Skip to main content
Fig. 4 | BMC Medical Imaging

Fig. 4

From: Use of multimodal dataset in AI for detecting glaucoma based on fundus photographs assessed with OCT: focus group study on high prevalence of myopia

Fig. 4

Regression model for predicting the OCTA acquired Cup/Disc vertical ratio and average RNFLT. The regression model can be trained to predict the average RNFLT and C/D V ratio from color fundus images (Pearson’s correlation coefficients: average RNFLT, 0.856; C/D V ratio, 0.885; R2: average RNFLT, 73.29%, Cup/Disc vertical ratio, 78.126). The test set showed similar results compared with the validation set. C/D V ratio, Cup/Disc vertical ratio; RNFLT, retinal nerve fiber layer thickness

Back to article page

BMC Medical Imaging

ISSN: 1471-2342

Contact us