ValueError when running on clinical data

[wardhendrix]

When I run the model on specific clinical CT scans, I get the following error:

bug in 1.3.6.1.4.1.14519.5.2.1.9999.9999.128110380291387120384417865294.mhd
out=out, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/numpy/core/_methods.py", line 29, in _amin
return umr_minimum(a, axis, None, out, keepdims)
ValueError: zero-size array to reduction operation minimum which has no identity
Traceback (most recent call last):
File "apply.py", line 86, in <module>
cwd=os.path.join(THIS_DIR, "DSB2017"),
File "/usr/lib/python2.7/subprocess.py", line 541, in check_call
raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['/usr/bin/python2', 'main.py']' returned non-zero exit status 1

The full error log can be found here: error_dlc_mewto.txt I used the following command on dlc-mewto:

/home/diag/c-submit --require-cpus=8 --require-mem=30g --gpu-count=1 --require-gpu-mem=11g --priority=high --input-dir=/mnt/netcache/bodyct/experiments/nodule_cad_clinical_t8725/subset_radboudumc_ct_thorax/temp --output-dir=/mnt/netcache/bodyct/experiments/nodule_cad_clinical_t8725/subset_radboudumc_ct_thorax/nodule_cad_results/results_grt123 ward 8725 7 doduo1.umcn.nl/uoks/bodyct-kaggle-grt123:processor

Do you perhaps know what is causing the problem?

[silvandeleemput]

@Whardian it seems to be a similar issue as before, where the image: 1.3.6.1.4.1.14519.5.2.1.9999.9999.128110380291387120384417865294.mhd yields an empty lung segmentation mask on the preprocessing (segmentation, resample, and crop) and crashes when determining the crop. Does the input image look ok?

[wardhendrix]

@silvandeleemput thanks for the explanation. It is a normal input image, but the lungs on the CT scan are cropped (which occurs occasionally in clinical data). Thus, it is understandable that the model yields an empty segmentation mask (the DIAG segmentation model and Xie's lobe segmentation model also fail). I will close this issue.