Detection and classification of intestinal parasites using advanced object detection models

Automated detection of intestinal parasites is crucial for improving diagnostic efficiency and accuracy in parasitology. This study evaluates the performance of three object detection models: Faster RCNN with ResNet back-bone, Faster RCNN with RetinaNet backbone, and YOLOv8. A dataset comprising 200...

Full description

Bibliographic Details
Main Authors: Hamza, Haifa, Kamarul Hawari, Ghazali, Ahmad, Abubakar
Format: Conference or Workshop Item
Language:English
Published: Atlantis Press 2025
Subjects:
Online Access:https://umpir.ump.edu.my/id/eprint/45627/
_version_ 1848827469546651648
author Hamza, Haifa
Kamarul Hawari, Ghazali
Ahmad, Abubakar
author_facet Hamza, Haifa
Kamarul Hawari, Ghazali
Ahmad, Abubakar
author_sort Hamza, Haifa
building UMP Institutional Repository
collection Online Access
description Automated detection of intestinal parasites is crucial for improving diagnostic efficiency and accuracy in parasitology. This study evaluates the performance of three object detection models: Faster RCNN with ResNet back-bone, Faster RCNN with RetinaNet backbone, and YOLOv8. A dataset comprising 2000 microscopic images of two parasite species, Ascaris lumbricoides and Trichuris trichiura, was used. The dataset was split into 1500 images for training, 300 for validation, and 200 for testing. Experimental results show that Faster RCNN with RetinaNet achieved the highest Average Precision (AP) across varying Intersection over Union (IoU) thresholds, demonstrating its robustness. YOLOv8 exhibited superior precision at low confidence thresholds, while Faster RCNN with ResNet demonstrated strong recall consistency. These findings provide a comparative analysis, highlighting the strengths and limitations of each model for reliable and efficient intestinal parasite detection, suggesting the integration of ensemble models to combine RetinaNet’s robustness and YOLOv8’s precision-recall capabilities for optimized results.
first_indexed 2025-11-15T04:01:13Z
format Conference or Workshop Item
id ump-45627
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T04:01:13Z
publishDate 2025
publisher Atlantis Press
recordtype eprints
repository_type Digital Repository
spelling ump-456272025-09-12T07:24:11Z https://umpir.ump.edu.my/id/eprint/45627/ Detection and classification of intestinal parasites using advanced object detection models Hamza, Haifa Kamarul Hawari, Ghazali Ahmad, Abubakar QA75 Electronic computers. Computer science T Technology (General) Automated detection of intestinal parasites is crucial for improving diagnostic efficiency and accuracy in parasitology. This study evaluates the performance of three object detection models: Faster RCNN with ResNet back-bone, Faster RCNN with RetinaNet backbone, and YOLOv8. A dataset comprising 2000 microscopic images of two parasite species, Ascaris lumbricoides and Trichuris trichiura, was used. The dataset was split into 1500 images for training, 300 for validation, and 200 for testing. Experimental results show that Faster RCNN with RetinaNet achieved the highest Average Precision (AP) across varying Intersection over Union (IoU) thresholds, demonstrating its robustness. YOLOv8 exhibited superior precision at low confidence thresholds, while Faster RCNN with ResNet demonstrated strong recall consistency. These findings provide a comparative analysis, highlighting the strengths and limitations of each model for reliable and efficient intestinal parasite detection, suggesting the integration of ensemble models to combine RetinaNet’s robustness and YOLOv8’s precision-recall capabilities for optimized results. Atlantis Press 2025 Conference or Workshop Item PeerReviewed pdf en https://umpir.ump.edu.my/id/eprint/45627/1/Detection%20and%20Classification%20of%20Intestinal%20Parasites%20Using%20Advanced%20Object%20Detection%20Models%20-%20haifa%20Ahmed.pdf Hamza, Haifa and Kamarul Hawari, Ghazali and Ahmad, Abubakar (2025) Detection and classification of intestinal parasites using advanced object detection models. In: Proceedings of the 3rd Lawang Sewu International Symposium on Engineering and Applied Sciences (LEWIS-EAS 2024). 3rd Lawang Sewu International Symposium on Engineering and Applied Sciences (LEWIS-EAS 2024) , 7 December 2024 , Semarang, Indonesia (Online). pp. 47-57.. ISSN 2352-5401 ISBN 978-94-6463-764-9 (Published) https://doi.org/10.2991/978-94-6463-764-9_6
spellingShingle QA75 Electronic computers. Computer science
T Technology (General)
Hamza, Haifa
Kamarul Hawari, Ghazali
Ahmad, Abubakar
Detection and classification of intestinal parasites using advanced object detection models
title Detection and classification of intestinal parasites using advanced object detection models
title_full Detection and classification of intestinal parasites using advanced object detection models
title_fullStr Detection and classification of intestinal parasites using advanced object detection models
title_full_unstemmed Detection and classification of intestinal parasites using advanced object detection models
title_short Detection and classification of intestinal parasites using advanced object detection models
title_sort detection and classification of intestinal parasites using advanced object detection models
topic QA75 Electronic computers. Computer science
T Technology (General)
url https://umpir.ump.edu.my/id/eprint/45627/
https://umpir.ump.edu.my/id/eprint/45627/