Journal
SCIENTIFIC REPORTS
Volume 12, Issue 1, Pages -Publisher
NATURE PORTFOLIO
DOI: 10.1038/s41598-022-25660-x
Keywords
-
Categories
Funding
- Ministry of Health & Welfare, Republic of Korea [HI19C0481, HC19C0276]
Ask authors/readers for more resources
This study aimed to develop a deep learning model to predict 10-2 visual field using wide-field swept-source optical coherence tomography images. By using the Inception-ResNet-V2 model and combining macular ganglion cell/inner plexiform layer thickness maps with retinal nerve fiber layer thickness maps, the model effectively predicted 10-2 visual field.
Close monitoring of central visual field (VF) defects with 10-2 VF helps prevent blindness in glaucoma. We aimed to develop a deep learning model to predict 10-2 VF from wide-field swept-source optical coherence tomography (SS-OCT) images. Macular ganglion cell/inner plexiform layer thickness maps with either wide-field en face images (en face model) or retinal nerve fiber layer thickness maps (RNFLT model) were extracted, combined, and preprocessed. Inception-ResNet-V2 was trained to predict 10-2 VF from combined images. Estimation performance was evaluated using mean absolute error (MAE) between actual and predicted threshold values, and the two models were compared with different input data. The training dataset comprised paired 10-2 VF and SS-OCT images of 3,025 eyes of 1,612 participants and the test dataset of 337 eyes of 186 participants. Global prediction errors (MAE(point-wise)) were 3.10 and 3.17 dB for the en face and RNFLT models, respectively. The en face model performed better than the RNFLT model in superonasal and inferonasal sectors (P = 0.011 and P = 0.030). Prediction errors were smaller in the inferior versus superior hemifields for both models. The deep learning model effectively predicted 10-2 VF from wide-field SS-OCT images and might help clinicians efficiently individualize the frequency of 10-2 VF in clinical practice.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available