Sensitivity and specificity of computer vision classification of eyelid photographs for programmatic trachoma assessment.
Matthew C KimKazunori OkadaAlexander M RynerAbdou AmzaZerihun TadesseSun Y CotterBruce D GaynorJeremy D KeenanThomas M LietmanTravis C PorcoPublished in: PloS one (2019)
For assessing the clinical signs of trachoma, a convolutional neural net performed well above chance when tested against expert consensus. Further improvements in specificity may render this method suitable for field use.