The Endomapper dataset is the first collection of complete endoscopy sequences acquired during regular medical practice, including slow and careful screening explorations, making secondary use of medical data. Its original purpose is to facilitate the development and evaluation of VSLAM (Visual Simultaneous Localization and Mapping) methods in real endoscopy data. The first release of the dataset is composed of 50 sequences with a total of more than 13 hours of video. It is also the first endoscopic dataset that includes both the computed geometric and photometric endoscope calibration as well as the original calibration videos. Meta-data and annotations associated to the dataset varies from anatomical landmark and description of the procedure labeling, tools segmentation masks, COLMAP 3D reconstructions, simulated sequences with groundtruth and meta-data related to special cases, such as sequences from the same patient. This information will improve the research in endoscopic VSLAM, as well as other research lines, and create new research lines.
Attribution-NonCommercial-ShareAlike 4.0 (CC BY-NC-SA 4.0)https://creativecommons.org/licenses/by-nc-sa/4.0/
License information was derived automatically
Colorectal cancer is one of the most common cancers in the world. By establishing a benchmark, SimCol3D 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. The real data is available on the EndoMapper Synapse page.
The synthetic colonoscopy data is made available in this repository.
Not seeing a result you expected?
Learn how you can add new datasets to our index.
The Endomapper dataset is the first collection of complete endoscopy sequences acquired during regular medical practice, including slow and careful screening explorations, making secondary use of medical data. Its original purpose is to facilitate the development and evaluation of VSLAM (Visual Simultaneous Localization and Mapping) methods in real endoscopy data. The first release of the dataset is composed of 50 sequences with a total of more than 13 hours of video. It is also the first endoscopic dataset that includes both the computed geometric and photometric endoscope calibration as well as the original calibration videos. Meta-data and annotations associated to the dataset varies from anatomical landmark and description of the procedure labeling, tools segmentation masks, COLMAP 3D reconstructions, simulated sequences with groundtruth and meta-data related to special cases, such as sequences from the same patient. This information will improve the research in endoscopic VSLAM, as well as other research lines, and create new research lines.