search

CMACH508 / TransIAR

11 stars 4 forks source link

How to obtain the blood vessel segmentation masks as shown in the paper? #1

Open zhaofenqiang opened 4 months ago

zhaofenqiang commented 4 months ago

Hi,

Thanks for the great work and the released code! I am very interested in your work and have tried to reimplement the work and results. During the reimplementation, I encountered an issue and hope you could clarify it for me.

As shown in the paper, the 3D CTA images were all like blood vessel segmentation masks. However, the released CTA images 0000.nii.gz or the CTA patches extracted from the dataset_af_balanced_test.pkl are intensity images with value range [-100, 500]. Could you share the method that was used to segment the 3D CTA intensity images to 3D CTA vessel segmentation masks? Also, what visualization tools or methods you used to show the CTA images so that it can be visualized as the one you presented in the paper?

Thank you very much for your time and consideration. I am looking forward to your response.

CMACH508 commented 4 months ago

We have uploaded the visualization code to data_processing/visualize.py, which can visualize the xxx.nii.gz file.