Iranian Journal of Blood and Cancer

en Comparative Evaluation of Custom Convolutional Neural Networks and EfficientNet-B3 for Malaria Cell Image Classification: Impact of Targeted Data Augmentation on Model Performance Infectious Diseases Infectious Diseases پژوهشي Original Article <div style="text-align: justify;">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.</div> Malaria, Deep learning, EfficientNet-B3, Albumentations, Parasitized cell images, Medical imaging AI, Soft-attention parallel CNN 62 72 http://ijbc.ir/browse.php?a_code=A-10-2180-2&slc_lang=en&sid=1 Reza Mohit 100319475328460012569 100319475328460012569 No Department of Anesthesia, School of Paramedical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran Emad Milani 100319475328460012570 100319475328460012570 No Student Research Committee, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran Ata Amini 100319475328460012571 100319475328460012571 No Department of Health Information Management and Medical Informatics, School of Allied Medical Sciences, Tehran University of Medical Sciences, Tehran, Iran Mehrnaz Ahani 100319475328460012572 100319475328460012572 No Department of Midwifery, School of Nursing and Midwifery, Shahid Beheshti University of Medical Sciences, Tehran, Iran Elham Nazari elham.nazari@sbmu.ac.ir 100319475328460012573 100319475328460012573 Yes Proteomics Research Center, Faculty of Paramedical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran. Tahmineh Aldaghi tahmineh1989@gmail.com 100319475328460012574 100319475328460012574 No Institute of Biophysics and Informatics, First Faculty of Medicine, Charles University, Prague, Czech Republic.