Segmentation of the Retinal Reflex in Brueckner Test Images Using U-Net Convolutional Network

摘要

Bruckner test is an eye exam characterized by the evaluation of brightness of red retinal reflex in pupillary area. The reflex region segmentation is important for a computational method that automatizes that examination and detects eye pathologies by the image analysis. This work presents an automatic method for retinal reflex segmentation in images of Bruckner test using the fully convolutional network U-Net. The method reaches 87.73% of Dice coefficient, 78.95% of Jaccard index, 90.63% recall and 88.03% precision.