search

shaoyanpan / 2D-Medical-Denoising-Diffusion-Probabilistic-Model-

This is the repository for the paper "2D Medical Image Synthesis Using Transformer-based Denoising Diffusion Probabilistic Model".
https://iopscience.iop.org/article/10.1088/1361-6560/acca5c
MIT License
35 stars 9 forks source link

Model Configuration for DICOM (dcm) images #4

Open josefapv opened 9 months ago

josefapv commented 9 months ago

Hi,

I'm currently working on adapting the code in the [TDM main.ipynb] notebook to handle 256 x 256 pixels DICOM images. I've already updated the image loader to use the 'pydicomreader,' and there are no errors throughout the code. However, the results I'm getting don't match up with the model's performance on the provided two .nii images in the repository.

Could you please assist me in identifying what changes I might need to make for the code to work effectively with 256 x 256 pixel DICOM images? I would greatly appreciate any guidance you can provide. Thank you very much in advance for your help.

shaoyanpan commented 9 months ago

Sure. Can you show me some example for your image? They are CT or MRI or something else?

josefapv commented 9 months ago

I am working with MRI images, specifically from the following link: https://www.kaggle.com/code/kmader/mri-heart-processing/input. I am extracting images from the following location: train/1/study/2ch_21. Can you help me with this?