Automated Malaria Ring Form Classification in Blood Smear Images Using Ensemble Parallel Neural Networks
Journal of Imaging · 12.03.2026 · 12 (3) · 127
DOI: 10.3390/jimaging12030127 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 12.03.2026. Verfasst von Pongphan Pongpanitanont und 5 weiteren Autor:innen. Beteiligte Einrichtung: Health Sciences (International Program), College of Graduate Studies, Walailak University, Nakhon Si Thammarat 80160, Thailand. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Walailak University Graduate Scholarships, Walailak University Graduate Research Fund, National Research Council of Thailand (NRCT) and Walailak University.
Abstract (Originalsprache)
Manual microscopy for malaria diagnosis is labor-intensive and prone to inter-observer variability. This study presents an automated binary classification approach for detecting malaria ring-form infections in thin blood smear single-cell images using a parallel neural network framework. Utilizing a balanced Kaggle dataset of 27,558 erythrocyte crops, images were standardized to 128 × 128 pixels and subjected to on-the-fly augmentation. The proposed architecture employs a dual-branch fusion strategy, integrating a convolutional neural network for local morphological feature extraction with a multi-head self-attention branch to capture global spatial relationships. Performance was rigorously evaluated using 10-fold stratified cross-validation and an independent 10% hold-out test set. Results demonstrated high-level discrimination, with all models achieving an ROC–AUC of approximately 0.99. The primary model (Model#1) attained a peak mean accuracy of 0.9567 during cross-validation and 0.97 accuracy (macro F1-score: 0.97) on the independent test set. In contrast, increasing architectural complexity in Model#3 led to a performance decline (0.95 accuracy) due to higher false-positive rates. These findings suggest that moderate-capacity feature fusion, combining convolutional descriptors with attention-based aggregation, provides a robust and generalizable solution for automated malaria screening without the risks associated with over-parameterization. Despite a strong performance, immediate clinical use remains limited because the model was developed on pre-segmented single-cell images, and external validation is still required before routine implementation.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Health Sciences (International Program), College of Graduate Studies, Walailak University, Nakhon Si Thammarat 80160, Thailand.
- Akkhraratchakumari Veterinary College, Walailak University, Nakhon Si Thammarat 80160, Thailand.
- Centre for One Health, Walailak University, Nakhon Si Thammarat 80160, Thailand.
- Department of Medical Technology, School of Allied Health Sciences, Walailak University, Nakhon Si Thammarat 80160, Thailand.
- Hematology and Transfusion Science Research Center, Walailak University, Nakhon Si Thammarat 80160, Thailand.
- Centre of Malariology, Parasitology and Entomology, Ministry of Health, Vientiane P.O. Box 0100, Laos.
ORCID-Profile: Manit Nuinoon
Förderung
- Walailak University Graduate Scholarships
- Walailak University Graduate Research Fund
- National Research Council of Thailand (NRCT) and Walailak University
- School of Allied Health Sciences, Walailak University, under the Research Cluster Accelerator scheme, Fiscal Year 2025
- School of Allied Health Sciences, Walailak University, under the Research Cluster Accelerator scheme
Zitieren
APA
Pongpanitanont, P., Suttidate, N., Nuinoon, M., Khampeeramao, N., Laymanivong, S., & Janwan, P. (2026). Automated Malaria Ring Form Classification in Blood Smear Images Using Ensemble Parallel Neural Networks. Journal of Imaging, 12(3), 127. https://doi.org/10.3390/jimaging12030127
Vancouver
Pongpanitanont P, Suttidate N, Nuinoon M, Khampeeramao N, Laymanivong S, Janwan P. Automated Malaria Ring Form Classification in Blood Smear Images Using Ensemble Parallel Neural Networks. Journal of Imaging. 2026;12(3):127. doi:10.3390/jimaging12030127
BibTeX
@article{Pongpanitanont2026,
author = {Pongpanitanont, Pongphan and Suttidate, Naparat and Nuinoon, Manit and Khampeeramao, Natthida and Laymanivong, Sakhone and Janwan, Penchom},
title = {Automated Malaria Ring Form Classification in Blood Smear Images Using Ensemble Parallel Neural Networks},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {3},
pages = {127},
doi = {10.3390/jimaging12030127}
}
EUVIMED