A Reproducible Deep Learning Pipeline for Augmentation-Enhanced Classification of Anemia-Related Blood-Cell Images
Received: 24 April 2026 | Revised: 13 May 2026, 24 May 2026, 25 May 2026, 3 June 2026, and 4 June 2026 | Accepted: 5 June 2026 | Online: 26 June 2026
Corresponding author: Divya Saleela
Abstract
This study presents a reproducible end-to-end deep learning pipeline for proof-of-concept classification of anemia-related and control-like blood cell images using a publicly accessible online dataset. The workflow integrates online data download, automatic extraction, dataset restructuring, class balancing, augmentation-enhanced preprocessing, transfer-learning-based model training, visualization, and structured metric generation within a single executable framework. A balanced binary dataset was constructed to reduce the effect of severe class imbalance, and augmentation strategies, including flipping, rotation, color jitter, and affine transformation, were applied only during training. A ResNet18-based classifier showed strong convergence under a fixed random seed and single train-validation-test split. On a small held-out test subset of 32 images, all images were correctly classified. However, this result should be interpreted cautiously because the test subset was small, no cross-validation or external validation was performed, and performance on limited balanced data may overestimate generalizability. Class-distribution plots, representative sample panels, learning curves, confusion matrices, prediction files, and metric summaries support transparent inspection and reproducibility. The main contribution of this study is a reproducible engineering workflow for blood-cell image classification, rather than a claim of algorithmic novelty or clinical readiness.
Keywords:
blood cell image classification, deep learning, reproducible pipeline, data augmentation, class balancing, ResNet18, hematology imaging, medical image analysisReferences
[1] M. A. Warner and A. C. Weyand, "The Global Burden of Anemia," in Blood Substitutes and Oxygen Biotherapeutics, H. Liu, A. D. Kaye, and J. S. Jahr, Eds. Springer International Publishing, 2022, pp. 53–59.
[2] K. T. Navya, K. Prasad, and B. M. K. Singh, "Analysis of red blood cells from peripheral blood smear images for anemia detection: a methodological review," Medical & Biological Engineering & Computing, vol. 60, no. 9, pp. 2445–2462, Sept. 2022.
[3] A. Husham, M. Hazim Alkawaz, T. Saba, A. Rehman, and J. Saleh Alghamdi, "Automated nuclei segmentation of malignant using level sets," Microscopy Research and Technique, vol. 79, no. 10, pp. 993–997, Oct. 2016.
[4] S. Divya, L. P. Suresh, and A. John, "A Deep Transfer Learning framework for Multi Class Brain Tumor Classification using MRI," in 2020 2nd International Conference on Advances in Computing, Communication Control and Networking (ICACCCN), Dec. 2020, pp. 283–290.
[5] L. Alzubaidi, M. A. Fadhel, O. Al-Shamma, J. Zhang, and Y. Duan, "Deep Learning Models for Classification of Red Blood Cells in Microscopy Images to Aid in Sickle Cell Anemia Diagnosis," Electronics, vol. 9, no. 3, Mar. 2020, Art. no. 427.
[6] M. M. Alam and M. T. Islam, "Machine learning approach of automatic identification and counting of blood cells," Healthcare Technology Letters, vol. 6, no. 4, pp. 103–108, Aug. 2019.
[7] S. Sharma and D. Dudeja, "Towards Intelligent Anemia Detection: An Empirical Analysis of Clinical and Imaging-Based Machine Learning Approaches," in 2025 IEEE 7th International Conference on Computing, Communication and Automation (ICCCA), Nov. 2025, pp. 1–6.
[8] K. K. Mohammed, N. Dahmani, R. Ahmed, A. Darwish, and A. E. Hassanien, "An Explainable AI and Optimized Multi-Branch Convolutional Neural Network Model for Eye Anemia Diagnosis," IEEE Access, vol. 13, pp. 71840–71857, 2025.
[9] J. B. Lazaro, J. C. Dela Cruz, and J. F. Villaverde, "An adaptive filter for anemia screening using deep convolutional neural network," Franklin Open, vol. 12, Sept. 2025, Art. no. 100345.
[10] A. A. Mahmud, P. Chowdhury, M. B. Uddin, K. E. Delowar, T. R. Talha, and B. Dewanjee, "AI-Driven anemia diagnosis: A review of advanced models and techniques." arXiv, 2025.
[11] Y. Tewachew, D. Dagneb, M. Andualem, and Y. Mekuriaw, "Predicting the Level of Anemia among Ethiopian Neonatal Using Ensemble Machine Learning Algorithms." In Review, Feb. 09, 2026.
[12] K. Malarkodi, "AnemiaX: A Predictive Intelligence Model for Hematological Health," in 2025 3rd International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI), Sept. 2025, pp. 162–168.
[13] M. Karimi et al., "Feature Selection Methods in Big Medical Databases:A Comprehensive Survey," International Journal of Theoritical & Applied Computational Intelligence, pp. 181–209, 2025.
[14] M. A. Khan, M. I. Sharif, M. Raza, A. Anjum, T. Saba, and S. A. Shad, "Skin lesion segmentation and classification: A unified framework of deep neural network features fusion and selection," Expert Systems, vol. 39, no. 7, Aug. 2022, Art. no. e12497.
[15] N. H. Q. Nguyen and A. C. Phan, "Explainable AI-Based Approach for Automated Blood Cell Classification," in Advances in Information and Communication Technology, vol. 1831, T. X. Tu, P. T. Nghia, N. T. Thuy, V. D. Thai, L. H. Son, and N. Van Nui, Eds. Springer Nature Switzerland, 2026, pp. 268–278.
[16] N. H. Q. Nguyen, T. T. Nguyen, and A. C. Phan, "A Lightweight Explainable Deep Learning for Blood Cell Classification," Computer Modeling in Engineering & Sciences, vol. 145, no. 2, pp. 2435–2456, 2025.
[17] N. Ayesha and H. Khalidi, "A Vision Transformer with a Self-Attention Mechanism for High-Accuracy Blood Cell Classification," Engineering, Technology & Applied Science Research, vol. 16, no. 1, pp. 32557–32563, Feb. 2026.
[18] A. Makhro et al., "Red Blood Cell RedTell Dataset." Zenodo, Apr. 05, 2023.
[19] D. Saleela, "divsal009/Anemia." May 13, 2026, [Online]. Available: https://github.com/divsal009/Anemia.
Downloads
How to Cite
License
Copyright (c) 2026 R. Remya, M. Janani, P. Thilakavathy, Mitha Rachel Jose, R. Reji, L. P. Supriya, Mohammad Asim, Lekshmi R. Nair, Dheeraj Tiger, Divya Saleela
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
