Frequently asked questions¶

I have requested to join the challenge, but my request has not been accepted yet. Why?
You will get access to the full website after you have sent the signed data use agreement to knoap2020@gmail.com. If you have sent the data use agreement and still not accepted, please contact us via email (knoap2020@gmail.com).

Will the models based on radiographs and MRIs be evaluated separately or will only one best model be selected regardless of its input type?
To be able to appoint a single overall winner, we chose to consider all submissions regardless of their input. We will also report the results/rankings for each category (radiography, MRI, radiography+MRI) independently.

I have downloaded the data, how do I get started?
You should decide which method you are going to use. The prediction method is not pre-specified and can be based for example on deep learning, hand-crafted image features, or semi-quantitative image features. If you need tissue segmentations, you can for example check the following segmentation methods that were submitted to the IWOAI2019 segmentation challenge:
- DOSMA: source code, publication
- MultiPlanarUNet: source code, publication