Deep learning for early diagnosis of uveal melanoma: a systematic review and meta-analysis.

AI / informaticsClinical & translational oncology : official publication of the Federation of Spanish Oncology Societies and of the National Cancer Institute of Mexico· Jul 2026

Deep learning for early diagnosis of uveal melanoma: a systematic review and meta-analysis.

Francisco Cezar Aquino de Moraes, Gustavo Tadeu Freitas Uchôa Matheus, Ísis Larissa de Brito Dichtl … Rommel Mario Rodriguez Burbano

Read paper

Ocular OncologyAI / informaticsDiagnosisQ2IF 2.8

Deep learning detected uveal melanoma with 89% pooled sensitivity across studies.

Deep learning for early diagnosis of uveal melanoma: a systematic review and meta-analysis.

Francisco Cezar Aquino de Moraes … Rommel Mario Rodriguez Burbano

Clinical & translational oncology · Jul 2026 · Q2 in General Medicine

Background

Uveal melanoma (uveal melanoma) is a rare cancer with an estimated annual incidence of 6 incidences per million people.

Purpose

The aim of this study was to evaluate the accuracy (sensitivity, specificity, and combined F1 score) of deep learning algorithms in the differential diagnosis of individuals with uveal melanoma.

Methods

We searched PubMed, Scopus, and Web of Science for studies comparing uveal melanoma patients to healthy individuals or those with ocular nevi using AI diagnostic tools.

n = 6388 patients

Results

AI correctly flagged uveal melanoma in most people who truly had it

89%

Sensitivity

84.9%

Specificity

More results

The mean age of uveal melanoma patients ranged from 58 to 63.2 years; for nevi, from 58 to 66 years.

Pooled specificity was 84.9% (95% CI 73.7-91.9%) with significant heterogeneity (I 2 = 72.3%, p = 0.006), ranging from 73.7 to 95.0%.

The largest cohort had a specificity of 76.0% (95% CI 75.1-76.9%).

“

Conclusion · 1 of 2

While fundus imaging is widely used in outpatient care, multimodal imaging remains limited to specialized clinics.

Conclusion · 2 of 2

Developing software to analyze fundus images could improve early, noninvasive uveal melanoma detection and offer a cost-effective diagnostic tool.

Deep learning for early diagnosis of uveal melanoma: a systematic review and meta-analysis.

Deep learning for early diagnosis of uveal melanoma: a systematic review and meta-analysis.

Related papers