Models and anatomical regions

Hi,

in the challenge organization document it says:

"Challenge participants may choose to participate either in Task 1 or 2 or both. For each task, algorithms should be provided for all the anatomical sites. The participants may decide whether to provide one or more models per task."

Does it mean that a single model should handle all anatomical sites or different dedicated models can be provided for different anatomical sites?

Thanks in advance for the clarification

Hi,

You can choose either a single model for all or different models for the anatomical sites. The choice is left up to the participants. During inference the algorithm will have a variable to discriminate on head-and-neck, thorax and abdomen.

Whether this is a sensible thing to do, up to you.

Cheers,

Matteo