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 Experiment Videos

Mathematical algorithm for the automatic recognition of intestinal parasites.

Alicia Alva1, Carla Cangalaya1,2,3, Miguel Quiliano1

  • 1Unidad de Bioinformática, Laboratorios de Investigación y Desarrollo, Facultad de Ciencias y Filosofía, Universidad Peruana Cayetano Heredia, Lima, Perú.

Plos One
|April 15, 2017
PubMed
Summary

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

Pericystic brain transcriptomics reveals molecular signatures of immune activation and neurovascular remodelling in viable and post-treatment porcine neurocysticercosis.

bioRxiv : the preprint server for biology·2026
Same author

Gene-specific Functional Roles of MSMEG_5046 , MSMEG_0241 , and MSMEG_0232 in Pyrazinoic Acid Efflux Identified through Clustered Regularly Interspaced Short Palindromic Repeat Interference.

International journal of mycobacteriology·2026
Same author

Detection of heteroresistance in Mycobacterium tuberculosis using nanopore-based amplicon sequencing and adaptive sampling.

Scientific reports·2026
Same author

A framework for the development and validation of an aptamer-based assay for pathogen detection using SARS-CoV-2 as a model.

Scientific reports·2026
Same author

Reimagining plant science training in the era of generative artificial intelligence: a global perspective.

The Plant cell·2026
Same author

Platelet-leucocyte interactions drive MMP-mediated tissue damage in tuberculosis.

PLoS pathogens·2026

A new software uses pattern recognition to automatically diagnose common human intestinal parasites from fecal smear images. This tool achieves high sensitivity and specificity, addressing a critical need in areas with limited medical specialists.

Area of Science:

  • Medical Parasitology
  • Computer Vision
  • Medical Diagnostics

Background:

  • Parasitic infections are diagnosed via microscopic examination of fecal smears by trained professionals.
  • Shortage of medical specialists in endemic regions hinders accurate diagnosis.
  • Automated diagnostic tools are needed to improve accessibility and efficiency.

Purpose of the Study:

  • To develop and evaluate a pattern recognition software for automated diagnosis of human intestinal parasites.
  • To assess the sensitivity and specificity of the algorithm in identifying specific parasite species.

Main Methods:

  • A dataset of microscopic images of fecal smears positive for Taenia sp., Trichuris trichiura, Diphyllobothrium latum, and Fasciola hepatica was compiled.
  • A 14-step image processing algorithm was implemented in SCILAB, involving grayscale conversion, filtering, and skeletonization.

Related Experiment Videos

  • Geometric and brightness features were extracted and analyzed using logistic regression for parasite identification.

    • Main Results:

    • The algorithm achieved high diagnostic performance, with sensitivities ranging from 99.10% to 100% and specificities between 98.13% and 98.38% for individual parasite detection.
    • No cross-reactivity was observed between the algorithms for the evaluated parasites.
    • The software demonstrated robust accuracy in identifying Taenia sp., Trichuris trichiura, Diphyllobothrium latum, and Fasciola hepatica.

    Conclusions:

    • The developed computer algorithm effectively automates the recognition and diagnosis of common human intestinal parasites.
    • The software offers a promising solution for improving parasitic infection diagnosis in resource-limited settings.
    • High sensitivity and specificity indicate the reliability of this automated diagnostic approach.