Jaemin Son

TL;DR: It is observed that two of the top-ranked teams outperformed two human experts in the glaucoma classification task, and the segmentation results were in general consistent with the ground truth annotations, with complementary outcomes that can be further exploited by ensembling the results.

TL;DR: The set-up and results of this challenge that is primarily based on Indian Diabetic Retinopathy Image Dataset (IDRiD), which received a positive response from the scientific community, have the potential to enable new developments in retinal image analysis and image-based DR screening in particular.

TL;DR: This paper presents a method that generates the precise map of retinal vessels using generative adversarial training and achieves dice coefficient of 0.829 on DRIVE dataset and0.834 on STARE dataset which is the state-of-the-art performance on both datasets.

TL;DR: The deep learning algorithms with region guidance showed reliable performance for detection of multiple findings in macula-centered retinal fundus images, especially in the detection of hemorrhage, hard exudate, membrane, macular hole, myelinated nerve fiber, and glaucomatous disc change.

TL;DR: This paper experimentally measures the performance gain for Generative Adversarial Networks (GAN) framework when applied to the segmentation tasks and shows that GAN achieves statistically significant improvement in area under the receiver operating characteristic (AU-ROC) and areaUnder the precision and recall curve ( AU-PR) on two public datasets by segmenting fine vessels.