Fig. 3: Model performance in assessing pointwise visual field (VF) values. | npj Digital Medicine

Fig. 3: Model performance in assessing pointwise visual field (VF) values.

From: Interpretable longitudinal glaucoma visual field estimation deep learning system from fundus images and clinical narratives

Fig. 3

a–e The pointwise mean absolute error (MAE) of the original color fundus photographs (CFPs), region of interest (ROI) of CFPs, ROI of CFPs with optic disc and optic cup segmentation, ROI and clinical information, ROI and follow-up interval years. f The difference between MAE of ROI with clinical information and MAE of ROI.

Back to article page