Thu, Oct 30, 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: (72 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
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
