Deep Learning Applications in Hematology: Optimizing Accuracy and Robustness of Blood Cell Counting and Classification

Ghazwan A. Al-Zaidi; Bashar S. Falih; Maryam I Nassar; Adil Ibrahim Khalil; Alhaji Osman Bah

doi:10.35377/saucis...1866886

Deep Learning Applications in Hematology: Optimizing Accuracy and Robustness of Blood Cell Counting and Classification

Abstract

Processing time, variability, and accuracy are the most significant limitations of traditional methods to determine the type and count of blood cells. These limitations could be addressed by using machine learning algorithms. Advanced YOLO architectures are among the most prominent of these technologies. This study aims to compare the performance of YOLOv11 and YOLOv12 models. Additionally, the impact of attention mechanisms on detection performance and the reduction of errors caused by cell overlap and interference were analyzed. Therefore, YOLOv11 and YOLOv12 models were applied to the BCCD dataset to detect, classify, and count blood cells (RBCs, WBCs, and platelets). Data augmentation strategies were implemented to increase the training dataset size. Both models were trained using a learning rate of 0.001, a batch size of 16, and 100 training epochs. The results showed that the YOLOv12 model achieved slightly higher numerical performance than YOLOv11 by achieving a validation mAP@50 value of 95.3% and a validation recall rate of 95.2%. The statistical results indicated that these differences were not statistically significant (p = 0.312). Therefore, both models provide comparable performance on the BCCD dataset. These findings suggest that both models are suitable for automated blood cell detection. However, larger and more diverse datasets are required to determine whether the observed numerical improvements generalize to broader clinical settings.

Keywords

Ethical Statement

It is declared that during the preparation process of this study, scientific and ethical principles were followed, and all the studies benefited from are stated in the bibliography.

References

B. George-Gay and K. Parker, “Understanding the complete blood count with differential,” J. Perianesth. Nurs., vol. 18, no. 2, pp. 96–117, Apr. 2003, doi: 10.1053/jpan.2003.50013.
S. W. Lockley, L. K. Barger, N. T. Ayas, J. M. Rothschild, C. A. Czeisler, and C. P. Landrigan, “Effects of health care provider work hours and sleep deprivation on safety and performance,” Jt. Comm. J. Qual. Patient Saf., vol. 33, no. 11, suppl., pp. 7–18, Nov. 2007, doi: 10.1016/S1553-7250(07)33109-7.
M. Maitra, R. K. Gupta, and M. Mukherjee, “Detection and counting of red blood cells in blood cell images using Hough transform,” Int. J. Comput. Appl., vol. 53, no. 16, Sep. 2012, doi: 10.5120/8505-2274.
G. Moallem, A. A. Pore, A. Gangadhar, H. Sari-Sarraf, and S. A. Vanapalli, “Detection of live breast cancer cells in bright-field microscopy images containing white blood cells by image analysis and deep learning,” J. Biomed. Opt., vol. 27, no. 7, Art. no. 076003, Jul. 2022, doi: 10.1117/1.JBO.27.7.076003.
N. Zaman et al., “Deep learning models for classification of red blood cells in microscopy images for anemia diagnosis,” in Proc. 2024 IEEE Int. Conf. Comput., Appl. Syst. (COMPAS), 2024, doi: 10.1109/COMPAS60761.2024.10797203.
L. Kamal and R. J. R. Raj, “Harnessing deep learning for blood quality assurance through complete blood cell count detection,” e-Prime–Adv. Electr. Eng., Electron. Energy, vol. 7, Art. no. 100450, Mar. 2024, doi: 10.1016/j.prime.2024.100450.
O. Katar and İ. F. Kılınçer, “Automatic classification of white blood cells using pre-trained deep models,” Sakarya Univ. J. Comput. Inf. Sci., vol. 5, no. 3, pp. 462–476, Dec. 2022, doi: 10.35377/saucis...1196934.
G. Drałus, D. Mazur, and A. Czmil, “Automatic detection and counting of blood cells in smear images using RetinaNet,” Entropy, vol. 23, no. 11, Art. no. 1522, Nov. 2021, doi: 10.3390/e23111522.

L. B. Eriksson, M. B. Eriksson, T. Gordh, and A. O. Larsson, “Significant associations between blood cell counts and plasma cytokines, chemokines, and growth factors,” Int. J. Mol. Sci., vol. 26, no. 9, Art. no. 4065, Apr. 2025, doi: 10.3390/ijms26094065.
Z. Jiang, X. Liu, Z. Yan, W. Gu, and J. Jiang, “Improved detection performance in blood cell count by an attention-guided deep learning method,” OSA Continuum, vol. 4, no. 2, pp. 323–333, Feb. 2021, doi: 10.1364/OSAC.413787.
S. Choudhary et al., “Advancing blood cell detection and classification: Performance evaluation of modern deep learning models,” BMC Med. Inform. Decis. Mak., vol. 25, Art. no. 207, Jun. 2025, doi: 10.1186/s12911-025-03027-2.
D. Wang, M. Hwang, W.-C. Jiang, K. Ding, H.-C. Chang, and K.-S. Hwang, “A deep learning method for counting white blood cells in bone marrow images,” BMC Bioinformatics, vol. 22, suppl. 5, Art. no. 94, 2021, doi: 10.1186/s12859-021-04003-z.
H. A. Aliyu, M. A. A. Razak, R. Sudirman, and N. Ramli, “A deep learning AlexNet model for classification of red blood cells in sickle cell anemia,” IAES Int. J. Artif. Intell., vol. 9, no. 2, pp. 221–228, Jun. 2020, doi: 10.11591/ijai.v9.i2.pp221-228.
F. Xu, X. Li, H. Yang, Y. Wang, and W. Xiang, “TE-YOLOF: Tiny and efficient YOLOF for blood cell detection,” Biomed. Signal Process. Control, vol. 73, Art. no. 103416, Mar. 2022, doi: 10.1016/j.bspc.2021.103416.
C. Liu, D. Li, and P. Huang, “ISE-YOLO: Improved squeeze-and-excitation attention module based YOLO for blood cells detection,” in Proc. 2021 IEEE Int. Conf. Big Data (Big Data), 2021, pp. 3911–3916.
Y. Wang, L. Pan, and X. Shu, “YOLO-FMS: A lightweight and efficient model for medical microscopic smear detection,” IEEE Access, vol. 12, pp. 125253–125265, 2024, doi: 10.1109/ACCESS.2024.3455555.
Shenggan, 2017, “BCCD Dataset,” GitHub. [Online]. Available: https://github.com/Shenggan/BCCD Dataset
S. Bayat Toksöz, G. Işık, G. Şahin, and E. Akin, “Parameter-efficient fine-tuning for photovoltaic cell defect classification: A systematic comparison of LoRA, QLoRA, and full fine-tuning on ConvNeXt-Tiny,” Sensors, vol. 26, no. 12, Art. no. 3659, Jun. 2026, doi: 10.3390/s26123659.
S. Bayat Toksöz, G. Işık, G. Şahin, and E. Akin, “Evaluating convolutional and transformer architectures for photovoltaic defect classification via electroluminescence imagery,” Sensors, vol. 26, no. 12, Art. no. 3775, Jun. 2026, doi: 10.3390/s26123775.
S. Bayat Toksöz and G. Işık, “SQ-LoRA: Memory-efficient language model compression through stable-rank-guided quantization for edge computing applications,” Appl. Sci., vol. 16, no. 4, Art. no. 2113, Feb. 2026, doi: 10.3390/app16042113.
C. Shorten and T. M. Khoshgoftaar, ”A survey on image data augmentation for deep learning,” Journal of Big Data, vol. 6, no. 1, pp. 1–48, 2019.
R. Sapkota, Z. Meng, M. Churuvija, X. Du, Z. Ma, and M. Karkee, “Comprehensive performance evaluation of YOLOv12, YOLO11, YOLOv10, YOLOv9 and YOLOv8 on detecting and counting fruitlet in complex orchard environments,” Agriculture Communications, vol. 4, no. 1, Art. no. 100125, Mar. 2026, doi: 10.1016/j.agrcom.2026.100125.
T. Zhang, B. Luo, A. Sharda, and G. Wang, “Dynamic label assignment for object detection by combining predicted IoUs and anchor IoUs,” J. Imaging, vol. 8, no. 7, Art. no. 193, Jul. 2022, doi: 10.3390/jimaging8070193.
Y. Tian, Q. Ye, and D. Doermann, “YOLOv12: Attention-centric real-time object detectors,” arXiv:2502.12524, Feb. 2025, doi: 10.48550/arXiv.2502.12524.
Y.-D. Jeon et al., “Deep learning model based on You Only Look Once algorithm for detection and visualization of fracture areas in three-dimensional skeletal images,” Diagnostics, vol. 14, no. 1, Art. no. 11, 2024, doi: 10.3390/diagnostics14010011.
C.-K. Chou et al., “Evaluation of spectrum-aided visual enhancer (SAVE) in esophageal cancer detection using YOLO frameworks,” Diagnostics, vol. 14, no. 11, Art. no. 1129, May 2024, doi: 10.3390/diagnostics14111129.
A. Sahafi, A. Koulaouzidis, and M. Lalinia, “Polypoid lesion segmentation using YOLO-V8 network in wireless video capsule endoscopy images,” Diagnostics, vol. 14, no. 5, Art. no. 474, Feb. 2024, doi: 10.3390/diagnostics14050474.
A. Shakarami, M. B. Menhaj, A. Mahdavi-Hormat, and H. Tarrah, “A fast and yet efficient YOLOv3 for blood cell detection,” Biomed. Signal Process. Control, vol. 66, Art. no. 102495, Apr. 2021, doi: 10.1016/j.bspc.2021.102495.
Y. Mao, H. Zhang, W. Wu, X. Gao, Z. Lin, and J. Lin, “DWS-YOLO: A lightweight detector for blood cell detection,” Appl. Artif. Intell., vol. 38, no. 1, Art. no. 2318673, 2024, doi: 10.1080/08839514.2024.2318673.
H. Sazak and M. Kotan, “Automated blood cell detection and classification in microscopic images using YOLOv11 and optimized weights,” Diagnostics, vol. 15, no. 1, Art. no. 22, 2025, doi: 10.3390/diagnostics15010022.

Details

Primary Language

English

Subjects

Computing Applications in Health

Journal Section

Research Article

Authors

Ghazwan A. Al-Zaidi
0009-0000-8409-6764
Iraq

Bashar S. Falih
0000-0001-6592-0500
Iraq

Maryam I Nassar
0009-0003-2220-8937
Iraq

Adil Ibrahim Khalil ^*
0000-0003-3379-0603
Iraq

Alhaji Osman Bah
0000-0002-3995-9468
Sierra Leone

Early Pub Date

October 28, 2026

Publication Date

October 30, 2026

Submission Date

January 26, 2026

Acceptance Date

August 25, 2026

Published in Issue

Year 2026 Volume: 9 Number: 5

DOI

https://doi.org/10.35377/saucis...1866886

IZ

https://izlik.org/JA49RP66AF

Cite

RIS / Bibtex

APA

A. Al-Zaidi, G., S. Falih, B., Nassar, M. I., Ibrahim Khalil, A., & Bah, A. O. (2026). Deep Learning Applications in Hematology: Optimizing Accuracy and Robustness of Blood Cell Counting and Classification. Sakarya University Journal of Computer and Information Sciences, 9(5), 1607-1615. https://doi.org/10.35377/saucis...1866886

AMA

1.A. Al-Zaidi G, S. Falih B, Nassar MI, Ibrahim Khalil A, Bah AO. Deep Learning Applications in Hematology: Optimizing Accuracy and Robustness of Blood Cell Counting and Classification. SAUCIS. 2026;9(5):1607-1615. doi:10.35377/saucis.1866886

Chicago

A. Al-Zaidi, Ghazwan, Bashar S. Falih, Maryam I Nassar, Adil Ibrahim Khalil, and Alhaji Osman Bah. 2026. “Deep Learning Applications in Hematology: Optimizing Accuracy and Robustness of Blood Cell Counting and Classification”. Sakarya University Journal of Computer and Information Sciences 9 (5): 1607-15. https://doi.org/10.35377/saucis. 1866886.

EndNote

A. Al-Zaidi G, S. Falih B, Nassar MI, Ibrahim Khalil A, Bah AO (October 1, 2026) Deep Learning Applications in Hematology: Optimizing Accuracy and Robustness of Blood Cell Counting and Classification. Sakarya University Journal of Computer and Information Sciences 9 5 1607–1615.

IEEE

[1]G. A. Al-Zaidi, B. S. Falih, M. I. Nassar, A. Ibrahim Khalil, and A. O. Bah, “Deep Learning Applications in Hematology: Optimizing Accuracy and Robustness of Blood Cell Counting and Classification”, SAUCIS, vol. 9, no. 5, pp. 1607–1615, Oct. 2026, doi: 10.35377/saucis...1866886.

ISNAD

A. Al-Zaidi, Ghazwan - S. Falih, Bashar - Nassar, Maryam I - Ibrahim Khalil, Adil - Bah, Alhaji Osman. “Deep Learning Applications in Hematology: Optimizing Accuracy and Robustness of Blood Cell Counting and Classification”. Sakarya University Journal of Computer and Information Sciences 9/5 (October 1, 2026): 1607-1615. https://doi.org/10.35377/saucis. 1866886.

JAMA

1.A. Al-Zaidi G, S. Falih B, Nassar MI, Ibrahim Khalil A, Bah AO. Deep Learning Applications in Hematology: Optimizing Accuracy and Robustness of Blood Cell Counting and Classification. SAUCIS. 2026;9:1607–1615.

MLA

A. Al-Zaidi, Ghazwan, et al. “Deep Learning Applications in Hematology: Optimizing Accuracy and Robustness of Blood Cell Counting and Classification”. Sakarya University Journal of Computer and Information Sciences, vol. 9, no. 5, Oct. 2026, pp. 1607-15, doi:10.35377/saucis. 1866886.

Vancouver

1.Ghazwan A. Al-Zaidi, Bashar S. Falih, Maryam I Nassar, Adil Ibrahim Khalil, Alhaji Osman Bah. Deep Learning Applications in Hematology: Optimizing Accuracy and Robustness of Blood Cell Counting and Classification. SAUCIS. 2026 Oct. 1;9(5):1607-15. doi:10.35377/saucis. 1866886