Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

做肝脏分割一阶段粗分割得到的dice只有65%算正常吗?好像太低了吧 #33

Open
Alagirl opened this issue Sep 25, 2019 · 7 comments

Comments

@Alagirl
Copy link

Alagirl commented Sep 25, 2019

做肝脏分割一阶段粗分割得到的dice只有65%算正常吗?好像太低了吧,用Unet3d也可以很快的训练达到同样的精度,想问一下你们的实验也是这样吗,还是我中间有错误

@Alagirl
Copy link
Author

Alagirl commented Sep 25, 2019

求解答

@cshwhale
Copy link
Collaborator

请问你decoder部分用的是什么?demo里提供的decoder比较简单,不同任务建议用pretrain+合适的decoder,我当时做肝脏参考了ASPP。

@Alagirl
Copy link
Author

Alagirl commented Sep 26, 2019

我是直接转置卷积上采样,因为我看论文里第一阶段就是直接上采样吧,得到ROI再做ASPP的

@luofeel
Copy link

luofeel commented Oct 9, 2019

我这里单做肺部裁剪 得到的效果也不是特别理想 不清楚是不是中间产生什么错误还是必须添加aspp

@joechenrh
Copy link

请问你decoder部分用的是什么?demo里提供的decoder比较简单,不同任务建议用pretrain+合适的decoder,我当时做肝脏参考了ASPP。

请问是在ASPP后接上采样吗?

@urmagicsmine
Copy link

I have the same problem. I trained the LIDC-IDRI segmentation dataset with the MedicalNet pretrained model(resnet 18), and got a dice score lower than traning from scratch(54.8 vs 74.0). Any suggestions?

@MDAooo
Copy link

MDAooo commented Dec 11, 2020

Hi @urmagicsmine @joechenrh @luofeel @Alagirl @cshwhale

For liver/liver tumor segmentation, probably you can try this post: https://github.com/MrGiovanni/ModelsGenesis/tree/master/competition

They also used a pre-trained 3D model and seemed to outperform training nnU-Net from scratch in liver/liver tumor.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

6 participants