The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
Apache License 2.0
1.3k
stars
297
forks
source link
Lots of suppressed ROIs in LIDC_IDRI Preprocessing script #108
I have been trying to work on setting up this code. I ran the LIDC_IDRI lidc_data_to_nifti.py script from the other repository (it is extremely slow) and I am not on the experiments/lidc_exp/preprocesing.py script. I am running that (with I believe the paths done properly in the config file), and after tweaking some stuff in the code (there seems to be some disconnect with what the characteristics.csv file contains) it is mostly working. However, I am receive a lot of suppressed roi! print outs. I was wondering why this may be the case, considering I believe I am using the same pipeline as was already used.
I have been trying to work on setting up this code. I ran the LIDC_IDRI
lidc_data_to_nifti.py
script from the other repository (it is extremely slow) and I am not on theexperiments/lidc_exp/preprocesing.py
script. I am running that (with I believe the paths done properly in the config file), and after tweaking some stuff in the code (there seems to be some disconnect with what thecharacteristics.csv
file contains) it is mostly working. However, I am receive a lot ofsuppressed roi!
print outs. I was wondering why this may be the case, considering I believe I am using the same pipeline as was already used.