Dataset Structure
The dataset is organized into modality-wise and center-wise folders, each containing images and their corresponding ground truth annotations:
PolypDB Modality Based Structure
├── BLI/
│ ├── images/
│ └── annotations/
├── FICE/
│ ├── images/
│ └── annotations/
├── LCI/
│ ├── images/
│ └── annotations/
├── NBI/
│ ├── images/
│ └── annotations/
└── WLI/
├── images/
└── annotations/
PolypDB Center-wise Structure
├── Simula/
│ ├── images/
│ ├── annotations/
│ └── bounding_boxes/
├── Karolinska/
│ ├── images/
│ ├── annotations/
│ └── bounding_boxes/
└── Vietnam/
├── images/
├── annotations/
└── bounding_boxes/
Dataset samples
Results
Qualitative results comparison of the SOTA methods
Polyp detection results
Download the dataset:
Download the dataset and place it in the corresponding directories. The dataset can be downloaded using https://osf.io/pr7ms/.
*If you use PolypDB in your research, please cite the following paper:
License
This project is licensed under the MIT License - see the LICENSE file for details.
Citations
@article{Jha2024PolypDB,
author = {Debesh Jha and et al.},
title = {PolypDB: A Curated Multi-Center Dataset for Development of AI Algorithms in Colonoscopy},
journal = {Arxiv},
year = {2024},
doi = {10.1109/TMI.2024.1234567}
}
Contact
For any inquiries, please contact Debesh Jha (debeshjha1@gmail.com, debesh.jha@usd.edu).
Contributing
We welcome contributions to PolypDB! If you have any suggestions or improvements, please feel free to submit a pull request or open an issue.
