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

Vision01:24

Vision

61.2K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
61.2K
Confocal Fluorescence Microscopy01:16

Confocal Fluorescence Microscopy

21.7K
Confocal microscopy is an advanced microscopic technique. The prime advantage of the confocal microscope over other microscopy techniques is its ability to block the out-of-focus light from the illuminated samples using pinholes. It is widely used with fluorescence optics to obtain high-resolution, sharp contrast images. Unlike optical microscopes, confocal microscopes use a focused beam of light laser to scan the entire sample surface at different z-planes. These microscopes are, therefore,...
21.7K

You might also read

Related Articles

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

Sort by
Same author

Estimation of cycloplegic spherical refraction from non-cycloplegic clinical and biometric data in children using machine learning: a retrospective pilot study for screening triage.

BMC ophthalmology·2026
Same author

Comparative analysis of GPT-4o as a representative multimodal large language model and human fitters in orthokeratology lens fitting: Assessing accuracy, efficiency and cost-effectiveness in initial lens parameter selection.

Acta ophthalmologica·2026
Same author

Evaluating reasoning in multimodal large language models for ophthalmology: a bilingual benchmark study using clinical vignettes and imaging.

The British journal of ophthalmology·2026
Same author

Early postoperative alignment as a predictor of recurrence after unilateral recession-plication for basic-type intermittent exotropia in children.

BMC ophthalmology·2026
Same author

Multi-modal large language models for paediatric tele-ophthalmology: A blinded real-world evaluation of diagnostic accuracy and safety.

Acta ophthalmologica·2026
Same author

Integrating AI, imaging innovations and omics for precision medicine.

BMJ open ophthalmology·2026

Related Experiment Video

Updated: Mar 16, 2026

Scanning Light Scattering Profiler SLPS Based Methodology to Quantitatively Evaluate Forward and Backward Light Scattering from Intraocular Lenses
06:55

Scanning Light Scattering Profiler SLPS Based Methodology to Quantitatively Evaluate Forward and Backward Light Scattering from Intraocular Lenses

Published on: June 6, 2017

8.0K

Report Generation System for Slit-Lamp Image Interpretation Using Vision-Language Models.

Xin Ye1, Yingjiao Shen1, Qian Chen2

  • 1Department of Ophthalmology, Zhejiang Provincial People's Hospital (Affiliated People's Hospital, Hangzhou Medical College), Hangzhou, Zhejiang, China.

Ophthalmology and Therapy
|March 14, 2026
PubMed
Summary

This study developed an interpretation pipeline for slit-lamp (SL) images using vision-language models (VLMs) to generate medical reports. The developed LLaVA and Qwen2.5-VL frameworks showed promising results in assisting ophthalmologists with ophthalmic image interpretation.

Keywords:
Medical report generationSlit-lampVision-language model

More Related Videos

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
07:11

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

2.5K
Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT
12:22

Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT

Published on: August 4, 2018

9.1K

Related Experiment Videos

Last Updated: Mar 16, 2026

Scanning Light Scattering Profiler SLPS Based Methodology to Quantitatively Evaluate Forward and Backward Light Scattering from Intraocular Lenses
06:55

Scanning Light Scattering Profiler SLPS Based Methodology to Quantitatively Evaluate Forward and Backward Light Scattering from Intraocular Lenses

Published on: June 6, 2017

8.0K
Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
07:11

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

2.5K
Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT
12:22

Multimodal Volumetric Retinal Imaging by Oblique Scanning Laser Ophthalmoscopy oSLO and Optical Coherence Tomography OCT

Published on: August 4, 2018

9.1K

Area of Science:

  • Ophthalmology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Slit-lamp (SL) imaging is crucial for diagnosing ophthalmic conditions.
  • Automated interpretation of SL images can improve diagnostic efficiency.
  • Vision-language models (VLMs) offer potential for image interpretation and report generation.

Purpose of the Study:

  • To develop and evaluate an interpretation pipeline for SL image report generation using VLMs.
  • To finetune and assess the performance of LLaVA and Qwen2.5-VL frameworks for ophthalmic image analysis.
  • To explore the potential of VLMs in assisting ophthalmologists and enhancing patient care.

Main Methods:

  • Developed an image-text alignment module using Bootstrapping Language-Image Pretraining (BLIP).
  • Finetuned LLaVA and Qwen2.5-VL frameworks on a dataset of SL images and medical reports from Zhaohui Hospital.
  • Validated the frameworks using an external dataset from Bijie Hospital.

Main Results:

  • Refined LLaVA and Qwen2.5-VL models achieved high performance in report generation, with LLaVA showing slightly better scores in correctness, completeness, and satisfaction.
  • Both models demonstrated strong disease classification accuracy (0.87-0.88), particularly for common conditions like glaucoma and conjunctivitis.
  • Interobserver agreement among ophthalmologists was substantial (κ scores 0.714-0.777).

Conclusions:

  • The developed framework effectively generates reports for SL images, enhancing ophthalmic image interpretation.
  • VLMs show significant potential to aid ophthalmologists in clinical practice.
  • This technology can improve diagnostic accuracy and streamline reporting for ophthalmic conditions.