Deep learning applications in parasite microscopy: A scoping review
- 1Department of Parasitology and Medical Entomology, Faculty of Medicine, Universiti Kebangsaan Malaysia, Kuala Lumpur, Malaysia
- 2Center for Cyber Security, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia
- 3Institute for Public Health, National Institutes of Health, Ministry of Health Malaysia, Shah Alam, Selangor, Malaysia
Abstract
Background: Parasitic diseases remain a significant contributor to the global burden of disease and conventional microscopy remains the gold standard for parasite detection. However, it is labour-intensive and dependent on skilled personnel, leading to variability in diagnostic accuracy. Recent advances in deep learning have enabled automated analysis of microscopy images, offering potential improvements in diagnostic efficiency and consistency. Methodology/principal findings: This scoping review aimed to map current evidence on deep learning applications in parasite microscopy for human clinical diagnosis. A systematic search of seven electronic databases was conducted for studies published between January 2015 and July 2025. Eligible studies included primary research that applied deep learning models to parasite microscopy images and reported performance metrics. A total of 118 studies were included. Image classification was the most commonly reported task, followed by object detection, while image segmentation was less frequently investigated. A wide range of architectures was used, including convolutional neural networks (CNNs), YOLO-based detection models and hybrid approaches. Most studies reported high performance across tasks, however, direct comparison was limited due to heterogeneity in datasets, evaluation metrics and experimental designs. In addition, most studies relied on internal validation using subsets of the same dataset, with limited external validation. Among the studies included in this review, several proposed implementation strategies. However, relatively few reported implementation or evaluation in real-world clinical or diagnostic laboratory settings. Conclusions/significance: Deep learning demonstrates substantial potential for automated parasite detection in microscopy. Among the studies included in this review, most deep learning models were evaluated under experimental conditions, with relatively few reporting implementation or evaluation in clinical or diagnostic laboratory settings. Key challenges include dataset heterogeneity, lack of standardised evaluation and limited real-world validation. Future research should prioritise external validation and implementation-focused studies to support integration into clinical and laboratory workflows. Author summary: Parasitic infections continue to affect millions of people worldwide, particularly in regions with limited healthcare resources. Diagnosis often relies on microscopy, which requires trained personnel and can be time-consuming and variable in accuracy. In recent years, deep learning has emerged as a promising tool for automating parasite detection in microscopy images. In this study, we reviewed current research on deep learning applications in parasite microscopy. We found that many models can detect and classify parasites with high accuracy under controlled conditions. However, most studies used pre-existing datasets and did not test their models in real clinical settings. In addition, differences in study design and evaluation methods make it difficult to compare results across studies. Our findings suggest that while deep learning has strong potential to support parasite diagnosis, further work is needed to ensure these systems are reliable and practical for real-world use. Future studies should focus on testing models in clinical environments and developing standardised approaches to improve comparability and implementation.
Related
- From Static Atlases to Intelligent Learning Systems: A Scoping Review of Imaging-Based Tools and Emerging Artificial Intelligence Applications for Facial Aesthetic Education and Training
- Applications of episodic future thinking in patients with chronic diseases: a scoping review
- Artificial intelligence-enabled mental health applications for adolescents: a scoping review of safety, effectiveness and clinical implementation
- The applications of artificial intelligence in liver transplantation: A comprehensive scoping review
- Retrieval-augmented generation in medicine: A scoping review of technical implementations, clinical applications, and ethical considerations
BibTeX
@article{maniraj2026deep,
title = {{Deep learning applications in parasite microscopy: A scoping review}},
author = {Rose Mary Maniraj and Emelia Osman and Siti Norul Huda Sheikh Abdullah and Aishah Hani Azil and Mohd Amierul Fikri Mahmud},
journal = {PLOS Neglected Tropical Diseases},
year = {2026},
month = oct,
doi = {10.1371/journal.pntd.0014774},
url = {https://journals.plos.org/plosntds/article?id=10.1371/journal.pntd.0014774},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Deep learning applications in parasite microscopy: A scoping review
AU - Rose Mary Maniraj
AU - Emelia Osman
AU - Siti Norul Huda Sheikh Abdullah
AU - Aishah Hani Azil
AU - Mohd Amierul Fikri Mahmud
PY - 2026
DA - 2026/10/07
JO - PLOS Neglected Tropical Diseases
DO - 10.1371/journal.pntd.0014774
UR - https://journals.plos.org/plosntds/article?id=10.1371/journal.pntd.0014774
AB - Background: Parasitic diseases remain a significant contributor to the global burden of disease and conventional microscopy remains the gold standard for parasite detection. However, it is labour-intensive and dependent on skilled personnel, leading to variability in diagnostic accuracy. Recent advances in deep learning have enabled automated analysis of microscopy images, offering potential improvements in diagnostic efficiency and consistency. Methodology/principal findings: This scoping review aimed to map current evidence on deep learning applications in parasite microscopy for human clinical diagnosis. A systematic search of seven electronic databases was conducted for studies published between January 2015 and July 2025. Eligible studies included primary research that applied deep learning models to parasite microscopy images and reported performance metrics. A total of 118 studies were included. Image classification was the most commonly reported task, followed by object detection, while image segmentation was less frequently investigated. A wide range of architectures was used, including convolutional neural networks (CNNs), YOLO-based detection models and hybrid approaches. Most studies reported high performance across tasks, however, direct comparison was limited due to heterogeneity in datasets, evaluation metrics and experimental designs. In addition, most studies relied on internal validation using subsets of the same dataset, with limited external validation. Among the studies included in this review, several proposed implementation strategies. However, relatively few reported implementation or evaluation in real-world clinical or diagnostic laboratory settings. Conclusions/significance: Deep learning demonstrates substantial potential for automated parasite detection in microscopy. Among the studies included in this review, most deep learning models were evaluated under experimental conditions, with relatively few reporting implementation or evaluation in clinical or diagnostic laboratory settings. Key challenges include dataset heterogeneity, lack of standardised evaluation and limited real-world validation. Future research should prioritise external validation and implementation-focused studies to support integration into clinical and laboratory workflows. Author summary: Parasitic infections continue to affect millions of people worldwide, particularly in regions with limited healthcare resources. Diagnosis often relies on microscopy, which requires trained personnel and can be time-consuming and variable in accuracy. In recent years, deep learning has emerged as a promising tool for automating parasite detection in microscopy images. In this study, we reviewed current research on deep learning applications in parasite microscopy. We found that many models can detect and classify parasites with high accuracy under controlled conditions. However, most studies used pre-existing datasets and did not test their models in real clinical settings. In addition, differences in study design and evaluation methods make it difficult to compare results across studies. Our findings suggest that while deep learning has strong potential to support parasite diagnosis, further work is needed to ensure these systems are reliable and practical for real-world use. Future studies should focus on testing models in clinical environments and developing standardised approaches to improve comparability and implementation.
SN - 1935-2735
ER -