Automated Detection of Retinopathy in Prematurity Using VGG19- Based Deep Learning on Fundus Images

Key Points

• The central aim is to explore the effectiveness of VGG19-based deep learning for detecting retinopathy in premature infants using fundus images.
• Utilized VGG19 deep learning architecture for image analysis.
• Analyzed fundus images of premature infants to identify signs of retinopathy.
• Employed automated detection techniques to enhance accuracy and speed of diagnosis.
• Successfully automated detection helps in early identification of retinopathy.
• Deep learning model demonstrated high accuracy in interpreting fundus images.
• Results support the feasibility of using AI for routine screening in clinical settings.