Malaria Parasite Detection Using Deep Learning: A Comparative Study of Six Architectures

Abstract

Malaria remains a major global health challenge, particularly in resource-limited regions where reliable diagnostic tools are scarce. Traditional thick blood smear microscopy, while accurate, is time-consuming and requires expert interpretation. This study employed Artificial Intelligence as a pre-diagnostic tool to mitigate the impact of malaria by evaluating six deep learning architectures for classifying malaria-infected cell images: Vanilla CNN, AlexNet, ViT, Swin Transformer, ConvNeXt, and MaxViT. The dataset consisted of 1,883 Giemsa-stained blood smear samples collected from patients at Chittagong Medical College Hospital, Bangladesh, with expert annotations from the Mahidol Oxford Tropical Medicine Research Unit. All models were trained for 100 epochs using the Adam optimizer, a cosine annealing learning rate scheduler, early stopping, and a batch size of 32 samples. Among the tested models, MaxViT yielded the highest accuracy of 99.67%, followed by ConvNeXt with 99.61% and Swin Transformer with 98.79%, while ViT reached 80.03%, AlexNet 77.83%, and Vanilla CNN 50.06%. These findings demonstrate that more advanced architectures integrating both convolutional and attention mechanisms yield superior performance in malaria cell classification. With their high accuracy, cost-effectiveness, and computational efficiency, these architectures show strong potential as reliable pre-diagnostic tools for malaria detection in resource-constrained settings.