ScholarDeck

AI / informaticsTranslational vision science & technology · 2026

Artificial Intelligence-Driven Differentiation Between Uveal Melanoma and Nevus Based on Fundus Photographs: A Systematic Review and Meta-Analysis.

Theofilos Kanavos, Effrosyni Birbas, Jasmine H Francis … Theodoros P Zanos

OphthalmologyAI / informatics

Artificial intelligence models distinguish uveal melanoma from nevus on fundus photos with high accuracy

Artificial Intelligence-Driven Differentiation Between Uveal Melanoma and Nevus Based on Fundus Photographs: A Systematic Review and Meta-Analysis.

Theofilos Kanavos … Theodoros P Zanos

Translational vision science & technology · 2026

Background

Distinguishing uveal melanoma (uveal melanoma) from uveal nevus (uveal nevus) is often challenging yet crucial for appropriate management.

Purpose

This study aimed to examine the ability of artificial intelligence (artificial intelligence) models to differentiate uveal melanoma from uveal nevus based on fundus photographs.

Methods

We systematically searched four databases through July 6, 2025, for studies developing machine learning models for distinguishing uveal melanoma from uveal nevus using fundus photographs as input.

n = 6208 participants

Results

Artificial intelligence correctly told melanoma from a harmless mole with excellent overall accuracy

Overall pooled

0.915AUC

Externally validated

0.873AUC

More results

Our review included seven articles with 6208 participants in total.

Six studies used deep learning and one applied conventional machine learning.

Only two studies conducted external validation.

More results

In subgroup analysis, externally validated models retained a promising discriminative ability with a subtotal pooled AUC of 0.873.

“

Conclusion · 1 of 3

Machine learning algorithms showcase consistently high performance in differentiating uveal melanoma from uveal nevus based on fundus photographs, supporting their potential role as adjunctive tools in clinical practice.

Conclusion · 2 of 3

Their objective, reproducible assessments may improve referrals, guide clinical decision-making, and boost diagnostic confidence across health care providers.

Conclusion · 3 of 3

However, existing evidence is highly heterogeneous and constrained by small dataset sizes and limited external validation.

Post

Artificial Intelligence-Driven Differentiation Between Uveal Melanoma and Nevus Based on Fundus Photographs: A Systematic Review and Meta-Analysis.

Artificial intelligence models distinguish uveal melanoma from nevus on fundus photos with high accuracy

Related papers