Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Constructing a Predictive Model for STH and Schistosomiasis Classification From Microscopic Images.

BioMed research international·2025
See all related articles

Related Experiment Video

Updated: Mar 25, 2026

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.8K

Constructing a Predictive Model for STH and Schistosomiasis Classification From Microscopic Images.

Etefa Belachew1, Kris Calpotura1, Abrham Adamu2

  • 1Faculty of Electrical and Computer Engineering, Jimma University-Institute of Technology, Jimma, Ethiopia.

Biomed Research International
|March 24, 2026
PubMed
Summary

A new hybrid machine learning (ML) and deep learning system significantly improves the accuracy and speed of diagnosing parasitic diseases like soil-transmitted helminths (STHs) and schistosomiasis from microscope images. This AI-powered tool offers a faster, more accurate alternative for resource-limited settings.

Keywords:
STH and schistosomiasisViTdeep learningdigital image processingmachine learningpretrained models

More Related Videos

Cercarial Transformation and in vitro Cultivation of Schistosoma mansoni Schistosomules
05:30

Cercarial Transformation and in vitro Cultivation of Schistosoma mansoni Schistosomules

Published on: August 16, 2011

18.8K
Using Eggs from Schistosoma mansoni as an In vivo Model of Helminth-induced Lung Inflammation
09:58

Using Eggs from Schistosoma mansoni as an In vivo Model of Helminth-induced Lung Inflammation

Published on: June 5, 2012

14.4K

Related Experiment Videos

Last Updated: Mar 25, 2026

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.8K
Cercarial Transformation and in vitro Cultivation of Schistosoma mansoni Schistosomules
05:30

Cercarial Transformation and in vitro Cultivation of Schistosoma mansoni Schistosomules

Published on: August 16, 2011

18.8K
Using Eggs from Schistosoma mansoni as an In vivo Model of Helminth-induced Lung Inflammation
09:58

Using Eggs from Schistosoma mansoni as an In vivo Model of Helminth-induced Lung Inflammation

Published on: June 5, 2012

14.4K

Area of Science:

  • Medical Parasitology
  • Artificial Intelligence in Healthcare
  • Image Analysis

Background:

  • Soil-transmitted helminths (STHs) and schistosomiasis cause significant health and economic burdens in tropical regions, especially Africa.
  • Accurate and rapid diagnosis is crucial for effective disease control, but traditional microscopy is slow and labor-intensive, particularly in resource-limited areas like Ethiopia.

Purpose of the Study:

  • To develop and evaluate an innovative system combining machine learning (ML) and deep learning for rapid and accurate analysis of parasite egg images.
  • To compare the performance of a hybrid CNN-ML approach against standalone deep learning models and vision transformers (ViTs) for classifying five diagnostic categories.

Main Methods:

  • A dataset of 1490 microscope images of parasite eggs (Ascaris, hookworm, schistosomiasis, Trichuris, and negative samples) was utilized.
  • Convolutional Neural Network (CNN) architectures (VGG16, ResNet50, DenseNet121, MobileNetV2, EfficientNetB0) and Vision Transformers (ViTs) were employed as feature extractors.
  • Machine learning classifiers (SVM, XGBoost, KNN, RF, DT) were used for prediction, creating hybrid CNN-ML models.

Main Results:

  • The hybrid CNN-ML models achieved superior performance, with VGG16-SVM and VGG16-XGBoost reaching test accuracies of 99.31% and 99.35%, respectively.
  • Standalone CNN models demonstrated significantly lower accuracy (e.g., VGG16 at 79.98%, DenseNet121 at 84.12%).
  • While negative samples were classified with high accuracy, performance on specific parasite classes varied by model architecture.

Conclusions:

  • The developed hybrid CNN-ML system offers enhanced diagnostic utility for STHs and schistosomiasis, particularly in low-resource settings, by enabling real-time image analysis.
  • The study highlights the potential of integrating ML with deep learning for improved parasitic disease diagnostics.
  • Limitations include a small, aged dataset with potential degradation, impacting generalizability.