Figure 5
Representative samples of prediction and uncertainty. (A) Dice scores of three representative samples on different models. (B) Input and output of each sample. Samples (a)–(c) are correspondent in (A) and (B). (a) All models yielded accurate predictions. (b) The color fundus model lagged in accuracy compared to the FA model due to shadowing, which was, however, mitigated by synthetic FA. (c) The use of GAN reduced accuracy by obfuscating key details in the color fundus images. Meanwhile, the color fundus model had high-uncertainty area in non-NPA regions.
