Jakob Wasserthal

I agree that making those file formats work is frustrating and takes quite a bit of time. However, in my experience the vast majority of people in the medical image...

Thank you. I will have a look at it. However, for the near future I will stay with nifti. Maybe the easiest solution for you is to create a branch...

Unfortunately the "invalid" nifti files occur quite often. When I get a batch of data from our PACS and convert them to nifti, then it typically contains a least one...

It is not yet part of a release. You could install the master branch without git the following way: ``` pip install https://github.com/wasserth/TotalSegmentator/archive/master.zip ```

Thanks for pointing this out. This probably is the reason. Unfortunately, I can not really make our techs change their approach. I guess this issue occurs in a lot of...

Hi, the input needs to be a DICOM image (compressed inside of a zip) or a NIFTI image. JPEG or PNG does not work. You can find a example CT...

Great to hear that our tool is working well for you. We are currently working on adding airways and vessel segmentation for the lung as well as adding pneumothorax segmentation....

Thanks for the explanation. We have no plans so far to add those segments. It seems that it would be quite a bit of effort to manually draw those segments...

In the beginning I would roughly need 20 labeled datasets. Then I would train a model and predict the 1200 subjects from the training dataset, then those predictions would need...

Sound good. Ideally you would pick 20 subjects from the TotalSegmentator dataset: https://zenodo.org/record/6802614 I does not really matter which subjects as long as they are from the training set (which...