Frequently Asked Questions

Can I use the data for other project than the cardiac segmentation?

No. The Data Use Agreement document explicitely specifies that the Data and its derived results can only be used for this Consensus Segmentation project. However, if you want to extend the usage of the Data for other research projects, then you can make a separate request (click here to fill in the request). We will forward it to the CAP Steering Committee for a review.

Why are the current consensus images not available for download?

You can get the current consensus images only if you do not use them to train your segmentation algorithm. In this way, we can maintain the reliability and the integrity of the current consensus images in this project to be used for testing, validating and benchmarking of new segmentation algorithms. You can request to us to get the current consensus images, and you must agree to a specific Data Use Agreement.

Can I download the consensus images if I contribute as a rater?

As a contributing rater, you do have a right to acess the consensus images upon which your segmentation results are validated with. You can use the consensus images to cross-check the correctness of the validation results that we perform on your segmentation images. However, these consensus images are not available online. You must specifically request to us to get them. Please note that those are the images that were used to validate your results. At the time of the validation, they were the current consensus images. However, they might not be the most up-to-date consensus images, because we always update the consensus based on coming new contributions.

Can I publish a paper based on the validation results?

Yes you can. In your paper you must use the following citations:

  • To describe the MRI data set:
    A. H. Kadish, D. Bello, J. P. Finn, R. O. Bonow, A. Schaechter, H. Subacius, C. Albert, J. P. Daubert, C. G. Fonseca, and J. J. Goldberger. Rationale and Design for the Defibrillators to Reduce Risk by Magnetic Resonance Imaging Evaluation (DETERMINE) Trial. J Cardiovasc Electrophysiol, 20(9):982–7, 2009.
  • Regarding the availability of the dataset:
    A. Suinesiaputra, B. R. Cowan, A. O. Al-Agamy, M. A. Elattar, N. Ayache, A. S. Fahmy, A. M. Khalifa, P. Medrano-Gracia, M.-P. Jolly, A. H. Kadish, D. C. Lee, J. Margeta, S. K. Warfield, and A. A. Young. A collaborative resource to build consensus for automated left ventricular segmentation of cardiac MR images. Medical Image Analysis, 18(1):50 – 62, 2014.

Can I validate my segmentation results without being a rater?

Yes, you can submit to us your segmentation images and we will send you back the validation results. We will not put your segmentation images as a contributing rater. However, you cannot request to download the consensus images that are used to validate your results. If you want to publish your results, then please use the citations as described above.

Can I publish a paper using only the Test Dataset and its segmentation images as the reference?

Yes, but with certain conditions. If you have not yet submitted your segmentation results on the Validation Dataset, then you are still obligated to do so based on the Terms and Agreement document that you have had agreed when joining this project. Apart from the proper citations, as described above, you must not write the segmentation images that come with the Test Dataset as the ground truth. Rather, you must specify them as semi-automated segmentation images, and refer to the following paper:

B. Li, Y. Liu, C. J. Occleshaw, B. R. Cowan, and A. A. Young. In-line automated tracking for ventricular function with magnetic resonance imaging. JACC Cardiovasc Imaging, 3(8):860–6, 2010.

Can I only download the Test Dataset and its segmentation images?

No, in the context of this consensus segmentation project. However, if you want to download any MRI dataset and its derived analysis (contours, models and/or segmentation images), then you can simply submit a request to us with this form. Specific conditions apply depending on which data you want to access.