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

Interfacial Compatibility and Performance Evaluation of Waste Plastic Aggregate in SBS-Modified Asphalt Mixtures Using Liquid Anti-Stripping Agents.

Polymers·2026
Same author

Publisher Correction: High-resolution functional mapping of androgen receptor variants.

Nature biomedical engineering·2026
Same author

Durability of Polymer-Modified Reclaimed Asphalt Mixtures Rejuvenated with Simulated Waste Cooking Oils from Palm, Soy, Olive, and Rice Oils.

Polymers·2026
Same author

High-resolution functional mapping of androgen receptor variants.

Nature biomedical engineering·2026
Same author

Model-informed development of bacteriophage therapy: bridging <i>in vitro</i> and <i>in vivo</i> efficacy against multidrug-resistant <i>Pseudomonas aeruginosa</i>.

mSystems·2025
Same author

A human gut metagenome-assembled genome catalogue spanning 41 countries supports genome-scale metabolic models.

Nature microbiology·2025

Related Experiment Video

Updated: Oct 1, 2025

Rapid Antimicrobial Susceptibility Testing by Stimulated Raman Scattering Imaging of Deuterium Incorporation in a Single Bacterium
12:08

Rapid Antimicrobial Susceptibility Testing by Stimulated Raman Scattering Imaging of Deuterium Incorporation in a Single Bacterium

Published on: February 14, 2022

2.9K

Rapid Bacterial Detection in Urine Using Laser Scattering and Deep Learning Analysis.

Kwang Seob Lee1, Hyung Jae Lim2, Kyungnam Kim3

  • 1Department of Laboratory Medicine, Yonsei University College of Medicine, Seoul, South Korea.

Microbiology Spectrum
|March 2, 2022
PubMed
Summary

Deep learning analyzes laser scattering patterns from urine bacteria to predict infections. This 30-minute method accurately identifies bacterial presence and Gram staining, offering a novel screening tool for urinary tract infections.

Keywords:
deep learninglaser scatterpredictionrapid testsurinary tract infection

More Related Videos

Detection of Tissue-resident Bacteria in Bladder Biopsies by 16S rRNA Fluorescence In Situ Hybridization
09:50

Detection of Tissue-resident Bacteria in Bladder Biopsies by 16S rRNA Fluorescence In Situ Hybridization

Published on: October 18, 2019

9.6K
Optical Screening of Novel Bacteria-specific Probes on Ex Vivo Human Lung Tissue by Confocal Laser Endomicroscopy
09:24

Optical Screening of Novel Bacteria-specific Probes on Ex Vivo Human Lung Tissue by Confocal Laser Endomicroscopy

Published on: November 29, 2017

7.7K

Related Experiment Videos

Last Updated: Oct 1, 2025

Rapid Antimicrobial Susceptibility Testing by Stimulated Raman Scattering Imaging of Deuterium Incorporation in a Single Bacterium
12:08

Rapid Antimicrobial Susceptibility Testing by Stimulated Raman Scattering Imaging of Deuterium Incorporation in a Single Bacterium

Published on: February 14, 2022

2.9K
Detection of Tissue-resident Bacteria in Bladder Biopsies by 16S rRNA Fluorescence In Situ Hybridization
09:50

Detection of Tissue-resident Bacteria in Bladder Biopsies by 16S rRNA Fluorescence In Situ Hybridization

Published on: October 18, 2019

9.6K
Optical Screening of Novel Bacteria-specific Probes on Ex Vivo Human Lung Tissue by Confocal Laser Endomicroscopy
09:24

Optical Screening of Novel Bacteria-specific Probes on Ex Vivo Human Lung Tissue by Confocal Laser Endomicroscopy

Published on: November 29, 2017

7.7K

Area of Science:

  • Microbiology
  • Biomedical Engineering
  • Artificial Intelligence

Background:

  • Laser scattering patterns from urine bacteria are complex and dynamic.
  • Deep learning requires analysis of spatial and temporal features for accurate bacterial identification.
  • Conventional urine analysis methods have limitations in rapid bacterial detection.

Purpose of the Study:

  • To develop and validate a deep learning model for predicting bacterial presence and Gram staining reactions in urine using laser scattering patterns.
  • To assess the model's accuracy at different bacterial densities (CFU/mL) and in clinical samples.
  • To establish laser scattering pattern analysis as a rapid screening tool for urinary tract infections.

Main Methods:

  • Deep learning algorithms were applied to analyze laser scattering patterns generated by bacteria in artificial urine.
  • The model was trained on data with varying bacterial densities and Gram staining characteristics.
  • Validation was performed using independent clinical urine samples from a tertiary hospital.

Main Results:

  • The model achieved 90.9% accuracy in predicting positive urine culture at a low cutoff of 1,000 CFU/mL.
  • Accuracy improved to 98.5% at a cutoff of 50,000 CFU/mL.
  • Satisfactory accuracy was obtained in predicting Gram staining reactions.

Conclusions:

  • Deep learning analysis of laser scattering patterns offers a rapid (30 min) and accurate method for predicting bacterial presence in urine.
  • This novel approach can serve as a standalone screening tool, complementing or preceding conventional urine culture.
  • The method shows potential for early detection and management of urinary tract infections.