SimCol3D - 3D Reconstruction during Colonoscopy Challenge

The SimCol3D challenge was hosted as an EndoVis sub-challenge in conjunction with MICCAI 2022 in Singapore.

Data Release

Colorectal cancer is one of the most common cancers in the world. By establishing a benchmark, the SimCol3D challenge aimed to facilitate data-driven navigation during colonoscopy. More details about the challenge and corresponding data can be found in the challenge paper on arXiv.

The challenge consisted of simulated colonoscopy data and images from real patients. This data release encompasses the synthetic portion of the challenge. The synthetic data includes three different anatomies derived from real human CT scans. Each anatomy provides several randomly generated trajectories with RGB renderings, camera intrinsics, ground truth depths, and ground truth poses. In total, this dataset includes more than 37,000 labelled images.

The real colonoscopy data used in the SimCol3D challenge consists of images extracted from the EndoMapper dataset. As the data cannot be publicly shared without user agreement, we unfortunately cannot publish the frames here. However, access to the challenge data can be requested on the EndoMapper Synapse page. Please follow their instructions, including providing a short Statement of Intended Use. Once your request is approved, you will find a dedicated folder on Synapse for the “SimCol Challenge”.

Downloading the Dataset

The complete synthetic SimCol3D dataset is available on the UCL Research Data Repository.

License

The SimCol3D Dataset is licensed under a Creative Commons Attribution 4.0 International (CC BY-NC-SA 4.0). https://creativecommons.org/licenses/by-nc-sa/4.0/

Citing the Dataset

If this dataset helped your research, please cite the following publications:

@article{rau2022bimodal,
  title={Bimodal camera pose prediction for endoscopy},
  author={Rau, Anita and Bhattarai, Binod and Agapito, Lourdes and Stoyanov, Danail},
  journal={arXiv preprint arXiv:2204.04968},
  year={2022}
}

@article{rau2023simcol3d,
  title={SimCol3D--3D Reconstruction during Colonoscopy Challenge},
  author={Rau, Anita and Bano, Sophia and Jin, Yueming and Azagra, Pablo and Morlana,  Javier and Sanderson, Edward and Matuszewski, Bogdan J and Lee, Jae Young and Lee,  Dong-Jae and Posner,  Erez and others},
  journal={arXiv preprint arXiv:2307.11261},
  year={2023}
}

Contact

If you have any questions about the challenge or data, please contact Anita Rau (a.rau.16@ucl.ac.uk).

If you are interested in our research, please visit our websites:
https://www.ucl.ac.uk/surgical-robot-vision/
https://www.ucl.ac.uk/interventional-surgical-sciences/