use on multi-label 3D medical image segmentation task?

Question

use on multi-label 3D medical image segmentation task?

xwjBupt opened this issue 4 years ago · comments

xwjBupt commented 4 years ago

Hi, thanks for your outstanding work!

Can your losses, for example focal loss, be used on multi-label 3D medical image segmentation task?

thank you so much! Look forward of your reply~

CoinCheung · Answer 1 · Mon Sep 21 2020 15:43:08 GMT+0800 (China Standard Time)

Hi,

Focal loss would be fine, since it is point-wise loss, and each sample is considered as a binary classification problem. As for other losses, I am afraid that they are not designed for 3d operations, but you might try to reform your problem and see if the 3d loss can be expressed in a 2d form. Good luck !!

CoinCheung · Answer 2 · Tue Feb 09 2021 14:08:45 GMT+0800 (China Standard Time)

I am closing this. You can leave messages if you need further discussions.