Post-treatment prediction of optical coherence tomography using a conditional generative adversarial network in age-related macular degeneration.

Researchers

Journal

Modalities

Models

Abstract

To develop a deep learning model to generate post-treatment optical coherence tomography (OCT) images of neovascular age-related macular degeneration (nAMD).
Two hundred ninety-eight patients with nAMD were included. The conditional generative adversarial network (cGAN) was trained using 15183 augmented paired OCT B-scan images obtained from 723 scans of 241 patients at baseline and 1 month after 3 loading doses of an anti-vascular endothelial growth factor (VEGF) treatment. The network was also trained using baseline fluorescein angiography (FA) or indocyanine green angiography (ICGA) images together with baseline OCT images. A test set of 150 images of 50 eyes was used to evaluate its ability to predict the presence of intraretinal fluid (IRF), subretinal fluid (SRF), pigment epithelial detachment (PED) and subretinal hyperreflective material (SHRM). Post-treatment OCT images were compared with images generated from baseline OCT with or without FA and ICGA images.
The predicted images inferred from baseline OCT images achieved an acceptable accuracy, specificity and negative predictive value for 4 lesions (range, %: 77.0-91.9, 94.1-95.1, and 54.7-96.5, respectively). The addition of both FA and ICGA images improved the accuracy, specificity and negative predictive value (range, %: 80.7-96.3, 97.3-99.0, and 59.0-98.3, respectively).
A cGAN is able to generate post-treatment OCT images from baseline OCT, FA and ICGA images.