Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Use abdominal datasets for training #43

Open
ccccwxc opened this issue Jun 16, 2021 · 3 comments
Open

Use abdominal datasets for training #43

ccccwxc opened this issue Jun 16, 2021 · 3 comments

Comments

@ccccwxc
Copy link

ccccwxc commented Jun 16, 2021

Hi Dr. chen
Thank you for all the work you have done before. I am trying to use the abdomen datasets to train a new model. However, the normalization value of cardiac can not work in abdomen datasets. Can you share the normalization value of the abdomen datasets?
Thank you!

@cchen-cc
Copy link
Owner

The normalization value should be calculated based on the images being used. Since we may have used different data augmentations for the abdominal dataset, the normalization value used specifically for my data may not suit for your data very well.

@jacobzhaoziyuan
Copy link

Hi Dr. Chen,

We plan to use the same abdominal dataset as you mentioned in your paper. We noticed that there are 20 MR from CHAOS, and 30 CT from another dataset. We have some questions on the dataset:

  1. Whether the 30 CT scans is from the training dataset /RawData/Training/.
  2. Could you please provide the split details of train/val/test for each modality?
  3. If possible, could you provide some preprocessing codes or processed data for reproducible results.

Thanks.

@cchen-cc
Copy link
Owner

cchen-cc commented Jan 28, 2022

Hi,

The 30 CT scans are from the training dataset /RawData/Training. The test data volumes are 1/9/30/32/33/39 for CT and 1/13/32/38/ for MR data and the other data volumes are used for training.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants