Pierre-Louis Benveniste

Results 18 comments of Pierre-Louis Benveniste

Thanks for the feedback @joshuacwnewton ! 😃

I am having the same problem so I looked at the code and it seems that in the latest version of nnunetv2, the trainer is not built the same way....

Eventhough, I don't have a correct spinal cord segmentation (WM/GM) for this image, I solved the problem of failing inference. The problem came from the image header (even though I...

Here is the result with `sct_deepseg -i thor_3d_10.nii.gz -task seg_mice_sc` ![Image](https://github.com/user-attachments/assets/f8cc5702-fa5c-4825-8c97-06a4b476ff62) The result with `sct_deepseg -i thor_3d_10_mul.nii.gz -task seg_mice_sc` (on the multiplied by -1 image) ![Image](https://github.com/user-attachments/assets/3e7bad9a-6576-4188-a5da-1ad9818b7d86)

FInally, the model `seg_mice_gm` doesn't segment anything on both the image and the image multiplied by -1.

You're right sct_image -transpose would have been easier!

I also tried changing the resolution to try human segmentation models. (resolution was changed from [1,0.001,0.001] to [10,0.01,0.01] (in mm). The `seg_exvivo_gm-wm_t2` created empty masks on the image. However, on...

@jcohenadad Are there other investigations that you have in mind?