Dennis Bontempi

Sorry to jump in randomly, @wasserth! @vikashg, to the best of my knowledge, TotalSegmentator uses a `3d_fullres` architecture from nnU-Net (no k-fold cross-validation or multiple models plus the ensembling). You...

Hey Jakob, Many thanks for the swift reply, as always! > Does this answer your questions? Otherwise let me know! It does for me - thanks!

> * it will become possible to download individual scans/subsets as needed > * download speeds should be much faster with IDC data in Google/Amazon buckets > * it will...

Hey Jakob, > I think the dataset is mainly used by researchers doing image analysis. In this case you do not really work with DICOM images, but you typically convert...

After speaking with @piiq at the Project Week I will try to take a look at SWIG (or some of the other tools he suggested) to bind the CPP DCQMI...

Hey Jakob, Thank you for your help on this - we are also using TotalSegmentator in a bunch of projects and this will help :-) Also - can I ask...

Hey Jakob, I see your point. But, besides the order of the classes (obviously different), didn't you drop some of the segmentation classes (e.g., heart chambers, vetrebrae - but I...

Dear All, > GitHub releases, unfortunately, cannot replace Zenodo, since, once the release has been published, it is possible to remove or replace those binary attachments, while in Zenodo once...

Hey Phil, > I think it's really cool that your automated pipelines pick up things like this, super useful! Thanks 🙃 > my initial reaction is that surely there must...

Hello again @pchlap @rnfinnegan :-) We found some more bizarre behaviors of Platipy when testing a freshly built container using our automated pipeline. The difference this time is that every...