search

KibromBerihu / ai4elife

This data-centric AI repository implements a robust deep learning method (LFBNet) for fully automated tumor segmentation in whole-body [18]F-FDG PET/CT images.
MIT License
30 stars 10 forks source link

question about test_env.py #7

Open marya1999 opened 7 months ago

marya1999 commented 7 months ago

HI, when I run test_env.py with my dataset the result is [2, 128, 256] could you please help me what is the reason?

KibromBerihu commented 7 months ago

Hello @marya1999 The results are the segmentations of the coronal and sagittal PET MIP images and are saved as two channel [2, 128, 256]. You could view these results on the Jupiter notebook in https://github.com/KibromBerihu/ai4elife/blob/main/documentation/tutorial/jupyter_notebook_step_by_step_illustration.ipynb. Look at the Step 7: Visualization of the PET and their segmentation results of the Jupyter notebook. Change the path to your local directory, to the predicted data.

or using other Medical Imaging software: ITKSNAP: http://www.itksnap.org/pmwiki/pmwiki.php LIFEx: https://www.lifexsoft.org/ ImageJ ; https://imagej.net/ij/ 3D Slicer: https://www.slicer.org/