Detection and classification of intestinal parasites with bayesian-optimized model
Automated detection of intestinal parasites in medical imaging enhances diagnostic efficiency and reduces human error. This study evaluates object detection techniques using Faster R-CNN with different backbone architectures such as ResNet, RetinaNet, ResNext and YOLOv8 series for detecting Ascaris...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Science and Information (SAI) Organization Limited
2025
|
| Subjects: | |
| Online Access: | https://umpir.ump.edu.my/id/eprint/45625/ |
| _version_ | 1848827469017120768 |
|---|---|
| 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 in medical imaging enhances diagnostic efficiency and reduces human error. This study evaluates object detection techniques using Faster R-CNN with different backbone architectures such as ResNet, RetinaNet, ResNext and YOLOv8 series for detecting Ascaris lumbricoides and Trichuris trichiura in microscopic images. A dataset of 2000 images was split into training (1500), validation (300), and testing (200). Results show Faster R-CNN with RetinaNet achieves the highest Average Precision (AP) across varying Intersection over Union (IoU) thresholds, making it robust in feature extraction. However, YOLOv8 excels in real-time detection, with YOLOv8n (nano) providing the best trade-off between accuracy and computational efficiency. Bayesian Optimization further improves YOLOv8n, achieving an AP of 99.6% and an Average Recall (AR) of 99.7%, surpassing two-stage architectures. This study highlights the potential of deep learning for automated parasite detection, reducing reliance on manual microscopy. Future research should explore transformer-based models, self-supervised learning, and mobile deployment for real-world clinical applications. |
| first_indexed | 2025-11-15T04:01:12Z |
| format | Article |
| id | ump-45625 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T04:01:12Z |
| publishDate | 2025 |
| publisher | The Science and Information (SAI) Organization Limited |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-456252025-09-12T06:47:14Z https://umpir.ump.edu.my/id/eprint/45625/ Detection and classification of intestinal parasites with bayesian-optimized model Hamza, Haifa Kamarul Hawari, Ghazali Ahmad, Abubakar QA76 Computer software T Technology (General) Automated detection of intestinal parasites in medical imaging enhances diagnostic efficiency and reduces human error. This study evaluates object detection techniques using Faster R-CNN with different backbone architectures such as ResNet, RetinaNet, ResNext and YOLOv8 series for detecting Ascaris lumbricoides and Trichuris trichiura in microscopic images. A dataset of 2000 images was split into training (1500), validation (300), and testing (200). Results show Faster R-CNN with RetinaNet achieves the highest Average Precision (AP) across varying Intersection over Union (IoU) thresholds, making it robust in feature extraction. However, YOLOv8 excels in real-time detection, with YOLOv8n (nano) providing the best trade-off between accuracy and computational efficiency. Bayesian Optimization further improves YOLOv8n, achieving an AP of 99.6% and an Average Recall (AR) of 99.7%, surpassing two-stage architectures. This study highlights the potential of deep learning for automated parasite detection, reducing reliance on manual microscopy. Future research should explore transformer-based models, self-supervised learning, and mobile deployment for real-world clinical applications. The Science and Information (SAI) Organization Limited 2025 Article PeerReviewed pdf en cc_by_4 https://umpir.ump.edu.my/id/eprint/45625/1/Detection_and_Classification_of_Intestinal_Parasites%20%281%29%20-%20haifa%20Ahmed.pdf Hamza, Haifa and Kamarul Hawari, Ghazali and Ahmad, Abubakar (2025) Detection and classification of intestinal parasites with bayesian-optimized model. International Journal of Advanced Computer Science and Applications (IJACSA), 16 (4). pp. 1-12. ISSN 2156-5570(Online). (Published) https://dx.doi.org/10.14569/IJACSA.2025.0160492 10.14569/IJACSA.2025.0160492 10.14569/IJACSA.2025.0160492 |
| spellingShingle | QA76 Computer software T Technology (General) Hamza, Haifa Kamarul Hawari, Ghazali Ahmad, Abubakar Detection and classification of intestinal parasites with bayesian-optimized model |
| title | Detection and classification of intestinal parasites with bayesian-optimized model |
| title_full | Detection and classification of intestinal parasites with bayesian-optimized model |
| title_fullStr | Detection and classification of intestinal parasites with bayesian-optimized model |
| title_full_unstemmed | Detection and classification of intestinal parasites with bayesian-optimized model |
| title_short | Detection and classification of intestinal parasites with bayesian-optimized model |
| title_sort | detection and classification of intestinal parasites with bayesian-optimized model |
| topic | QA76 Computer software T Technology (General) |
| url | https://umpir.ump.edu.my/id/eprint/45625/ https://umpir.ump.edu.my/id/eprint/45625/ https://umpir.ump.edu.my/id/eprint/45625/ |