Evaluation of an AI system for the detection of diabetic retinopathy from images captured with a handheld portable fundus camera: the MAILOR AI study.

T W RogersJ Gonzalez-BuenoR Garcia FrancoE Lopez StarD Méndez MarínJ VassalloVan Charles LansinghS TrikhaN Jaccard

Published in: Eye (London, England) (2020)

Pegasus showed good transferability for the detection of PDR from a curated desktop fundus camera dataset to real-world clinical practice with a handheld portable fundus camera. However, there was a substantial, and statistically significant, decrease in the diagnostic performance for RDR when using the handheld device.

Keyphrases

diabetic retinopathy
optical coherence tomography
convolutional neural network
high speed
clinical practice
artificial intelligence
loop mediated isothermal amplification
deep learning
real time pcr
label free
low cost
mass spectrometry
quantum dots