This repository includes Tensorflow (v1.0), PyTorch, and Chainer (v2.0) implementations of 3D UNet, semantic segmentation neural network for 3D voxel data.
NOTE: This is not official implementation. Currently only Chainer implementation works well.
The original paper is: Özgün Çiçek, Ahmed Abdulkadir, S. Lienkamp, Thomas Brox & Olaf Ronneberger. 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer, LNCS, Vol.9901, 424--432, Oct 2016
Download SLIVER07 dataset. You need to register to download it.
Please let me know if you know better 3D voxel dataset to apply 3D convolutional neural network!
MIT LICENSE.
shiba24, April 2017.