Rapid grading of fundus photographs for diabetic retinopathy using crowdsourcing.

Christopher John Brady Andrea C Villanti Jennifer L Pearson Thomas R Kirchner Omesh P Gupta Chirag P Shah

Published in: Journal of medical Internet research (2014)

With minimal training, the Amazon Mechanical Turk workforce can rapidly and correctly categorize fundus photos of diabetic patients as normal or abnormal, though further refinement of the methodology is needed to improve Turker ratings of the degree of retinopathy. Images were interpreted for a total cost of US $1.10 per eye. Crowdsourcing may offer a novel and inexpensive means to reduce the skilled grader burden and increase screening for diabetic retinopathy.

Keyphrases

diabetic retinopathy
optical coherence tomography
public health
deep learning
convolutional neural network
risk factors
acute care
loop mediated isothermal amplification