search

uci-cbcl / DeepLung

WACV18 paper "DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification"
GNU General Public License v3.0
153 stars 54 forks source link

about LIDC-IDRI data #9

Closed anruoxi123 closed 5 years ago

anruoxi123 commented 5 years ago

Do you need to filter LIDC data before extracting data labels for LIDC data?

When I run the./data/extclsshpinfo.py file, it always reminds me that I can't find the 000006.dcm file.

Excuse me, why does the program specify 000006.dcm all these pieces?

In some cases, there are no such tablets as 000006.dcm. What should be done in this case? e3ec9332aa02803670bed08eb9eb5c0

wentaozhu commented 5 years ago

Yes. We use it to filter LIDC data. If the number of slices is less than 6, we remove the folder.

anruoxi123 commented 5 years ago

Ok, I've removed the folder with less than 6 files,

But now there's another error. Look at the picture below.

What's the reason?

d9132313732b1363641f57abec6de7a

anruoxi123 commented 5 years ago

afec094bd61851dc4e06f2e176e4af5

abhishek-s-jha commented 5 years ago

antdictscan maps LIDC parent folder with final folder which contains CT scans in that folder. eg: antdictscan{'0380_3000012-34623' : some list of values}

And code is searching for this structure: antdictscan{'0380_SeriesInstanceUID': list of values}

Modify line 135 in extclsshpinfo.py: antdictscan[pid+'_'+srs] = v --> antdictscan[pid + '_' + RefDs[0x20, 0x0e].value] = v **RefDs[0x20, 0x0e].value contain SeriesInstanceUID of CT present in folder LIDC-IDRI-0380

https://github.com/uci-cbcl/DeepLung/blob/58923bab278e5bcf4aeea860a3bef1dd9d3d1462/nodcls/data/extclsshpinfo.py#L135