search

mohamed-ezz / saratan

Code for MICCAI 2016 paper : Automatic liver and lesions segmentation using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields
39 stars 18 forks source link

hello i wanna to ask where to download your train-data(like 3Dircab1) and how to run the codes #7

Closed chenxiChu closed 4 years ago

chenxiChu commented 7 years ago

i have two questions 👍

  1. where to download your train-data(like 3Dircab1) 2.Is CRF necessary or not(if necessary,how to run it)? and should i train with your Recompiled-caffenet or offical version？does this matter？ Thank you
mohamed-ezz commented 4 years ago

1.You can download 3Dircadb here https://www.ircad.fr/research/3d-ircadb-01/

  1. Since each slice was predicted independently, CRF improves the smoothness of the overall predicted 3D volume. However it requires a lot of finetuning, so it would be a good improvement to eliminate the need for it.