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

Three-Dimensional Microscopy in Microbiology

Three-Dimensional Microscopy in Microbiology

Three-dimensional imaging techniques are essential in cell biology, allowing researchers to visualize intricate cellular structures with high resolution. Two prominent methods, Differential Interference Contrast Microscopy (DIC) and Confocal Scanning Laser Microscopy (CSLM), provide distinct advantages for imaging live and thick specimens, respectively.Differential Interference Contrast MicroscopyDIC microscopy enhances contrast in transparent, unstained samples by converting phase...

You might also read

Related Articles

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

Sort by

Same author

Increasing the utilisation of hydroxychloroquine blood level testing in lupus: a quality improvement project.

Lupus science & medicine·2026

Same author

Rose Bengal Electromagnetic Activation With Green Light for Infection Reduction: Follow-Up of a Randomized Clinical Trial.

JAMA ophthalmology·2026

Same author

How I Do It: Designing A Scalable, Low-Cost Simulation Platform for Global Laparoscopic Training.

Journal of surgical education·2026

Same author

Vision in the margins: the association between census tract neighbourhood disadvantage and visual difficulty and blindness in the United States.

Eye (London, England)·2026

Same author

Distinguishing Factors for Microbial Keratitis Groups: A Cross-Sectional Survey of US Cornea Specialists.

Cornea·2026

Same author

Early Treatment Response and 90-Day Vision in Microbial Keratitis.

JAMA ophthalmology·2026

Search research articles

Related Experiment Video

Updated: Jun 17, 2026

In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model

In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model

Published on: January 21, 2018

Association of Deep Learning Imaging Algorithm Measures of Microbial Keratitis With Vision Outcomes.

Emily L Vogt¹, Leslie M Niziol¹, Ziyun Yang²

¹Department of Ophthalmology and Visual Sciences, Kellogg Eye Center, University of Michigan, Ann Arbor, MI.

|November 17, 2025

Summary

Artificial intelligence accurately predicts vision loss in microbial keratitis patients by analyzing corneal changes. AI measurements of stromal infiltrate and hypopyon correlate with vision outcomes, similar to clinician assessments.

Keywords:

artificial intelligence deep learning microbial keratitis slit lamp photography vision outcomes

More Related Videos

Intravitreal Injection and Quantitation of Infection Parameters in a Mouse Model of Bacterial Endophthalmitis

Intravitreal Injection and Quantitation of Infection Parameters in a Mouse Model of Bacterial Endophthalmitis

Published on: February 6, 2021

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

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

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jun 17, 2026

In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model

In Vivo Multimodal Imaging and Analysis of Mouse Laser-Induced Choroidal Neovascularization Model

Published on: January 21, 2018

Intravitreal Injection and Quantitation of Infection Parameters in a Mouse Model of Bacterial Endophthalmitis

Intravitreal Injection and Quantitation of Infection Parameters in a Mouse Model of Bacterial Endophthalmitis

Published on: February 6, 2021

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

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

Published on: November 30, 2022

Area of Science:

Ophthalmology
Medical Imaging
Artificial Intelligence

Background:

Microbial keratitis can lead to significant vision impairment.
Accurate assessment of corneal changes is crucial for predicting visual outcomes.
Current methods rely on clinician expertise, which can be subjective.

Purpose of the Study:

To compare the predictive accuracy of an AI algorithm versus clinician measurements for 90-day vision outcomes in microbial keratitis.
To assess the association between AI-quantified corneal changes and visual acuity.
To evaluate the utility of AI in managing microbial keratitis.

Main Methods:

Prospective cohort study in the US and India.
Collected clinical data, visual acuity, and slitlamp images.
Developed an AI imaging segmentation algorithm to quantify stromal infiltrate (SI) area and hypopyon presence.
Used multivariable linear regression to assess associations between AI-predicted measurements and 90-day visual acuity.

Main Results:

Larger AI-predicted SI area was associated with worse 90-day vision across bacterial, fungal, and viral ulcers in the US.
In India, larger AI-predicted SI area and AI-predicted hypopyon were linked to worse 90-day vision.
AI-based measurements showed similar associations with visual outcomes as clinician measurements.

Conclusions:

AI algorithms can effectively predict vision outcomes in microbial keratitis.
AI-quantified corneal changes, including SI area and hypopyon, are significant predictors of vision loss.
AI offers a promising tool for objective assessment and management of microbial keratitis.