Tom Vercauteren
Tom Vercauteren
This would also be a helpful workaround for #26
A tooltip could be an option but will mostly be of little interest for my personal use case. What I had in mind was something that could work without requiring...
Exactly. Background color adaptation instead of background icon adaptation would of course not change the usefulness of the feature at all.
Also of relevance: https://cmiclab.cs.ucl.ac.uk/CMIC/NiftyNet/issues/240
For ease of reference, I am copy-pasting the content of https://cmiclab.cs.ucl.ac.uk/CMIC/NiftyNet/issues/240 here. Using NiftyNet as a module -- It is currently not trivial to run NiftyNet as part of a...
As discussed in #484 NiftyNet is not actively mainatained anymore. Most of the NiftyNet development efforts have now been redirected towards [MONAI](https://github.com/Project-MONAI/MONAI).
To ease cross-referencing this ticket. The proposed behaviour would be great to implement hetero-modal networks such as [HeMIS](https://arxiv.org/abs/1607.05194), [PIMMS](https://arxiv.org/abs/1807.06537) from @tomvars , [Dorent:19](http://proceedings.mlr.press/v102/dorent19a.html) from @reubendo and the like.
As discussed with @tomvars and @mjorgecardoso a similar requirement for [TCIA](https://www.cancerimagingarchive.net) and [Synapse](https://www.synapse.org) would help making better use of challenge-related datasets.
Note that this is related to #334 The implementation of the resampling should be transparent to the user and should ideally be efficiently running on the GPU when feasible.
This relates also to #280