xmengli / H-DenseUNet

TMI 2018. H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

a question about result

Apple-zly opened this issue · comments

hello, author.
I run the whole code, the result is not same as your result in the paper and competition. I want to know what improvements you have made.

Looking forward to your reply!
Thank you very much

What is your result?

What is your result?
Hello,
The test result is submitted in the codalab
lesion_dice_global: 0.732
lesion_dice: 0.76
lesion_dice_per_case: 0.645
liver_dice_global: 0.899
liver_dice: 0.903
liver_dice_per_case: 0.903

Looking forward to your reply!
Thank you very much

What is your result?
Hello,
The test result is submitted in the codalab
lesion_dice_global: 0.732
lesion_dice: 0.76
lesion_dice_per_case: 0.645
liver_dice_global: 0.899
liver_dice: 0.903
liver_dice_per_case: 0.903

Looking forward to your reply!
Thank you very much

When I run the step 5, the training loss is bigger than 0.05. I am still trying to get the final result. Can we discuss through email or qq,1069582001@qq.com.

Hi, we ran into the same result - has anyone figured out the source of the discrepancy? Perhaps there's a change in implementation?

What is your result?
Hello,
The test result is submitted in the codalab
lesion_dice_global: 0.732
lesion_dice: 0.76
lesion_dice_per_case: 0.645
liver_dice_global: 0.899
liver_dice: 0.903
liver_dice_per_case: 0.903

Looking forward to your reply!
Thank you very much

Hi! How do you evaluate dice?
Can you please provide some scripts?
Thanks!