João Barbosa-Breda

Jun 13, 2023 | nature.com | Andrew White |Patrick De Boever |Ruben Hemelings |Matthew B. Blaschko |João Barbosa-Breda

AbstractA plethora of classification models for the detection of glaucoma from fundus images have been proposed in recent years. Often trained with data from a single glaucoma clinic, they report impressive performance on internal test sets, but tend to struggle in generalizing to external sets. This performance drop can be attributed to data shifts in glaucoma prevalence, fundus camera, and the definition of glaucoma ground truth.