vnet.pytorch Luna dataset preparation

Hi, thanks for the great work! I see that you use some folders normalized_brightened_CT_2_5, inferred_seg_lungs_2_5, luna16_ct_normalized. And as far as i understand this folders stored some preprocessed files from original LUNA16 dataset. I found some methods in luna16.py for preprocessing but can't find clear instructions how to use it. I wondering if you has some preprocessing script for this datasets. Could you please share this script or some instructions for usage of this preprocessing functions?

Jul 18 '17 13:07 Borov19

Hi @Borov19 did you find anything that resolves your issue?

Mar 22 '18 13:03 abhiML

Hi @abhiML Do you know how to preprocess data now?

May 13 '18 16:05 Marcovaldong

I think in luna16.py, the masks are used to indicate lung region, the targets are actually the 3D heatmap of the groundtruth nodules. However, there is no code to generate the target 3D heatmaps. It seems you need to write your own 3D heatmap generation code based on the annotation information.

Jun 14 '18 20:06 hsu-z2

@Borov19, bro, did you know how to preprocess the data now?

Mar 12 '19 01:03 RayShark

https://github.com/mattmacy/torchbiomed/blob/master/torchbiomed/datasets/luna16.py

Jul 14 '19 16:07 AlexandrosFerles

@Borov19 Hello, Do you konw how to preprocess the data now ?

Jan 03 '23 09:01 RunningPill