An Efficient and Effective Framework for Intestinal Parasite Egg Detection Using YOLOv5.

Area of Science:

• Medical Imaging
• Parasitology
• Computer Vision

Background:

• Intestinal parasitic infections are a major global health concern, especially in tropical regions.
• Current manual microscopy for diagnosis is slow, expensive, and requires specialized expertise.
• Deep learning, particularly convolutional neural networks, shows promise for image analysis but is underutilized in parasitology.

Purpose of the Study:

• To develop and evaluate a novel deep learning model for detecting and classifying intestinal parasite eggs from images.
• To improve the speed and accuracy of intestinal parasite diagnosis.
• To reduce the workload on medical specialists and facilitate prompt patient treatment.

Main Methods:

• A transfer learning architecture was employed for image analysis.
• Image pre-processing and augmentation techniques were utilized.
• The YOLOv5 algorithm was implemented for detection and classification of parasite eggs.

Main Results:

• The proposed model achieved a mean average precision of approximately 97%.
• The detection time per sample was remarkably fast, averaging only 8.5 milliseconds.
• The system was trained and validated on a dataset of 5393 intestinal parasite images.

Conclusions:

• The developed deep learning approach offers a highly efficient and accurate method for detecting intestinal parasite eggs.
• This technology has the potential to form the basis for real-time diagnostic tools in clinical settings.
• The findings advance medical imaging and diagnostic capabilities for parasitic infections.