Sun, Dec 14, 2025
[Archive]
Volume 17, Issue 3 (September-2025 2025)
Iranian Journal of Blood and Cancer 2025, 17(3): 62-72 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Mohit R, Milani E, Amini A, Ahani M, Nazari E, Aldaghi T. Comparative Evaluation of Custom Convolutional Neural Networks and EfficientNet-B3 for Malaria Cell Image Classification: Impact of Targeted Data Augmentation on Model Performance. Iranian Journal of Blood and Cancer 2025; 17 (3) :62-72
URL: http://ijbc.ir/article-1-1787-en.html
URL: http://ijbc.ir/article-1-1787-en.html
1- Department of Anesthesia, School of Paramedical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran
2- Student Research Committee, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran
3- Department of Health Information Management and Medical Informatics, School of Allied Medical Sciences, Tehran University of Medical Sciences, Tehran, Iran
4- Department of Midwifery, School of Nursing and Midwifery, Shahid Beheshti University of Medical Sciences, Tehran, Iran
5- Proteomics Research Center, Faculty of Paramedical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran. ,elham.nazari@sbmu.ac.ir
6- Institute of Biophysics and Informatics, First Faculty of Medicine, Charles University, Prague, Czech Republic.
2- Student Research Committee, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran
3- Department of Health Information Management and Medical Informatics, School of Allied Medical Sciences, Tehran University of Medical Sciences, Tehran, Iran
4- Department of Midwifery, School of Nursing and Midwifery, Shahid Beheshti University of Medical Sciences, Tehran, Iran
5- Proteomics Research Center, Faculty of Paramedical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran. ,
6- Institute of Biophysics and Informatics, First Faculty of Medicine, Charles University, Prague, Czech Republic.
Abstract: (517 Views)
Background: Malaria diagnosis with thin blood smears remains labor-intensive and relies on the operator. Deep learning could enable accurate automation.
Objective: Compare four convolutional approaches for classifying parasitized versus uninfected erythrocytes and to evaluate whether targeted image-quality augmentations enhance performance.
Materials and Methods: We used the balanced NIH/Kaggle dataset, which included 13,780 parasitized and 13,780 uninfected samples. Data were split stratified into training, validation, and test sets (70/15/15). Images were resized to 256×256 and normalized. Four experiments were conducted: (1) a custom CNN; (2) the same CNN with targeted augmentation applied to 20% of training samples per class—using Contrast Limited Adaptive Histogram Equalization [CLAHE] and controlled brightness adjustment—and augmented images were added back to the training set (totaling 30,864 images); (3) a soft-attention parallel CNN (SPCNN); and (4) transfer learning with EfficientNet-B3 on 300×300 inputs with full fine-tuning. Evaluation metrics included accuracy, precision, recall, F1 score, and AUC-ROC.
Results: EfficientNet-B3 achieved the highest performance with a validation accuracy of 0.9741, 98% precision, 96% recall, an F1 score of 0.97, and an AUC-ROC of 0.9964. SPCNN was competitive but slightly lower, with a validation accuracy of 0.9652, 98% precision, 95% recall, an F1 score of 0.96, and an AUC-ROC of 0.9909. The baseline CNN had a validation accuracy of 0.9649, 97% precision, 94% recall, an F1 score of 0.96, and an AUC-ROC of 0.9910. Targeted augmentation resulted in negligible change compared to the baseline CNN, with a validation accuracy of 0.9647, an F1 score of 0.96, and an AUC-ROC of 0.9908, indicating limited added discriminative value for this dataset.
Conclusion: EfficientNet-B3 outperformed SPCNN and custom CNNs. The CLAHE/brightness strategy applied to 20% of training images and added back to the dataset did not significantly improve generalization. External validation and prospective field testing are necessary before clinical deployment.
Objective: Compare four convolutional approaches for classifying parasitized versus uninfected erythrocytes and to evaluate whether targeted image-quality augmentations enhance performance.
Materials and Methods: We used the balanced NIH/Kaggle dataset, which included 13,780 parasitized and 13,780 uninfected samples. Data were split stratified into training, validation, and test sets (70/15/15). Images were resized to 256×256 and normalized. Four experiments were conducted: (1) a custom CNN; (2) the same CNN with targeted augmentation applied to 20% of training samples per class—using Contrast Limited Adaptive Histogram Equalization [CLAHE] and controlled brightness adjustment—and augmented images were added back to the training set (totaling 30,864 images); (3) a soft-attention parallel CNN (SPCNN); and (4) transfer learning with EfficientNet-B3 on 300×300 inputs with full fine-tuning. Evaluation metrics included accuracy, precision, recall, F1 score, and AUC-ROC.
Results: EfficientNet-B3 achieved the highest performance with a validation accuracy of 0.9741, 98% precision, 96% recall, an F1 score of 0.97, and an AUC-ROC of 0.9964. SPCNN was competitive but slightly lower, with a validation accuracy of 0.9652, 98% precision, 95% recall, an F1 score of 0.96, and an AUC-ROC of 0.9909. The baseline CNN had a validation accuracy of 0.9649, 97% precision, 94% recall, an F1 score of 0.96, and an AUC-ROC of 0.9910. Targeted augmentation resulted in negligible change compared to the baseline CNN, with a validation accuracy of 0.9647, an F1 score of 0.96, and an AUC-ROC of 0.9908, indicating limited added discriminative value for this dataset.
Conclusion: EfficientNet-B3 outperformed SPCNN and custom CNNs. The CLAHE/brightness strategy applied to 20% of training images and added back to the dataset did not significantly improve generalization. External validation and prospective field testing are necessary before clinical deployment.
Keywords: Malaria, Deep learning, EfficientNet-B3, Albumentations, Parasitized cell images, Medical imaging AI, Soft-attention parallel CNN
: Original Article |
Subject:
Infectious Diseases
Received: 2025/07/10 | Accepted: 2025/09/10 | Published: 2025/09/30
Received: 2025/07/10 | Accepted: 2025/09/10 | Published: 2025/09/30
References
1. World Health Organization. World Malaria Report 2024. Geneva: WHO; 2024.
2. Venkatesan P. WHO World Malaria Report 2024. Lancet Microbe. 2025;6(1). [DOI:10.1016/j.lanmic.2025.101073]
3. Jones S, et al. Trends in Plasmodium burden in children and pregnant women in the WHO African Region. Lancet Glob Health. 2024.
4. RTS,S Clinical Trials Partnership. Efficacy and safety of RTS,S/AS01 malaria vaccine. Lancet. 2015;386(9988):31-45. [DOI:10.1016/S0140-6736(15)60721-8]
5. Datoo MS, et al. Efficacy of R21/Matrix-M malaria vaccine. Lancet. 2021;397(10287):1809-18. [DOI:10.1016/S0140-6736(21)00943-0]
6. Moody A. Rapid diagnostic tests for malaria parasites. Clin Microbiol Rev. 2002;15(1):66-78. [DOI:10.1128/CMR.15.1.66-78.2002]
7. WHO. Malaria Microscopy Quality Assurance Manual, 2023.
8. Hopkins H, et al. Microscopy in malaria diagnosis. Malaria J. 2007;6:115. [DOI:10.1186/1475-2875-6-134]
9. Gamboa D, et al. A large proportion of P. falciparum in Peru lack pfhrp2 and pfhrp3. J Clin Microbiol. 2010;48(6):2055-7.
10. Snounou G. PCR diagnosis of malaria. Clin Microbiol Rev. 1993;6(1):15-28.
11. Rajaraman S, et al. Transfer learning for malaria parasite detection in thin smear images. PeerJ. 2018;6:e4568. [DOI:10.7717/peerj.4568]
12. Pattanaik D, et al. Comparison of CNN frameworks for malaria diagnosis. arXiv preprint arXiv:1909.02829.
13. Liang Z, et al. CNN-based parasite stage classification. Comput Biol Med. 2021;134:104524.
14. Ahuja S, et al. EfficientNet B3-based malaria parasite detection. Biomed Signal Process Control. 2020;62:102093. [DOI:10.1016/j.bspc.2020.102093]
15. Tan M, Le Q. EfficientNet: Rethinking model scaling. ICML. 2019.
16. Shorten C, Khoshgoftaar TM. A survey on image data augmentation. J Big Data. 2019;6:60. [DOI:10.1186/s40537-019-0197-0]
17. Perez L, Wang J. Effectiveness of data augmentation. arXiv preprint arXiv:1712.04621.
18. Ahamed F, et al. SPCNN for malaria detection. Sci Rep. 2025;15:6484. [DOI:10.1038/s41598-025-90851-1]
19. Rajaraman S, Antani SK, Poostchi M, et al. Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images. PeerJ. 2018;6:e4568. [DOI:10.7717/peerj.4568]
20. Poostchi M, Silamut K, Maude RJ, Jaeger S, Thoma G. Image analysis and machine learning for detecting malaria. Trans R Soc Trop Med Hyg. 2018;112(4):170-182. [DOI:10.1016/j.trsl.2017.12.004]
21. Kaggle. Cell Images for Malaria Detection dataset. Available at: https://www.kaggle.com/datasets/iarunava/cell-images-for-malaria. Accessed 2025.
22. Li X, Wang Y, Zhang J, et al. Attention-based parallel CNN architectures for interpretable malaria diagnosis. Sci Rep. 2024;14:12345.
23. Shorten C, Khoshgoftaar TM. A survey on image data augmentation for deep learning. J Big Data. 2019;6:60. [DOI:10.1186/s40537-019-0197-0]
24. Tan M, Le QV. EfficientNet: Rethinking model scaling for convolutional neural networks. Proc Int Conf Mach Learn. 2019:6105-6114.
25. (Dataset): https://www.kaggle.com/datasets/iarunava/cell-images-for-detecting-malaria
26. Shorten C, Khoshgoftaar TM. A survey on image data augmentation for deep learning. J Big Data. 2019;6(1):60. [DOI:10.1186/s40537-019-0197-0]
27. Perez L, Wang J. The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621.
28. Ahamed F, et al. SPCNN vs transfer learning on malaria detection. Sci Rep. 2025;15:6484. [DOI:10.1038/s41598-025-90851-1]
29. Tan M, Le QV. EfficientNet: Rethinking model scaling for convolutional neural networks. ICML. 2019.
30. Silva, R. R. et al. (2022). Malaria Parasite Detection using EfficientNet Models. Biomedical Signal Processing and Control, 74, 103557.
31. Lundervold, A. S., & Lundervold, A. (2019). An overview of deep learning in medical imaging focusing on MRI. Zeitschrift für Medizinische Physik, 29(2), 102-127. [DOI:10.1016/j.zemedi.2018.11.002]
32. Kim DW, Jang HY, Kim KW, Shin Y, Park SH. Design characteristics of studies reporting the performance of artificial intelligence algorithms for diagnostic analysis of medical images: Results from recently published papers. Radiol Artif Intell. 2022;4(1):e210064.
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
- Iranian Journal of Blood and Cancer
- Journal Tel: +989369936116
- Publisher Tel: +982122275917
- Mail: Info@ijbc.ir
