Prediction of visual field from swept-source optical coherence tomography using deep learning algorithms.

Keunheung ParkJinmi KimSangyoon KimJonghoon Shin

Published in: Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie (2020)

Inception-ResNet-v2 achieved the best performance, and the global prediction error (RMSE) was 4.44 dB. As glaucoma progressed, the prediction error became larger. This method may help clinicians determine VF, particularly for patients who are unable to undergo a physical VF test.

Keyphrases

optical coherence tomography
deep learning
end stage renal disease
ejection fraction
chronic kidney disease
physical activity
prognostic factors
palliative care
optic nerve
convolutional neural network