Deep Learning-Based Malaria Parasite Image Classification on Real Microscopy Data
Infectious Disease Reports · 27.07.2026 · 18 (4) · 78
DOI: 10.3390/idr18040078 ↗Kurz gefasst
Fachartikel in der Zeitschrift Infectious Disease Reports, online erschienen am 27.07.2026. Verfasst von Francesco Branda und 10 weiteren Autor:innen. Beteiligte Einrichtung: Unit of Medical Statistics and Molecular Epidemiology, Università Campus Bio-Medico di Roma, Via Àlvaro del Portillo 21, 00128 Rome, Italy. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Accurate and timely malaria diagnosis with species-level identification of Plasmodium parasites is critical for guiding effective treatment and disease management. Although light microscopy remains the diagnostic gold standard, its dependence on highly trained personnel limits accessibility, particularly in resource-constrained settings. Recent advances in deep learning have enabled automated image-based diagnosis with promising performance; however, reliable differentiation among Plasmodium species continues to pose a major challenge. This study aims to evaluate and compare the effectiveness of different deep learning architectures for automated species identification from microscopy images.
Methods
Three deep learning architectures were systematically assessed: a convolutional backbone (ResNet50), a Vision Transformer (ViT), and a hybrid ResNetViT model. All models were trained from scratch, without using pretrained weights, on a dataset comprising real-world thick blood smear images augmented with publicly available microscopy data from Kaggle. In the hybrid architecture, the ResNet module was used to extract robust local morphological features, while the ViT component captured long-range dependencies and contextual relationships within images.
Results
In cross-validation experiments, all three architectures consistently achieved high diagnostic performance. ResNet50 attained the highest accuracy (96.9%), an F1-score of 96.3%, and an ROC-AUC of 0.997. The Vision Transformer achieved 93.1% accuracy, 91.7% F1-score, and an ROC-AUC of 0.989. The hybrid ResNetViT reached 95.2% accuracy, 94.2% F1-score, and an ROC-AUC of 0.995. These results confirm that all architectures can reliably distinguish among Plasmodium species. Although ResNet50 achieved the highest raw accuracy, the hybrid model showed the most stable calibration and the closest qualitative agreement between its attention maps and expert-annotated parasite locations.
Conclusions
The findings demonstrate that convolutional, transformer-based, and hybrid deep learning architectures can be successfully trained on real microscopy data for species-level malaria diagnosis. These results support the feasibility of deploying scalable, automated diagnostic systems to improve both accuracy and accessibility of malaria detection, particularly in resource-limited healthcare settings.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Unit of Medical Statistics and Molecular Epidemiology, Università Campus Bio-Medico di Roma, Via Àlvaro del Portillo 21, 00128 Rome, Italy.
- Unit of General Clinical Laboratory with Specialized Areas General Clinical Pathology and Substances of Abuse, Microbiology and Virology, Department of Clinical Services, Azienda Socio Sanitaria Territoriale della Valte…
- Department of Medicine (DMED), University of Udine, Piazzale Kolbe 4, 33100 Udine, Italy.
- Microbiology and Virology Unit, Department of Laboratory Medicine, Azienda Sanitaria Friuli Occidentale (ASFO), Santa Maria degli Angeli Hospital, Via Montereale 24, 33170 Pordenone, Italy.
- Department of Surgical and Medical Sciences, Magna Graecia University of Catanzaro, Viale Europa, 88100 Catanzaro, Italy.
- Department of Public Health and Infectious Diseases, University of Rome Sapienza, 00185 Rome, Italy.
ORCID-Profile: Francesco Branda, Lilia Andriani, Riccardo Lucis, Annamaria Defilippo, Ugo Lomoio, Barbara Puccio, Giancarlo Ceccarelli, Massimo Ciccozzi, Fabio Scarpa, Pierangelo Veltri, Pietro Hiram Guzzi
Zitieren
APA
Branda, F., Andriani, L., Lucis, R., Defilippo, A., Lomoio, U., Puccio, B., Ceccarelli, G., Ciccozzi, M., Scarpa, F., Veltri, P., & Guzzi, P. H. (2026). Deep Learning-Based Malaria Parasite Image Classification on Real Microscopy Data. Infectious Disease Reports, 18(4), 78. https://doi.org/10.3390/idr18040078
Vancouver
Branda F, Andriani L, Lucis R, Defilippo A, Lomoio U, Puccio B, et al. Deep Learning-Based Malaria Parasite Image Classification on Real Microscopy Data. Infectious Disease Reports. 2026;18(4):78. doi:10.3390/idr18040078
BibTeX
@article{Branda2026,
author = {Branda, Francesco and Andriani, Lilia and Lucis, Riccardo and Defilippo, Annamaria and Lomoio, Ugo and Puccio, Barbara and Ceccarelli, Giancarlo and Ciccozzi, Massimo and Scarpa, Fabio and Veltri, Pierangelo and Guzzi, Pietro Hiram},
title = {Deep Learning-Based Malaria Parasite Image Classification on Real Microscopy Data},
journal = {Infectious Disease Reports},
year = {2026},
volume = {18},
number = {4},
pages = {78},
doi = {10.3390/idr18040078}
}
EUVIMED