Rules - RETOUCH - Grand Challenge

The following ''Terms of Participation'' apply to those who register a team and download the data.

Registration¶

For the registration to be approved the agreement of data confidentiality needs to be completed.
Anonymous registration is not allowed. All information entered when registering a team, including the name of the contact person, the affiliation and the e-mail address must be complete and correct.

OCT datasets and associated reference standard provided by the organizers may not be given or distributed under any circumstances to persons other than the people who are part of the registered team.
The data shared in this challenge is strictly limited to research purpose ONLY, any commercial use is prohibited.
The data may only be used for the evaluation of fluid segmentation methods and participation in RETOUCH challenge and CANNOT be used for any other purposes. The data may not be used to train or develop other algorithms, including but not limited to algorithms used in commercial products.

To participate in the challenge and have your results visible on this website it is mandatory to submit a paper (max. 8 pages, PDF in Springer LNCS format) to the organizers explaining your algorithm. The organizers of the challenge will check the method description before publishing the results on the website.
Evaluation of results uploaded to this website will be made publicly available on this site, and by submitting results, you grant us permission to publish our evaluation. Participating teams maintain full ownership and rights to their method. We do not claim any ownership or rights to the algorithms.
A maximum of 3 submissions is allowed for each team. Multiple submissions are only allowed when the utilised algorithm differs significantly from the algorithm used in the first submission (e.g. new submission when only the hyper-parameters of the algorithm are changed is not allowed). The second and third submissions must be accompanied by a new abstract or a short description of the difference of the method from the previous submissions.
When publishing the obtained results in scientific publications, you should make an appropriate citation in accordance with academic custom. The citation should refer to the following journal publication that describes the results of the challenge and the workshop: DOI 10.1109/TMI.2019.2901398.

To assure fair competition, the use of external data for augmenting the annotated training set is not permitted. However, using pre-processing methods trained on external datasets is allowed.
Making extra annotations on the training data set is only allowed if the annotations are subsequently submitted to the organizers along with the submission of the results so that these annotations can be made available to other participants.