Table 2 Sensitivity, specificity, and accuracy of the model for detecting neovascular AMD and classifying RAP and PCV OCT images.

From: Distinguishing retinal angiomatous proliferation from polypoidal choroidal vasculopathy with a deep neural network based on optical coherence tomography

 

Normal vs. neovascular AMDa

Predicted normal

Predicted wet AMD

Actual normal

421

4

Actual neovascular AMDa

3

365

 

RAP vs. PCV

Predicted PCV

Predicted RAP

Actual PCV

183

23

Actual RAPb

20

169

  1. Neovascular AMD, neovascular age-related macular degeneration; RAP, retinal angiomatous proliferation; PCV, polypoidal choroidal vasculopathy; OCT, optical coherence tomography.
  2. aThe sensitivity of the classifier for detecting wet AMD eyes was 99.2%, the specificity was 99.1%, and the accuracy was 99.1%.
  3. bThe sensitivity of the classifier for detecting RAP was 89.4%, the specificity was 88.8%, and the accuracy was 89.1%.
Back to article page