Angelou0516/kvasir-seg
收藏资源简介:
# Kvasir-SEG: Gastrointestinal Polyp Segmentation Dataset ## Dataset Description Kvasir-SEG is a gastrointestinal polyp segmentation dataset containing 900 polyp images with corresponding segmentation masks from the Kvasir dataset. - **Task**: Binary segmentation (polyp vs. background) - **Modality**: Gastrointestinal endoscopy - **Format**: PNG images (332x487 to 1920x1072 pixels) with binary masks - **Split**: 800 training images, 100 test images ## Dataset Structure ``` kvasir-seg/ ├── train/ │ ├── images/ # 800 training images │ └── masks/ # 800 training masks └── test/ ├── images/ # 100 test images └── masks/ # 100 test masks ``` ## Citation If you use this dataset, please cite: ```bibtex @inproceedings{jha2020kvasir, title={Kvasir-SEG: A Segmented Polyp Dataset}, author={Jha, Debesh and Smedsrud, Pia H and Riegler, Michael A and Halvorsen, P{a}l and de Lange, Thomas and Johansen, Dag and Johansen, H{a}vard D}, booktitle={International Conference on Multimedia Modeling}, pages={451--462}, year={2020}, organization={Springer} } ``` ## Usage ```python from datasets import load_dataset # Load dataset dataset = load_dataset("Angelou0516/kvasir-seg", split="train") # Access sample sample = dataset[0] image = sample['image'] mask = sample['mask'] ``` ## License Please refer to the original Kvasir dataset license and citation requirements. ## Links - Original Dataset: https://datasets.simula.no/kvasir-seg/ - Paper: https://link.springer.com/chapter/10.1007/978-3-030-37734-2_37
Kvasir-SEG is a gastrointestinal polyp segmentation dataset containing 900 polyp images with corresponding binary segmentation masks for the task of segmenting polyps from the background in gastrointestinal endoscopy images. The dataset is split into a training set with 800 images and a test set with 100 images.



