Closed wardhendrix closed 4 years ago
@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?
@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.
When I run the model on specific clinical CT scans, I get the following error:
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?