Revisão sistemática de banco de dados de retinografias em pacientes com DMRI: dispositivos de abordagens computacionais

Abstract

Age-Related Macular Degeneration (AMD) is one of the leading causes of visual impairment in the elderly, affecting the macula and compromising essential visual functions such as reading, facial recognition, and color perception. Early diagnosis is crucial to slow the progression of the disease, with retinography and Optical Coherence Tomography (OCT) being the main diagnostic tools used in clinical practice. In recent years, the application of artificial intelligence techniques to retinal image analysis has shown promising results, provided that it is supported by high-quality databases. This study aims to conduct a systematic review of the main retinal image datasets related to AMD, investigating their characteristics, the imaging devices used for image acquisition, and the computational approaches applied in research. The methodology includes searching academic databases such as PubMed, Scopus, and Web of Science, with well-defined inclusion and exclusion criteria. The expected outcome is to contribute to the consolidation of relevant information about the available datasets, highlighting opportunities and limitations in their use for computational purposes. This research seeks to support future studies in the development of more accurate and accessible technological solutions for automated AMD diagnosis.