Thibescobar
Thibescobar
Hello, thank you very much for the update with masked loss. This post is still relevant. I would appreciate a hint to change the masked loss to a weighted one....
Hello all, I am very interested in this feature as it is closely related to the #1471 if we consider a voxel weight of 0 where we want to ignore....
Hello Karol, Huang, I am also very interested, if I can be included in the loop it would be great. Thank you very much. Best regards. Thibault Le ven. 29...
Great update. I'll test it today.
For the moment I use these functions. It seems to work when using SimpleITK even if a bit dirty... ``` def check_if_seg_outside_vol(seg, img, verbose=False, round=None): img_origin = img.GetOrigin() seg_origin =...
Thank you very much for your quick answer. `seg` is just opened with SimpleITK as an ITK image object with `seg = sitk.ReadImage("seg/path.dcm")`, the path pointing to the DICOM SEG...
Concerned cases are 262, 291, 311, 313, 415, 423, 671, 697, 785, 796, 850, 938. I just add something else the case 733 have nodules 3 and 4 that are...
Nice ! Things end well ! If you plan and manage to fix these data on TCIA please let me know so I redownload the last data version.
Just tested locally by cloning, taking the present branch, and installing using `pip install -e . `. Works perfectly on - Linux Ubuntu 22.04 - Conda env with Python 3.12.7...
Dear Michael, thank you for your complete answer. > regarding your side question: both values first compute TP and FP across the entire dataset (nothing is computed per sample). The...