Table 3 The performance of the deep learning models trained using concatenated OCT image sets for CSC prognosis.

From: Predicting persistent central serous chorioretinopathy using multiple optical coherence tomographic images by deep learning

 

Accuracy

Precision

Recall

Specificity

F1 score

Kappa mean

Kappa SE

B-scan + retinal thickness

0.9520

0.9487

0.9024

0.9762

0.9250

0.7230

0.0670

B-scan + EZ

0.8800

0.8421

0.7805

0.9286

0.8101

0.8900

0.0440

EZ + retinal thickness

0.9280

0.881

0.9024

0.9405

0.8916

0.8380

0.0520

  1. OCT: optical coherence tomography; CSC: central serous chorioretinopathy; SE: standard error; EZ: ellipsoid zone.
  2. F1 score = 2 × {(precision × recall)/(precision + recall)}.
Back to article page