search

ellisdg / 3DUnetCNN

Pytorch 3D U-Net Convolution Neural Network (CNN) designed for medical image segmentation
MIT License
1.89k stars 650 forks source link

3d vessel Segmentation and Testing issue #40

Closed arielluluh closed 3 years ago

arielluluh commented 7 years ago

Hi @ellisdg I am doing 3d image segmentation for detection stenosis and plague of vessel inside coronary artery. Can I use the code that you provided? My dataset format is also in Nifti format but only one modality. Besides, will you provide the testing code for this 3d unet segmentation example?

Thank you for your time:)

ellisdg commented 6 years ago

I don't know anything about your dataset, so I can't really write code to test it. Does your dataset have a ground truth?

arielluluh commented 6 years ago

yes. I have a ground truth. Or could you code to test your BRATS dataset as an example. So that I may have a idea how to do the testing:)

ellisdg commented 6 years ago

Check out this file. It specifies the training/network configuration, collects the data, and then runs the network training. You can modify that file to run the training on your data. Is that what you are asking?

arielluluh commented 6 years ago

Actually I am asking about the testing process after we have done the training. Because I saw the dataset you provided include both training data and testing data. But the code are all for training. Do you have the code for testing?

stale[bot] commented 3 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. If you have questions, feel free to join the Slack group or email me at davidgellis2@gmail.com.