggressive Network Self-Defense, pp. 287–311, Jan. 2005, doi: 10.1016/B978-193183620-3/50014-2.
T. Fawcett, “An introduction to ROC analysis,” Pattern Recognit Lett, vol. 27, no. 8, pp. 861–874, Jun. 2006, doi: 10.1016/j.patrec.2005.10.010.
K. Hajian-Tilaki, “Receiver Operating Characteristic (ROC) Curve Analysis for Medical Diagnostic Test Evaluation,” 2013.
M. Akhavan Anvari, D. Rahmati, and S. Kumar, “t-Distributed stochastic neighbor embedding,” Dimensionality Reduction in Machine Learning, pp. 187–207, Jan. 2025, doi: 10.1016/B978-0-44-332818-3.00017-
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 I Gde Eka Dirgayussa, Kevin Elfancyus Herman, Doni Bowo Nugroho, Sekar Asri Tresnaningtyas, Meita Mahardianti, Nurul Maulidiyah, Rafli Filano, Rudi Setiawan, Muhammad Artha Jabatsudewa Maras, Yohanssen Pratama
This work is licensed under a Creative Commons Attribution 4.0 International License.
