PARAZİT YUMURTA TÜRLERİNİN FÜZYON MODEL İLE SINIFLANDIRILMASI

Talha Tursun; Meltem Kurt Pehlivanoğlu; Ayşe Gül Eker; Hikmetcan Özcan

doi:10.17780/ksujes.1719173

EN TR

CLASSIFICATION OF PARASITE EGG TYPES WITH A FUSION MODEL

Abstract

Intestinal parasites represent a significant public health issue worldwide, with particularly high prevalence in tropical and developing countries. These parasites reside in the host's intestinal system, feeding and causing various health problems; if left untreated, they can lead to serious complications such as vomiting, diarrhea, weakness, and developmental disorders in children. Therefore, timely detection of parasitic infections is critical for protecting individual health and improving public health outcomes. Traditional microscopic examination methods face challenges such as low efficiency and reliance on expert interpretation. In this context, artificial intelligence-based automated detection systems enhance the efficiency of healthcare services by enabling the rapid and accurate identification of parasites. This study examines the integration of deep learning and machine learning methods using the Chula-Parasite-Egg-11 dataset, and the results demonstrate significant performance improvements in parasite detection through these approaches. The highest performance was achieved with the ViT-FPN-supported YOLO11m model, with an F1 score of 99.53% and an mAP score of 95.62%. Additionally, combining the outputs of deep learning-based approaches with machine learning classifiers improved accuracy rates, making resource utilization more efficient. This research highlights the effectiveness of artificial intelligence applications in parasite detection, making a significant contribution to the literature.

Keywords

PARAZİT YUMURTA TÜRLERİNİN FÜZYON MODEL İLE SINIFLANDIRILMASI

Öz

Bağırsak parazitleri, dünya genelinde önemli bir halk sağlığı sorunu oluşturarak, özellikle tropik ve gelişmekte olan ülkelerde yüksek yayılım göstermektedir. Bu parazitler, konakçıların bağırsak sisteminde yaşar ve beslenerek çeşitli sağlık sorunlarına yol açar; tedavi edilmediğinde kusma, ishal, güçsüzlük ve çocuk gelişiminde bozukluk gibi ciddi komplikasyonlar doğurabilir. Bu nedenle, parazit enfeksiyonlarının zamanında tespiti, bireylerin sağlık durumunu korumak ve toplum sağlığını iyileştirmek için kritik öneme sahiptir. Geleneksel mikroskobik inceleme yöntemleri, düşük verimlilik ve uzman bağımlılığı gibi sorunlarla karşı karşıyadır. Bu bağlamda, yapay zeka tabanlı otomatik tespit sistemleri, parazitlerin hızlı ve doğru bir şekilde tanımlanmasını sağlayarak sağlık hizmetlerinin etkinliğini artırmaktadır. Bu çalışma, Chula-Parasite-Egg-11 veri kümesi kullanarak derin öğrenme ve makine öğrenmesi yöntemlerinin entegrasyonunu incelemekte ve elde edilen sonuçlar, bu yaklaşımların parazit tespitinde önemli performans artışları sağladığını göstermektedir. Yapılan deneyler sonucu en yüksek başarı ViT-FPN destekli YOLO11m modeli ile elde edilmiş; F1 skoru %99,53, mAP skoru ise %95,62 olarak ölçülmüştür. Ayrıca, derin öğrenme tabanlı yaklaşımların çıktılarının makine öğrenmesi sınıflayıcılarıyla birleştirilmesi, doğruluk oranlarını artırarak kaynak kullanımını daha verimli hale getirmiştir. Bu araştırma, parazit tespitinde yapay zeka uygulamalarının etkinliğini vurgulayarak, literatüre önemli bir katkı sunmaktadır.

Anahtar Kelimeler

Supporting Institution

TÜBİTAK

Project Number

1919B012466699

References

AlDahoul, N., Abdul Karim, H., Kee, S. L., & Tan, M. J. T. (2022). Localization and classification of parasitic eggs in microscopic images using an EfficientDet detector. 2022 IEEE International Conference on Image Processing (ICIP), 1922–1926. https://doi.org/10.1109/ICIP46576.2022.9897844
AlDahoul, N., Abdul Karim, H., Momo, M. A., Escobar, F. I. F., Magallanes, V. A., & Tan, M. J. T. (2023). Parasitic egg recognition using convolution and attention network. Scientific Reports, 13, 14475. https://doi.org/10.1038/s41598-023-41711-3
Anantrasirichai, N., Chalidabhongse, T. H., Palasuwan, D., Naruenatthanaset, K., Kobchaisawat, T., Nunthanasup, N., Boonpeng, K., Ma, X., & Achim, A. (2022). ICIP 2022 challenge on parasitic egg detection and classification in microscopic images: Dataset, methods and results. IEEE International Conference on Image Processing (ICIP). https://doi.org/10.21227/vyh8-4h71
Belete, Y. A., Kassa, T. Y., & Baye, M. F. (2021). Prevalence of intestinal parasite infections and associated risk factors among patients of Jimma health center requested for stool examination, Jimma, Ethiopia. PLoS ONE, 16, e247063.
Lane, M., Kashani, M., Barratt, J. L., Qvarnstrom, Y., Yabsley, M. J., Garrett, K. B., et al. (2023). Application of a universal parasite diagnostic test to biological specimens collected from animals. International Journal for Parasitology: Parasites and Wildlife, 20, 20–30.
Pedraza, A., Ruiz-Santaquiteria, J., Deniz, O., & Bueno, G. (2022). Parasitic egg detection and classification with transformer-based architectures. 2022 IEEE International Conference on Image Processing (ICIP), 1942–1946. https://doi.org/10.1109/ICIP46576.2022.9897846
Pinetsuksai, N., Jaksukam, K., Kittichai, V., Tongloy, T., Chuwongin, S., Jomtarak, R., & Boonsang, S. (2023). Development of self-supervised learning with Dinov2-distilled models for parasite classification in screening. 2023 15th International Conference on Information Technology and Electrical Engineering (ICITEE). https://doi.org/10.1109/ICITEE59582.2023.10317719
Pratama, Y., Fujimura, Y., Funatomi, T., & Mukaigawa, Y. (2022). Parasitic egg detection and classification by utilizing the YOLO algorithm with deep latent space image restoration and GrabCut augmentation. 2022 IEEE International Conference on Image Processing (ICIP), 1881–1885. https://doi.org/10.1109/ICIP46576.2022.9897645

Rajasekar, S. J. S., Jaswal, G., Perumal, V., Ravi, S., & Dutt, V. (2023). Parasite.ai – An automated parasitic egg detection model from microscopic images of fecal smears using deep learning techniques. 2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI). https://doi.org/10.1109/ACCAI58221.2023.10200869
Ruiz-Santaquiteria, J., Pedraza, A., Vallez, N., & Velasco, A. (2022). Parasitic egg detection with a deep learning ensemble. 2022 IEEE International Conference on Image Processing (ICIP), 1937–1941. https://doi.org/10.1109/ICIP46576.2022.9897858
Suzuki, C. T., Gomes, J. F., Falcao, A. X., Papa, J. P., & Hoshino-Shimizu, S. (2012). Automatic segmentation and classification of human intestinal parasites from microscopy images. IEEE Transactions on Biomedical Engineering, 60(3), 803–812.
Taghipour, A., Javanmard, E., Rahimi, H. M., Abdoli, A., Matin, S., Haghbin, M., et al. (2024). Prevalence of intestinal parasitic infections in patients with diabetes: A systematic review and meta-analysis. International Health, 16, 23–34.
Tureckova, A., Turecek, T., & Oplatkova, Z. K. (2022). ICIP 2022 challenge: PEDCMI, TOOD enhanced by slicing-aided fine-tuning and inference. IEEE International Conference on Image Processing (ICIP) Proceedings. https://doi.org/10.1109/ICIP46576.2022.9897826
World Health Organization. (2023). Soil-transmitted helminth infections. https://www.who.int/news-room/fact-sheets/detail/soil-transmitted-helminth-infections
Xu, W., Zhai, Q., Liu, J., Xu, X., & Hua, J. (2024). A lightweight deep-learning model for parasite egg detection in microscopy images. Parasites & Vectors, 17, 454. https://doi.org/10.1186/s13071-024-06503-2

Details

Primary Language

Turkish

Subjects

Computer Vision , Image Processing

Journal Section

Research Article

Authors

Talha Tursun
0009-0009-2724-9395
Türkiye

Meltem Kurt Pehlivanoğlu
0000-0002-7581-9390
Türkiye

Ayşe Gül Eker ^*
0000-0003-0721-2631
Türkiye

Hikmetcan Özcan
0000-0002-7146-203X
Türkiye

Publication Date

December 3, 2025

Submission Date

June 13, 2025

Acceptance Date

November 7, 2025

Published in Issue

Year 2025 Volume: 28 Number: 4

DOI

https://doi.org/10.17780/ksujes.1719173

IZ

https://izlik.org/JA24AY98WG

Cite

RIS / Bibtex

APA

Tursun, T., Kurt Pehlivanoğlu, M., Eker, A. G., & Özcan, H. (2025). PARAZİT YUMURTA TÜRLERİNİN FÜZYON MODEL İLE SINIFLANDIRILMASI. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(4), 2032-2044. https://doi.org/10.17780/ksujes.1719173