The standardized evaluation methodology for 2D-3D registration methods aims to achieve objective comparison of 2D-3D registration methods. The evaluation methodology uses the calibrated geometry of a 3D rotational X-ray (3DRX) imaging system in combination with image-based 3D-3D registration for attaining a highly accurate gold standard for 2D X-ray to 3D MR/CT/3DRX registration. It provides multi-modality datasets, centers of rotation, evaluation criteria, and starting positions that allow for direct comparison of methods.
The data included in this database can be used, free of charge, for research purposes only. Copying, redistribution, and any unauthorized commercial use is prohibited. Any researcher reporting results based on this database must acknowledge this database as follows:
"The 3DRX, CT, MR and X-ray images and ground truth for the 2D-3D registration used in this work was provided by the Image Sciences Institute, University Medical Center Utrecht, The Netherlands."
We also kindly request you to cite this publication:
In addition, we appreciate to hear about any publications that use the database. Feedback on the database and this website is also welcome. The person to contact is Everine van de Kraats.
The data page describes the data in the database.
The download page gives instructions on downloading the database.
The results page lists the results in tabular format per method.
We invite other researchers to run their registration algorithms and to send us the results. We will then run our evaluation software, and report the algorithm's performance on this site. The upload page describes the format that you should use for uploading and the output that we provide.
To upload your results, contact the maintainer of the database by e-mail.