Related Experiment Video
Updated: Jun 12, 2025
Comparative Analysis of Automatic Fecal Analyzer versus Direct Wet Smear Microscopy for Detecting Parasitic Infections in Stool Samples
Published on: April 25, 2025
Development of a Machine Learning Model for the Classification of Enterobius vermicularis Egg
Natthanai Chaibutr1,2,3, Pongphan Pongpanitanont4, Sakhone Laymanivong5
1Medical Innovation and Technology Program, School of Allied Health Sciences, Walailak University, Nakhon Si Thammarat 80160, Thailand.
Insights
Automated detection of pinworm (Enterobius vermicularis) eggs using convolutional neural networks (CNNs) significantly improves diagnostic accuracy. Data augmentation enhanced CNN performance, offering a more efficient alternative to traditional methods.
Area of Science:
- Medical diagnostics
- Computational biology
- Parasitology
Background:
- Enterobius vermicularis infections are common globally, particularly in children.
- Current diagnosis relies on the time-consuming scotch tape technique, requiring expert microscopic examination.
- Automated detection using artificial intelligence offers potential for improved efficiency and accuracy.
Purpose of the Study:
- To enhance the automated detection of Enterobius vermicularis eggs using convolutional neural networks (CNNs).
- To benchmark a proposed CNN model against leading models for pinworm egg detection.
- To evaluate the impact of data augmentation on diagnostic performance.
Main Methods:
- Digitization and augmentation of 40,000 microscopic images of E. vermicularis eggs and artifacts.
- Training and validation using an 80:20 split and five-fold cross-validation.
- Development and benchmarking of a CNN model, including the Xception architecture.
Main Results:
- The proposed CNN model achieved 90.0% accuracy, precision, recall, and F1-score after data augmentation.
- Data augmentation improved model stability, increasing ROC-AUC from 0.77 to 0.97.
- The Xception model demonstrated superior performance with 99.0% accuracy, precision, recall, and F1-score.
Conclusions:
- Data augmentation and advanced CNN architectures significantly improve the accuracy and efficiency of E. vermicularis diagnosis.
- AI-powered tools can provide a reliable and faster alternative to traditional pinworm detection methods.
- The developed CNN models show comparable performance to larger models despite smaller file sizes.
Abstract:
Enterobius vermicularis (pinworm) infections are a significant global health issue, affecting children predominantly in environments like schools and daycares. Traditional diagnosis using the scotch tape technique involves examining E. vermicularis eggs under a microscope. This method is time-consuming and depends heavily on the examiner's expertise. To improve this, convolutional neural networks (CNNs) have been used to automate the detection of pinworm eggs from microscopic images. In our study, we enhanced E. vermicularis egg detection using a CNN benchmarked against leading models. We digitized and augmented 40,000 images of E. vermicularis eggs (class 1) and artifacts (class 0) for comprehensive training, using an 80:20 training-validation and a five-fold cross-validation. The proposed CNN model showed limited initial performance but achieved 90.0% accuracy, precision, recall, and F1-score after data augmentation. It also demonstrated improved stability with an ROC-AUC metric increase from 0.77 to 0.97. Despite its smaller file size, our CNN model performed comparably to larger models. Notably, the Xception model achieved 99.0% accuracy, precision, recall, and F1-score. These findings highlight the effectiveness of data augmentation and advanced CNN architectures in improving diagnostic accuracy and efficiency for E. vermicularis infections.
