Support AAPM low-dose CT reconstruction
Starbucksmax opened this issue · 2 comments
Is your feature request related to a problem? Please describe.
Although Low Dose CT Grand Challenge is 2016 dataset. Nowadays still many paper use it. But it seems not a clear code to guide how to reconstruct to CT image from the raw projection data which can be use to the down stream task(sparse-view & limited angle).
Describe the solution you'd like
Add the recons code to Demo 21: Loading scanner data to TIGRE.
@Starbucksmax that dataset is not real data, so it definetly doesn't fit the demo. Scanner data is data that comes raw from the machine, and the linked dataset is a machine learning one.
To reconstruct that dataset with Tigre you just need to input the operator properly. Happy to add a separate demo of it if you provide code.
Note that in any case TIGRE will have limited ML support, I am putting my efforts of CT recon for ML in an unfinished project called LION, which will support datasets.
I am closing this issue @Starbucksmax , but do let me know if you need help.