Correction of Retinal Nerve Fiber Layer Thickness Measurement on Spectral-Domain Optical Coherence Tomographic Images Using U-net Architecture.
Ghazale RazaghiMasoud Aghsaei FardSedigheh Marjaneh HejaziPublished in: Journal of ophthalmic & vision research (2023)
2.1 μm in SD-OCT B-scans. Performance is comparable with human annotation of the RNFL layer and other algorithms according to the correlation coefficient of 0.99 and 0.88, respectively, while artifacts and errors are evident.
Keyphrases
- optical coherence tomography
- diabetic retinopathy
- endothelial cells
- machine learning
- optic nerve
- deep learning
- computed tomography
- cone beam
- high resolution
- induced pluripotent stem cells
- pluripotent stem cells
- diffusion weighted imaging
- magnetic resonance imaging
- emergency department
- peripheral nerve
- contrast enhanced
- mass spectrometry