A Comparative Evaluation of Transfer Learning Techniques for White Blood Cell Detection

Skala Hassan Hussen; Shahab Wahab Kareem

doi:10.21271/ZJPAS.37.6.12

Authors

Skala Hassan Hussen Department of Software Engineering & Informatics, College of Engineering, Salahaddin University - Erbil, Erbil, Kurdistan Region, Iraq.
Shahab Wahab Kareem 1Technical Information System Engineering Dept., Erbil Technical Engineering College, Erbil Polytechnic University, 2Department of Computer Technical Engineering, Al-Qalam University College, Kirkuk, Iraq.

DOI:

https://doi.org/10.21271/ZJPAS.37.6.12

Keywords:

: Leukemia, Image preprocessing, Classification, Transfer learning, Deep learning

Abstract

Standard deep-learning (DL) and machine learning (ML) approaches are valuable frameworks in computer vision that improve the accuracy of medical image diagnosis and classification, including the identification of microscopic blood cells. This study examines the detection and categorization of acute leukemia in detail. Improving patient prognosis and treatment options requires early diagnosis, categorization, and accurate detection of white blood cells. Developing a precise and effective model for identifying and classifying malignancies in white blood cell (WBC) images remains challenging despite the widespread use of microscopes for blood cell examination and advancements in AI-based detection techniques. To address these challenges, the authors utilized a total of 48,000 images, comprising both public and private sources, after augmenting three classes of white blood cell (WBC) cells. This study aims to evaluate whether Vision Transformers can match or surpass the performance of convolutional neural networks (CNNs) for WBC classification using large-scale datasets, and to determine whether spatial inductive biases inherent in CNNs offer a measurable advantage, and achieved accuracies of 95.07%, 95.27%, 82.66%, 92.00%, and 83.59%., also creating an Ensemble model that combine three models(VGG19, Xception, and U-Net) running on gpu.v2-4090x4 server with RAM 384 GB because of volume of data which achieving accuracy of 92%, Also study proposed an architecture for deep learning that automatically recognizes and classifies WBC images, categorizing them into five types. The models for detection and classification techniques were also assessed using accuracy, F1 score, recall, and precision for each class of WBC.

References

Abdeldaim, A.M. et al. (2018) ‘Computer-aided acute lymphoblastic leukemia diagnosis system based on image analysis’, in Studies in Computational Intelligence. Springer Verlag, pp. 131–147. Available at: https://doi.org/10.1007/978-3-319-63754-9_7.

Ansari, S. et al. (2023) ‘A Customized Efficient Deep Learning Model for the Diagnosis of Acute Leukemia Cells Based on Lymphocyte and Monocyte Images’, Electronics (Switzerland), 12(2). Available at: https://doi.org/10.3390/electronics12020322.

Asgari Taghanaki, S. et al. (2021) ‘Deep semantic segmentation of natural and medical images: a review’, Artificial Intelligence Review, 54(1), pp. 137–178. Available at: https://doi.org/10.1007/s10462-020-09854-1.

Asghar, R. et al. (2024a) ‘Classification of white blood cells (leucocytes) from blood smear imagery using machine and deep learning models: A global scoping review’, PLoS ONE, 19(6). Available at: https://doi.org/10.1371/journal.pone.0292026.

Asghar, R. et al. (2024b) ‘Classification of white blood cells (leucocytes) from blood smear imagery using machine and deep learning models: A global scoping review’, PLoS ONE, 19(6). Available at: https://doi.org/10.1371/journal.pone.0292026.

Asghar, R. et al. (2024c) ‘Classification of white blood cells (leucocytes) from blood smear imagery using machine and deep learning models: A global scoping review’, PLoS ONE, 19(6). Available at: https://doi.org/10.1371/journal.pone.0292026.

Chen, J. et al. (2024) ‘Label-free white blood cells classification using a deep feature fusion neural network’, Heliyon, 10(11). Available at: https://doi.org/10.1016/j.heliyon.2024.e31496.

Crimi, A. and Bakas, S. (eds) (2022) Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. Cham: Springer International Publishing (Lecture Notes in Computer Science). Available at: https://doi.org/10.1007/978-3-031-08999-2.

Dai, W.C. et al. (2020) ‘CT Imaging and Differential Diagnosis of COVID-19’, Canadian Association of Radiologists Journal, 71(2), pp. 195–200. Available at: https://doi.org/10.1177/0846537120913033.

Darrin, M. et al. (2023) ‘Classification of red cell dynamics with convolutional and recurrent neural networks: a sickle cell disease case study’, Scientific Reports, 13(1). Available at: https://doi.org/10.1038/s41598-023-27718-w.

Derdour, Makhlouf., Ahmim, Marwa. and Benjedou, Amira. (2019) Proceedings, ICNAS 2019 : 4th International Conference on Networking and Advanced Systems : 26-27 June 2019. IEEE.

ELEN, A. and TURAN, M.K. (2019a) ‘Classifying White Blood Cells Using Machine Learning Algorithms’, Uluslararası Muhendislik Arastirma ve Gelistirme Dergisi, pp. 141–152. Available at: https://doi.org/10.29137/umagd.498372.

ELEN, A. and TURAN, M.K. (2019b) ‘Classifying White Blood Cells Using Machine Learning Algorithms’, Uluslararası Muhendislik Arastirma ve Gelistirme Dergisi, pp. 141–152. Available at: https://doi.org/10.29137/umagd.498372.

Elhassan, T.A. et al. (2023) ‘Classification of Atypical White Blood Cells in Acute Myeloid Leukemia Using a Two-Stage Hybrid Model Based on Deep Convolutional Autoencoder and Deep Convolutional Neural Network’, Diagnostics, 13(2). Available at: https://doi.org/10.3390/diagnostics13020196.

Fang, C., Di, W. and Cao, M. (2024) ‘On-chain federated learning approach for Internet of Vehicles’, in. SPIE-Intl Soc Optical Eng, p. 3. Available at: https://doi.org/10.1117/12.3031889.

Gu, X. et al. (2024) ‘Mobility-aware federated self-supervised learning in vehicular network’, Urban Lifeline, 2(1), p. 10. Available at: https://doi.org/10.1007/s44285-024-00020-5.

Gupta, D. et al. (2019) ‘Optimized Binary Bat algorithm for classification of white blood cells’, Measurement: Journal of the International Measurement Confederation, 143, pp. 180–190. Available at: https://doi.org/10.1016/j.measurement.2019.01.002.

Hawezi, R.S., Khoshaba, F.S. and Kareem, S.W. (2022) ‘A comparison of automated classification techniques for image processing in video internet of things’, Computers and Electrical Engineering, 101. Available at: https://doi.org/10.1016/j.compeleceng.2022.108074.

Jung, C. et al. (2019) ‘W-Net: A CNN-based Architecture for White Blood Cells Image Classification’. Available at: http://arxiv.org/abs/1910.01091.

Jung, C. et al. (2021) ‘White Blood Cells (WBC) Images Classification Using CNN-Based Networks’. Available at: https://doi.org/10.21203/rs.3.rs-1046210/v1.

Jung, C. et al. (2022) ‘WBC image classification and generative models based on convolutional neural network’, BMC Medical Imaging, 22(1). Available at: https://doi.org/10.1186/s12880-022-00818-1.

Kumar, D. et al. (2020) ‘Automatic Detection of White Blood Cancer from Bone Marrow Microscopic Images Using Convolutional Neural Networks’, IEEE Access, 8, pp. 142521–142531. Available at: https://doi.org/10.1109/ACCESS.2020.3012292.

Loey, M., Naman, M. and Zayed, H. (2020a) ‘Deep transfer learning in diagnosing leukemia in blood cells’, Computers, 9(2). Available at: https://doi.org/10.3390/computers9020029.

Loey, M., Naman, M. and Zayed, H. (2020b) ‘Deep transfer learning in diagnosing leukemia in blood cells’, Computers, 9(2). Available at: https://doi.org/10.3390/computers9020029.

Luong, D.T. et al. (2022) ‘Distinguish normal white blood cells from leukemia cells by detection, classification, and counting blood cells using YOLOv5’, in 2022 7th International Scientific Conference on Applying New Technology in Green Buildings, ATiGB 2022. Institute of Electrical and Electronics Engineers Inc., pp. 156–160. Available at: https://doi.org/10.1109/ATiGB56486.2022.9984098.

Nguyen, D.C. et al. (2021) ‘Federated Learning for Internet of Things: A Comprehensive Survey’, IEEE Communications Surveys and Tutorials. Institute of Electrical and Electronics Engineers Inc., pp. 1622–1658. Available at: https://doi.org/10.1109/COMST.2021.3075439.

Othman, M.Z., Mohammed, T.S. and Ali, A.B. (2017) Neural Network Classification of White Blood Cell using Microscopic Images, IJACSA) International Journal of Advanced Computer Science and Applications. Available at: www.ijacsa.thesai.org.

Prayitno et al. (2021) ‘A systematic review of federated learning in the healthcare area: From the perspective of data properties and applications’, Applied Sciences (Switzerland). MDPI. Available at: https://doi.org/10.3390/app112311191.

Prinyakupt, J. and Pluempitiwiriyawej, C. (2015) ‘Segmentation of white blood cells and comparison of cell morphology by linear and naïve Bayes classifiers’, BioMedical Engineering Online, 14(1). Available at: https://doi.org/10.1186/s12938-015-0037-1.

Qin, Yajie., Hong, Zhiliang. and Tang, T.-Ao. (2018) Proceedings 2017 IEEE 12th International Conference on ASIC : October 25-28, 2017, Guiyang, China. IEEE.

Sahlol, A.T., Kollmannsberger, P. and Ewees, A.A. (2020a) ‘Efficient Classification of White Blood Cell Leukemia with Improved Swarm Optimization of Deep Features’, Scientific Reports, 10(1). Available at: https://doi.org/10.1038/s41598-020-59215-9.

Sahlol, A.T., Kollmannsberger, P. and Ewees, A.A. (2020b) ‘Efficient Classification of White Blood Cell Leukemia with Improved Swarm Optimization of Deep Features’, Scientific Reports, 10(1). Available at: https://doi.org/10.1038/s41598-020-59215-9.

Saidani, O. et al. (2024) ‘White blood cells classification using multi-fold pre-processing and optimized CNN model’, Scientific Reports, 14(1). Available at: https://doi.org/10.1038/s41598-024-52880-0.

Şengür, A. et al. (2019a) White Blood Cell Classification Based on Shape and Deep Features; White Blood Cell Classification Based on Shape and Deep Features, 2019 International Artificial Intelligence and Data Processing Symposium (IDAP).

Şengür, A. et al. (2019b) White Blood Cell Classification Based on Shape and Deep Features; White Blood Cell Classification Based on Shape and Deep Features, 2019 International Artificial Intelligence and Data Processing Symposium (IDAP).

Shafique, S. and Tehsin, S. (2018) ‘Acute lymphoblastic leukemia detection and classification of its subtypes using pretrained deep convolutional neural networks’, Technology in Cancer Research and Treatment, 17, pp. 1–7. Available at: https://doi.org/10.1177/1533033818802789.

Sun, J. et al. (no date) FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective. Available at: https://github.com/jeremy313/FL-WBC.

Tamang, T., Baral, S. and Paing, M.P. (2022) ‘Classification of White Blood Cells: A Comprehensive Study Using Transfer Learning Based on Convolutional Neural Networks’, Diagnostics, 12(12). Available at: https://doi.org/10.3390/diagnostics12122903.

Vogado, L.H.S. et al. (2018) ‘Leukemia diagnosis in blood slides using transfer learning in CNNs and SVM for classification’, Engineering Applications of Artificial Intelligence, 72, pp. 415–422. Available at: https://doi.org/10.1016/j.engappai.2018.04.024.

Zolfaghari, M. and Sajedi, H. (2022) ‘A survey on automated detection and classification of acute leukemia and WBCs in microscopic blood cells’, Multimedia Tools and Applications, 81(5), pp. 6723–6753. Available at: https://doi.org/10.1007/s11042-022-12108-7.

Zou, Y., Wu, L., Zuo, C., Chen, L., Zhou, B., & Zhang, H. (2025). White blood cell classification network using MobileNetv2 with multiscale feature extraction module and attention mechanism. Biomedical Signal Processing and Control, 99, 106820.

Duc, M. L., Bilik, P., & Martinek, R. (2025). White blood cell classification using multi-hop attention graph neural networks. Expert Systems with Applications, 126725.

Kim, H., Kweon, O. J., Yoon, S., Lim, Y. K., & Kim, B. (2025). Performance of the automated digital cell image analyzer UIMD PBIA in white blood cell classification: a comparative study with sysmex DI-60. Clinical Chemistry and Laboratory Medicine (CCLM), (0).

Sutabri, T., & Putra, C. A. (2025). White Blood Cell Classification Using SMOTE-SVM Method with Hybrid Feature Extraction and Image Segmentation Using Gaussian Mixture Model. ECTI Transactions on Computer and Information Technology (ECTI-CIT), 19(1), 75-87.

ABDULLAH, S. B. & AL-ATTAR, M. S. 2023. Association of CYP1A1*2C Variant (Ile464Val Polymorphism) and Some Hematological Parameters with Acute Myeloid Leukemia (AML) and Chronic Myeloid Leukemia (CML) in Erbil-Iraq. ZANCO JOURNAL OF PURE AND APPLIED SCIENCES.

HUSSEIN AND KAREEM 2023. Demonstration of tissue and peripheral blood eosinophils in patients with acute appendicitis. ZANCO JOURNAL OF PURE AND APPLIED SCIENCES.

OSMAN, H. M. & YABA, S. P. 2022. Automated segmentation of Acute Lymphocytic Leukemia (ALL) subtypes by the combination of color space conversion and K-means cluster. ZANCO JOURNAL OF PURE AND APPLIED SCIENCES.

YOUSIF, R.-H. A., MOHAMED, Z. A., POLUS, R. K., YASSIN, A. K., HASAN, K. M., ABDULLA, B. K., MOHAMMED, N. S., GETTA, H. A., JALAL, S. D., SHAMOON, R. P. & ABDULLAH, D. A. 2022. CLL-366 Comorbidities and Treatment Decisions in Newly Diagnosed CLL Patients Across All Disease Stages in the Kurdistan Region of Iraq. Clinical lymphoma, myeloma & leukemia, 22 Suppl 2, S276.