RIGA+ Dataset for Unsupervised Domain Adaptation in Medical Image Segmentation

Version 1
Description

Different from the previous combined multi-domain dataset for unsupervised domain adaptation (UDA) in medical image segmentation, this multi-domain fundus image dataset contains annotations made by the same group of ophthalmologists. Hence the annotator bias among different datasets can be mitigated. Therefore, this dataset can provide a relatively fair benchmark for evaluating UDA methods in fundus image segmentation. This dataset is based on the RIGA[1] dataset and MESSIDOR[2] dataset. We appr

Keywords
Conditions
License

No license available

Different from the previous combined multi-domain dataset for unsupervised domain adaptation (UDA) in medical image segmentation, this multi-domain fundus image dataset contains annotations made by the same group of ophthalmologists. Hence the annotator bias among different datasets can be mitigated. Therefore, this dataset can provide a relatively fair benchmark for evaluating UDA methods in fundus image segmentation. This dataset is based on the RIGA[1] dataset and MESSIDOR[2] dataset. We appr