Published September 5, 2022 | Version 1.0
Dataset Restricted

Shifts Multiple Sclerosis Lesion Segmentation Dataset Part 1

Description

This archive contains the part 1 of Shift Benchmark on Multiple Sclerosis lesion segmentation data. This dataset is provided by the Shifts Project to enable assessment of the robustness of models to distributional shift and the quality of their uncertainty estimates. This part is the MSSEG data collected in the digital repository of the OFSEP Cohort provided in the context of the MICCAI 2016 and 2021 challenges. A full description of the benchmark is available in https://arxiv.org/pdf/2206.15407. Part 2 of the data is available here. To find out more about the Shifts Project, please visit https://shifts.ai .

Notes

This work is supported by the Hasler Foundation, Cambridge University Press and Cambridge Assessment and DeepSea.

Files

Restricted

The record is publicly accessible, but files are restricted to users with access.

Request access

If you would like to request access to these files, please fill out the form below.

You need to satisfy these conditions in order for this request to be accepted:

To use this data you must, you must:

1.     Provide your full name, institutional address and purpose of use;
2.     Accept the OFSEP DUA detailed below.
3.     Agree on your personal information to be stored in a secure location and the sharing of this personal information with OFSEP. Specifically, this data will contain your full name, institutional email address, date when you applied for access, date when you received access.

 

------------------------------- DATA USAGE AGREEMENT ---------------------------------------

Access to OFSEP MRI used for the
MSSEG-I MICCAI 2016 and MSSEG-II MICCAI 2021 challenges

I request access to the data collected in the digital repository of the OFSEP Cohort provided in the context of the MICCAI 2016 and 2021 challenges.

By accepting this agreement, I become the data controller (as defined under the European GDPR) of the data that I have access to, and I am responsible that I access these data under the GDPR obligations and the specific following terms:

1. I will comply with all relevant rules and regulations imposed by my institution and my government. This agreement never has prevalence over existing general data protection regulations that are applicable in my country.

2. I will not attempt to establish or retrieve the identity of the study participants. I will not link these data to any other database in a way that could provide identifying information. I shall not request the pseudonymisation key that would link these data to an individual's personal information, nor will I accept any additional information about individual participants under this Data Use Agreement.

3. I will not redistribute these data or share access to these data with others, unless they have independently applied and been granted access to these data, i.e., signed this Data Use Agreement. This includes individuals in my institution.

4. When sharing secondary or derivative data (e.g. group statistical maps, learnt models or templates), I will only do so if they are on a group level, and information from individual participants cannot be deduced.

5. I will reference the specific source of the accessed data when publicly presenting any results or algorithms that benefited from their use: (a) Papers, book chapters, books, posters, oral presentations, and all other presentations of results derived from the data should acknowledge the origin of the data as indicated in the Terms of use below (b) Authors of publications or presentations using the data should cite relevant publications describing the methods developed and used as described in the Terms of use below (c) Neither the [Research centre/University Department] or [University] or [Institution], nor the researchers that provide this data will be liable for any results and/or derived data.

6. I will register my [Research centre/University Department] or [University] or [Institution] in the agreement form and I accept that it is cited on the OFSEP website; I will register using my professional email address.

7. I will have the right to use this dataset for a period of 3 years starting from the date when access to the dataset will be granted. If I need to use this data for more time, I will have to ask for an extension on this website: https://shanoir.irisa.fr. Otherwise, I will have to delete them from my disk after this period of three years.

8. I will not use this data or a derivative product of it for a commercial use – if looking for a commercial use of the dataset or unsure, please contact OFSEP (projects@ofsep.org).

9. I will inform OFSEP of the publication of my article with its references via the email address publications@ofsep.org.

10. I agree to be contacted from time to time by OFSEP staff in charge of projects and publications in order to follow the progress of my work.

11. Failure to abide by these guidelines will result in termination of my privileges to access these data.

 

Terms of use

When using part or all of this data, please adhere to the following guidelines: 

1. Indicate in Methods

Data were generated by participating neurologists in the framework of Observatoire Français de la Sclérose en Plaques (OFSEP), the French MS registry (Vukusic et al. 2020). They collect clinical data prospectively in the European Database for Multiple Sclerosis (EDMUS) software (Confavreux et al. 1992). MRI of patients were provided as part of a care protocol. Nominative data are deleted from MRI before transfer and storage on the Shanoir platform (Sharing NeurOImagingResources, shanoir.org).

Vukusic S, Casey R, Rollot F, Brochet B, Pelletier J, Laplaud D-A, et al. Observatoire Français de la Sclérose en Plaques (OFSEP): A unique multimodal nationwide MS registry in France. Mult Scler. 2020;26(1):118–22.

Confavreux C, Compston DAS, Hommes OR, McDonald WI, Thompson AJ. EDMUS, a European database for multiple sclerosis. J Neurol Neurosurg Psychiatry 1992; 55: 671-676.

Andrey Malinin, Andreas Athanasopoulos, Muhamed Barakovic, Meritxell Bach Cuadra, Mark JF Gales, Cristina Granziera, Mara Graziani, Nikolay Kartashev, Konstantinos Kyriakopoulos, Po-Jui Lu, Nataliia Molchanova, Antonis Nikitakis, Vatsal Raina, Francesco La Rosa, Eli Sivena, Vasileios Tsarsitalidis, Efi Tsompopoulou, Elena Volf. Shifts 2.0: Extending The Dataset of Real Distributional Shifts, arxiv preprint https://arxiv.org/abs/2206.15407

Please cite the challenge dataset description article in any publication using a part or all of the dataset images, when they will become available (see challenge website for updates).

2. Add to Acknowledgments

This work was carried out in collaboration with The Observatoire Français de la Sclérose en Plaques (OFSEP), who is supported by a grant provided by the French State and handled by the“Agence Nationale de la Recherche,” within the framework of the “Investments for the Future” program, under the reference ANR-10-COHO-002, by the Eugène Devic EDMUS Foundation against multiple sclerosis and by the ARSEP Foundation.

------------------------------- DATA USAGE AGREEMENT ---------------------------------------

 

Please, clearly state your full name, institution, institutional email address and purpose of use to accept the DUA. 

You are currently not logged in. Do you have an account? Log in here

Additional details

Funding

AI4Media – A European Excellence Centre for Media, Society and Democracy 951911
European Commission

References

  • Malinin, Andrey et al. (2022).  Shifts 2.0: Extending The Dataset of Real Distributional Shifts, arXiv:2206.15407