Cataract Dataset for Image Segmentation
CaDIS: a Cataract Dataset for Image Segmentation is a dataset for semantic segmentation created by Digital Surgery Ltd. on top of the CATARACTS dataset. CaDIS consists of 4670 images sampled from the 25 videos on CATARACTS' training set. Each pixel in each image is labeled with its respective instrument or anatomical class from a set of 36 identified classes. More details about the dataset could be found in the paper (https://arxiv.org/pdf/1906.11586.pdf).
Variants: CaDIS
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| 2D Semantic Segmentation task 3 (25 classes) | OCR-R50-Repeat Factor-Lovasz | Effective semantic segmentation in Cataract … | 2021-08-13 |
| 2D Semantic Segmentation task 3 (25 classes) | DeepLabv3+-R50-Repeat Factor-Lovasz | Effective semantic segmentation in Cataract … | 2021-08-13 |
| 2D Semantic Segmentation task 3 (25 classes) | UPN-R50-Repeat Factor-Lovasz | Effective semantic segmentation in Cataract … | 2021-08-13 |
| 2D Semantic Segmentation task 3 (25 classes) | UPN | CaDIS: Cataract Dataset for Image … | 2019-06-27 |
| 2D Semantic Segmentation task 3 (25 classes) | HRNetv2 | CaDIS: Cataract Dataset for Image … | 2019-06-27 |
| 2D Semantic Segmentation task 3 (25 classes) | DeepLabv3+ | CaDIS: Cataract Dataset for Image … | 2019-06-27 |
Recent papers with results on this dataset: