search

paulhager / MMCL-Tabular-Imaging

82 stars 13 forks source link

How to do image preprocessing #8

Closed Ivygugu closed 11 months ago

Ivygugu commented 11 months ago

Hi,

I'm trying to use your network structure for pulmonary embolism detection based on CT images and electronic medical records, but I have some problems in the reproduction process:

  1. Since I haven't got the UKBB dataset yet, I don't know the structure of the dataset, can you introduce how you deal with medical images and electronic medical records? What should their directory look like in code?
  2. If the inputs are CT images and electronic medical records, how can I get the respective .py files?

Thanks！

paulhager commented 11 months ago

If you are loading images with a paths file (i.e. liveloading=False), it doesn't matter where the images are, you just need to have the correct paths to the images in a .pt file and set the flag. Take a look at the dataset file.

If you are loading all images into RAM at once, create a list of tensors and then save them with torch.save. Then provide the path to the newly saved tensor file (.pt).

For the tabular data, you just provide it as a CSV. The CSV cannot have missing values and should not have a header.

github-actions[bot] commented 11 months ago

This issue is stale because it has been open for 14 days with no activity.