Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Two-Dimensional Microscopy in Microbiology

Two-Dimensional Microscopy in Microbiology

Two-dimensional (2D) microscopy encompasses a range of optical techniques that capture images within a single focal plane, offering detailed representations of microscopic structures. These techniques are essential in biological and medical research, enabling the visualization of cellular and subcellular structures with different levels of contrast and specificity.There are several major types of 2D microscopy, each with strengths and applications.Bright-Field MicroscopyBright-field microscopy...

You might also read

Related Articles

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

Sort by

Same author

Automated HER2 Scoring with Uncertainty Quantification Using Lensfree Holography and Deep Learning.

BME frontiers·2026

Same author

Snapshot 3D image projection using a diffractive decoder.

Light, science & applications·2026

Same author

Autonomous Uncertainty Quantification for Computational Point-of-Care Sensors.

ACS nano·2026

Same author

Universal and transferable attacks on pathology foundation models using microscopic perturbations.

Light, science & applications·2026

Same author

Super-resolution image projection over an extended depth of field using a diffractive decoder.

Light, science & applications·2026

Same author

Deep learning-enhanced dual-mode multiplexed optical sensor for point-of-care diagnostics of cardiovascular diseases.

Light, science & applications·2026

Search research articles

Related Experiment Video

Updated: Jul 13, 2026

Induction of Cellular Differentiation and Single Cell Imaging of Vibrio parahaemolyticus Swimmer and Swarmer Cells

Induction of Cellular Differentiation and Single Cell Imaging of Vibrio parahaemolyticus Swimmer and Swarmer Cells

Published on: May 15, 2017

Deep learning-based detection of bacterial swarm motion using a single image.

Yuzhu Li^1,2,3, Hao Li⁴, Weijie Chen⁴

¹Electrical and Computer Engineering Department, University of California, Los Angeles, CA, USA.

|May 14, 2025

Summary

A new deep learning model accurately predicts bacterial swarming motility from single images, overcoming limitations of traditional methods. This AI approach offers rapid, objective, and potentially portable screening for diseases like IBD and UTI.

Keywords:

Bacterial motility deep learning in vitro diagnosis inflammatory bowel disease microbiome test swarming

More Related Videos

Time-lapse Imaging of Bacterial Swarms and the Collective Stress Response

Time-lapse Imaging of Bacterial Swarms and the Collective Stress Response

Published on: May 23, 2020

Quantifying Bacterial Surface Swarming Motility on Inducer Gradient Plates

Quantifying Bacterial Surface Swarming Motility on Inducer Gradient Plates

Published on: January 5, 2022

Related Experiment Videos

Last Updated: Jul 13, 2026

Induction of Cellular Differentiation and Single Cell Imaging of Vibrio parahaemolyticus Swimmer and Swarmer Cells

Induction of Cellular Differentiation and Single Cell Imaging of Vibrio parahaemolyticus Swimmer and Swarmer Cells

Published on: May 15, 2017

Time-lapse Imaging of Bacterial Swarms and the Collective Stress Response

Time-lapse Imaging of Bacterial Swarms and the Collective Stress Response

Published on: May 23, 2020

Quantifying Bacterial Surface Swarming Motility on Inducer Gradient Plates

Quantifying Bacterial Surface Swarming Motility on Inducer Gradient Plates

Published on: January 5, 2022

Area of Science:

Microbiology
Artificial Intelligence
Biotechnology

Background:

Bacterial motility, specifically swarming and swimming, is crucial for understanding bacterial behavior and disease.
Traditional methods for detecting bacterial swarming are qualitative, time-consuming, and prone to human bias.
Existing rapid methods still rely on expert interpretation and can be labor-intensive.

Purpose of the Study:

To develop a rapid, objective, and automated method for distinguishing bacterial swarming from swimming motility.
To create a deep learning model capable of predicting swarming probability from single, potentially blurry images.
To assess the performance and generalizability of the developed classifier across different bacterial species.

Main Methods:

A deep learning-based classifier was developed and trained on images of *Enterobacter sp*. SM3.
The model was designed to predict swarming probability using single blurry images, bypassing traditional video analysis.
Performance was evaluated using sensitivity and specificity metrics on both training and independent test datasets, including other bacterial species.

Main Results:

The deep learning classifier achieved high accuracy, with a sensitivity of 97.44% and a specificity of 100% for *Enterobacter sp*. SM3.
The model demonstrated robust generalization capabilities when tested on unseen species like *Serratia marcescens* and *Citrobacter koseri*.
The AI approach provides objective, quantitative assessments, outperforming traditional manual methods in speed and objectivity.

Conclusions:

A deep learning classifier offers a rapid, autonomous, and objective method for detecting bacterial swarming motility.
This AI-driven approach has the potential for high-throughput screening and integration into portable diagnostic devices.
The technology could significantly enhance early disease detection and treatment assessment for conditions like IBD and UTI.