Datasets
Standard Dataset
Domain Adaptation for 2D Medical Image Segmentation
- Citation Author(s):
- Submitted by:
- Ziyang Chen
- Last updated:
- Mon, 10/07/2024 - 22:29
- DOI:
- 10.21227/006q-3967
- License:
66 Views- Categories:
- Keywords:
Abstract
This dataset includes two 2D medical image segmentation benchmark.
1. OD/OC Segmentation in Fundus Image
This dataset conprises five sub-datasets: Drishti-GS, RIM-ONE-r3, ORIGA, REFUGE, and the validation set of REFUGE2. Each image is cropped around the optic disc area. The size of all images is 512×512. The manual pixel-wise annotation is stored as a PNG image with the same size as the corresponding fundus image with the following labels:
128: Optic Disc (Grey color)
0: Optic Cup (Black color)
255: Background (White color)
2. Polyp Segmentation in Endoscopy Image
This dataset conprises four sub-datasets: BKAI, CVC-ClinicDB, ETIS-LaribPolypDB, and Kvasir-SEG. The manual pixel-wise annotation is stored as a PNG image with the same size as the corresponding fundus image with the following labels:
255: Polyp (White color)
0: Background (Black color)
OD/OC Segmentation in Fundus Image (Fundus folder):
├─Drishti_GS
│ ├─test
│ │ ├─image
│ │ └─mask
│ └─train
│ ├─image
│ └─mask
├─ORIGA
│ ├─test
│ │ ├─image
│ │ └─mask
│ └─train
│ ├─image
│ └─mask
├─REFUGE
│ ├─test
│ │ ├─image
│ │ └─mask
│ └─train
│ ├─image
│ └─mask
├─REFUGE_Valid
│ ├─test
│ │ ├─image
│ │ └─mask
│ └─train
│ ├─image
│ └─mask
└─RIM_ONE_r3
├─test
│ ├─image
│ └─mask
└─train
├─image
└─mask
Polyp Segmentation in Endoscopy Image (Polyp folder):
├─BKAI
│ ├─test
│ │ ├─image
│ │ └─mask
│ └─train
│ ├─image
│ └─mask
├─CVC-ClinicDB
│ ├─test
│ │ ├─image
│ │ └─mask
│ └─train
│ ├─image
│ └─mask
├─ETIS-LaribPolypDB
│ ├─test
│ │ ├─image
│ │ └─mask
│ └─train
│ ├─image
│ └─mask
└─Kvasir-SEG
├─test
│ ├─image
│ └─mask
└─train
├─image
└─mask
Dataset Files
- OD/OC Segmentation in Fundus Image Fundus.zip (1.01 GB)
- Polyp Segmentation in Endoscopy Image Polyp.zip (894.13 MB)
