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 Experiment Video

Updated: Jun 2, 2026

Implantation and Evaluation of Melanoma in the Murine Choroid via Optical Coherence Tomography
05:46

Implantation and Evaluation of Melanoma in the Murine Choroid via Optical Coherence Tomography

Published on: December 2, 2022

Choroidal Melanocytic Lesion Detection Using Patch Vectors With a Foundational Vision Transformer.

Run Zhou David Ye1, David A Leske1, Mostafa Sadegh Mousavi1

  • 1Department of Ophthalmology, Mayo Clinic, Rochester, MN, USA.

Translational Vision Science & Technology
|June 1, 2026
PubMed
Summary
This summary is machine-generated.

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

Increasing Familial Retinoblastoma in High-Income Countries Despite Stable Overall Incidence, 2017-2024.

Ophthalmology. Retina·2026
Same author

Proliferative Diabetic Retinopathy Incidence and Outcomes in Younger Patients from 1970 to 2019.

Ophthalmology. Retina·2026
Same author

Wavefield-Aware quality control and shear wave speed estimation in ocular Vibro-Elastography.

Ultrasonics·2026
Same author

Clinical characteristics and outcomes of secondary orbital lymphoma.

European journal of ophthalmology·2026
Same author

When Does Acceptable Become Unacceptable? Toxicities of Emerging Therapies.

American Society of Clinical Oncology educational book. American Society of Clinical Oncology. Annual Meeting·2026
Same author

Novel uveal melanoma patient-derived cell line and organoid models show increased treatment resistance compared with commercially available cell lines.

Melanoma research·2026
Same journal

The Role of Nrf2 in SIRT1-Mediated RGC Neuroprotection in Traumatic Optic Neuropathy.

Translational vision science & technology·2026
Same journal

Explicit Inclusion of Diabetes Mellitus Without Retinopathy Within Diabetic Retinopathy Prediction.

Translational vision science & technology·2026
Same journal

Preclinical Safety and Feasibility Study of Line-Field Confocal Optical Coherence Tomography for Ophthalmology Applications.

Translational vision science & technology·2026
Same journal

Pathogenicity Analysis of Two Novel CRB1 Mutations in Three Chinese Inherited Retinal Dystrophy Families and a Literature Review.

Translational vision science & technology·2026
Same journal

Gas-Lesion Contact and Postural Compliance After Vitrectomy With Tamponade: A Continuous Monitoring and 3D Quantitative Analysis.

Translational vision science & technology·2026
Same journal

Automated Deep Learning Quantification of Avascular Area and Intravitreal Neovascularization in Retinal Flatmounts of Rodent Oxygen-Induced Retinopathy Models.

Translational vision science & technology·2026
See all related articles

Automated detection of choroidal melanocytic lesions using a self-supervised model improves early diagnosis of uveal melanoma. This reliable model achieves high accuracy, aiding in timely patient treatment and survival.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Early detection of uveal melanoma is crucial for patient survival.
  • Choroidal melanocytic lesions require accurate identification for timely diagnosis.

Purpose of the Study:

  • To develop an automated model for early detection of choroidal melanocytic lesions from fundus images.
  • To improve the diagnostic accuracy of uveal melanoma through advanced image analysis.

Main Methods:

  • A self-supervised model generated patch embeddings from 15 million ophthalmic images.
  • Latent embeddings were applied to fundus images from the Prospective Ocular Tumor Study (POTS) dataset.
  • A supervised classifier was trained on identified melanocytic lesions for detection.

More Related Videos

Transpupillary-Guided Trans-Scleral Transplantation of Subretinal Grafts in a Retinal Degeneration Mouse Model
07:37

Transpupillary-Guided Trans-Scleral Transplantation of Subretinal Grafts in a Retinal Degeneration Mouse Model

Published on: January 26, 2024

Limbal Approach-Subretinal Injection of Viral Vectors for Gene Therapy in Mice Retinal Pigment Epithelium
06:48

Limbal Approach-Subretinal Injection of Viral Vectors for Gene Therapy in Mice Retinal Pigment Epithelium

Published on: August 7, 2015

Related Experiment Videos

Last Updated: Jun 2, 2026

Implantation and Evaluation of Melanoma in the Murine Choroid via Optical Coherence Tomography
05:46

Implantation and Evaluation of Melanoma in the Murine Choroid via Optical Coherence Tomography

Published on: December 2, 2022

Transpupillary-Guided Trans-Scleral Transplantation of Subretinal Grafts in a Retinal Degeneration Mouse Model
07:37

Transpupillary-Guided Trans-Scleral Transplantation of Subretinal Grafts in a Retinal Degeneration Mouse Model

Published on: January 26, 2024

Limbal Approach-Subretinal Injection of Viral Vectors for Gene Therapy in Mice Retinal Pigment Epithelium
06:48

Limbal Approach-Subretinal Injection of Viral Vectors for Gene Therapy in Mice Retinal Pigment Epithelium

Published on: August 7, 2015

Main Results:

  • The model achieved high performance in detecting melanocytic lesions.
  • Area under the receiver operating characteristic curve (AUC-ROC) was 0.9856 for color fundus, 0.9040 for pseudocolor, and 0.9544 for CLARUS images.

Conclusions:

  • A reliable melanocytic lesion detection model was created without task-specific fine-tuning.
  • The model demonstrated high accuracy, sensitivity, and specificity in identifying lesions.
  • Combining self-supervised learning with lightweight classifiers enables robust diagnostic tools with minimal annotation.