Título / Title

ARTIFICIAL INTELLIGENCE METHODS IN DIAGNOSIS OF RETINOBLASTOMA BASED ON FUNDUS IMAGING: A SYSTEMATIC REVIEW AND META-ANALYSIS

Introdução / Purpose

Artificial intelligence (AI) algorithms for the detection of retinoblastoma (RB) by fundus image analysis have been proposed as a potentially effective technique to facilitate diagnosis and potential screening programs. However, doubts remain about the accuracy of the technique, the best type of AI for this situation, and its feasibility for everyday use. Therefore, we performed a systematic review and meta-analysis to evaluate this issue.

Material e Método / Methods

Following PRISMA 2020 guidelines, a comprehensive search of MEDLINE, Embase, and IEEEX databases identified 417 studies whose titles and abstracts were screened for eligibility. We included diagnostic studies that evaluated the accuracy of AI in identifying retinoblastoma based on fundus imaging. Univariate and bivariate analysis was performed using the random effects model. The study protocol was registered in PROSPERO under CRD42024499221.

Resultados / Results

Six studies with 9902 fundus images were included, of which 5944 (60%) had confirmed RB. Only one dataset used a semi-supervised machine learning (ML) based method, all other studies used supervised ML, three using architectures requiring high computational power and two using more economical models. The pooled analysis of all models showed a sensitivity of 98.2% (95% CI: 0.947 - 0.994), a specificity of 98.5% (95% CI: 0.916 - 0.998) and an AUC of 0.986 (95% CI: 0.970 - 0.989). Subgroup analyses comparing models with high and low computational power showed no significant difference (p=0.824).

Discussão e Conclusões / Conclusion

AI methods showed a high precision in the diagnosis of RB based on fundus images with no significant difference when comparing high and low computational power models, suggesting a viability of their use. Validation and cost-effectiveness studies are needed in different income countries. Subpopulations should also be analyzed, as AI may not be cost-effective in general screening, but may be useful in populations at high risk for RB.

Palavras Chave

Retinoblastoma, Ocular Oncology, Artificial Intelligence, Machine Learning.

Area

CLINICAL RETINA

Institutions

Centro Pediátrico do Câncer - Fortaleza - Ceará - Brasil, Instituto Penido Burnier - Campinas - São Paulo - Brasil, Universidade de Fortaleza - Fortaleza - Ceará - Brasil

Authors

RIAN VILAR LIMA, MATEUS PIMENTA ARRUDA, MARIA CAROLINA ROCHA MUNIZ, HELVÉCIO NEVES FEITOSA FILHO, DAIANE MEMÓRIA RIBEIRO FERREIRA, SAMUEL MONTENEGRO PEREIRA