Related Experiment Video
Updated: Jan 12, 2026
08:20
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
Published on: October 27, 2023
2.4K
Automated detection of pinworm parasite eggs using YOLO convolutional block attention module for enhanced microscopic
Esraa Hassan1, Felwah Alqahtani2, Samar Elbedwehy1
1Faculty of Artificial Intelligence, Kafrelsheikh University, Kafrelsheikh, Egypt.
Frontiers in Bioengineering and Biotechnology
|October 31, 2025
Summary
A new automated system, YOLO Convolutional Block Attention Module (YCBAM), accurately detects pinworm eggs in microscopic images. This deep learning approach enhances parasitic infection diagnosis, improving efficiency and reducing errors in medical parasitology.
Area of Science:
- Medical Parasitology
- Computational Biology
- Medical Imaging
Background:
- Parasitic infections pose significant public health challenges, necessitating rapid and accurate diagnostics.
- Traditional microscopic examination for parasites is labor-intensive and prone to errors.
- Automated imaging and deep learning offer advancements for diagnostic efficiency.
Purpose of the Study:
- To develop and evaluate an automated framework for detecting pinworm parasite eggs.
- To enhance the accuracy and efficiency of parasitic infection diagnosis using artificial intelligence.
Main Methods:
- Proposed a novel framework: YOLO Convolutional Block Attention Module (YCBAM).
- Integrated YOLO with self-attention mechanisms and Convolutional Block Attention Module (CBAM).
- Applied the framework to automate the detection and localization of pinworm eggs in microscopic images.
Main Results:
- YCBAM achieved high precision (0.9971) and recall (0.9934).
- Demonstrated superior detection performance with a mean Average Precision (mAP) of 0.9950.
- The model showed efficient learning and convergence with a low training box loss (1.1410).
Conclusions:
- The YCBAM framework significantly improves automated detection of pinworm eggs.
- Offers a highly accurate and reliable tool for medical parasitology diagnostics.
- Has the potential to reduce diagnostic errors and support clinical decision-making.
