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

Hantavirus infection in returned travellers: data from the GeoSentinel Network.

Journal of travel medicine·2026
Same author

From the Laboratory to the Field: Assessing the Usability of the NTDscope in the Tropical Rainforest Region of Gabon.

The American journal of tropical medicine and hygiene·2026
Same author

Ebola virus disease.

CMAJ : Canadian Medical Association journal = journal de l'Association medicale canadienne·2026
Same author

Transmission dynamics of Andes virus and implications for outbreak monitoring.

The Lancet. Microbe·2026
Same author

HIV post-exposure prophylaxis (PEP) and PEP-in-pocket (PIP) for women: A rodgers' evolutionary concept analysis.

Women's health (London, England)·2026
Same author

Combined high-quality metagenomics reveals off-target effects of albendazole, ivermectin-albendazole and moxidectin-albendazole on the human gut bacteria.

NPJ biofilms and microbiomes·2026

Related Experiment Video

Updated: Sep 12, 2025

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

1.7K

Multi-contrast machine learning improves schistosomiasis diagnostic performance.

María Díaz de León Derby1, Charles B Delahunt2, Ethan Spencer2

  • 1Department of Bioengineering, University of California, Berkeley, Berkeley, California, United States of America.

Plos Neglected Tropical Diseases
|August 4, 2025
PubMed
Summary
This summary is machine-generated.

Machine learning models using darkfield (DF) and brightfield (BF) imaging significantly improved automated detection of Schistosoma haematobium eggs. This combined approach enhances diagnostic accuracy for schistosomiasis control efforts.

More Related Videos

Comparative Analysis of Automatic Fecal Analyzer versus Direct Wet Smear Microscopy for Detecting Parasitic Infections in Stool Samples
04:57

Comparative Analysis of Automatic Fecal Analyzer versus Direct Wet Smear Microscopy for Detecting Parasitic Infections in Stool Samples

Published on: April 25, 2025

596
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K

Related Experiment Videos

Last Updated: Sep 12, 2025

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

1.7K
Comparative Analysis of Automatic Fecal Analyzer versus Direct Wet Smear Microscopy for Detecting Parasitic Infections in Stool Samples
04:57

Comparative Analysis of Automatic Fecal Analyzer versus Direct Wet Smear Microscopy for Detecting Parasitic Infections in Stool Samples

Published on: April 25, 2025

596
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K

Area of Science:

  • Medical diagnostics
  • Parasitology
  • Machine learning in healthcare

Background:

  • Schistosomiasis affects over 250 million people globally, posing a significant public health challenge.
  • Accurate diagnosis of Schistosoma haematobium relies on microscopy, which requires skilled personnel for egg identification.
  • Existing diagnostic methods face limitations in speed and accessibility, particularly in resource-limited settings.

Purpose of the Study:

  • To develop and evaluate a machine learning (ML)-based strategy for automated detection of Schistosoma haematobium eggs.
  • To improve diagnostic performance by combining brightfield (BF) and darkfield (DF) imaging techniques.
  • To assess the feasibility of using a mobile phone-based microscope for automated schistosomiasis diagnosis.

Main Methods:

  • Collected paired brightfield (BF) and darkfield (DF) images of urine samples using a mobile phone-based microscope (SchistoScope).
  • Trained separate ML models for egg detection using BF and DF images, and compared their performance individually and in combination.
  • Validated model performance against annotations from trained microscopists, using data from two field studies in Côte d'Ivoire.

Main Results:

  • ML models trained on DF images and combined BF/DF images significantly outperformed models trained solely on BF images.
  • Patient-level classification performance met WHO Diagnostic Target Product Profile (TPP) for sensitivity (>75%) and specificity (>96.5%) in monitoring and evaluation.
  • Utilizing images from both field studies for training further improved model performance.

Conclusions:

  • Combining darkfield and brightfield imaging enhances the performance of ML models for automated detection of Schistosoma haematobium eggs.
  • This approach improves diagnostic accuracy using low-cost optics while maintaining portability and rapid results, aligning with WHO TPP.
  • Darkfield imaging offers a practical, no-additional-preparation method to boost automated microscopy diagnostics for schistosomiasis and other conditions.