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

Environmental former <i>Massilia</i> group bacteria secrete metabolites that promote <i>Leptospira</i> growth.

mSystems·2026
Same author

Three Fatal Gestational Psittacosis Cases Caused by Chlamydia psittaci Strains Belonging to Closely Related Lineages, Japan.

Emerging infectious diseases·2026
Same author

Cigarette smoking and long-term incidence of colorectal cancer subclassified by tumor-infiltrating myeloid cells: A prospective cohort study.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

Tumor vessel phenotype in colorectal cancer microenvironment according to age at diagnosis.

British journal of cancer·2026
Same author

Aortic wall needle extraction: Difference between forceps and needle holder use.

Asian cardiovascular & thoracic annals·2026
Same author

Evaluation of Blood-Sampling Performance of Automatic Fingertip-Blood-Sampling System and Correlation Between Fingertip-Blood-Vessel Image and Blood-Sampling Volume.

Cardiovascular engineering and technology·2025
Same journal

Kombucha tea as a natural coagulant in legume-based milk systems: Optimization and characterization of fermented curds.

Journal of microbiological methods·2026
Same journal

A single-cell isolation strategy for screening diverse functional Haloarchaea strains.

Journal of microbiological methods·2026
Same journal

Body site-dependent variation in the human forensic microbiome: A comparative analysis of publicly available 16S rRNA gene amplicon data.

Journal of microbiological methods·2026
Same journal

Crude sap based colorimetric duplex RT-RPA assay for rapid detection of citrus yellow vein clearing virus and citrus yellow mottle-associated virus in citrus.

Journal of microbiological methods·2026
Same journal

Real-time quantitative PCR combined with propidium monoazide for simultaneous detection and quantification of Escherichia coli, Staphylococcus aureus and Salmonella spp. during processing of animal-based food products.

Journal of microbiological methods·2026
Same journal

A low-cost microbial bioassay for comparative assessment of nitrogen fixation in pesticide-exposed cyanobacteria.

Journal of microbiological methods·2026
See all related articles

Related Experiment Video

Updated: Jan 18, 2026

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
09:11

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

2.7K

Emulating visual evaluations in the microscopic agglutination test with deep learning.

Risa Nakano1, Yuji Oyamada1, Ryo Ozuru2

  • 1Graduate School of Engineering, Tottori University, Japan.

Journal of Microbiological Methods
|September 7, 2025
PubMed
Summary
This summary is machine-generated.

Deep learning models can now objectively estimate agglutination rates for diagnosing leptospirosis (a zoonotic disease), overcoming the subjectivity of the traditional Microscopic Agglutination Test (MAT). This approach promises more consistent and reproducible results for disease diagnosis.

Keywords:
Computer aided diagnosisDeep learningLeptospirosisMicroscopic agglutination testSerological test

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K
High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.5K

Related Experiment Videos

Last Updated: Jan 18, 2026

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
09:11

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

2.7K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K
High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.5K

Area of Science:

  • Veterinary Medicine
  • Microbiology
  • Artificial Intelligence

Background:

  • The Microscopic Agglutination Test (MAT) is the gold standard for diagnosing leptospirosis.
  • MAT results are subjective, leading to inter-observer variability and diagnostic inconsistencies.
  • Objective and reproducible diagnostic methods are needed for leptospirosis.

Purpose of the Study:

  • To develop a deep learning model to emulate expert MAT assessments.
  • To convert subjective expert evaluations into objective, reproducible numerical outputs.
  • To improve the objectivity and consistency of leptospirosis diagnosis.

Main Methods:

  • Utilized a pre-trained DenseNet121 deep learning model for image analysis.
  • Trained and validated the model on an in-house dataset of MAT images.
  • Employed UMAP for dimensionality reduction to visualize learned feature representations.

Main Results:

  • The deep learning network accurately estimated agglutination rates.
  • The model's performance approximated expert evaluations.
  • UMAP visualization confirmed the network learned features related to Leptospira abundance.

Conclusions:

  • Deep learning offers a consistent and objective method for estimating agglutination rates, mimicking expert judgment.
  • The developed model shows potential for improving leptospirosis diagnosis objectivity.
  • Enhanced interpretability of the deep learning model aids in understanding its behavior and potential clinical integration.