Deep learning-based signal-independent assessment of macular avascular area on 6×6 mm optical coherence tomography angiogram in diabetic retinopathy: a comparison to instrument-embedded software.

Honglian XiongQi Sheng You Yukun GuoJie WangBingjie WangLiqin GaoChristina J FlaxelSteven T BaileyThomas S HwangYali Jia

Published in: The British journal of ophthalmology (2021)

Macular EAA on 6×6 mm OCTA measured with a deep learning-based algorithm is less dependent on the signal strength and shadow artefacts, and provides better diagnostic accuracy for DR severity than EVD measured with the instrument-embedded software.

Keyphrases

diabetic retinopathy
deep learning
optical coherence tomography
artificial intelligence
convolutional neural network
machine learning
patient reported outcomes
data analysis
optic nerve
editorial comment
neural network