Commit a3d5bb18 authored by Wenqi Li's avatar Wenqi Li

Merge branch 'revising-config' into 'master'

BRATS whole tumor segmentations

See merge request !5
parents 54b04934 6533b1ce
[config]
version = 1.0
[data]
local_id = BRATS_examples
url = https://www.dropbox.com/s/jyxnm3cqokjghje/BRATS_examples.tar.gz?dl=1
action = expand
destination = data
[weights]
local_id = anisotropic_nets_brats_challenge
url = https://www.dropbox.com/s/cnbsszxa418xc1x/anisotropic_nets_brats_challenge_weights.tar.gz?dl=1
action = expand
destination = models
[network_inference_config]
local_id = anisotropic_nets_brats_challenge
url = https://www.dropbox.com/s/fncslr3ink0jnup/anisotropic_nets_brats_challenge_code_config.tar.gz?dl=1
action = expand
destination = extensions
\ No newline at end of file
# Automatic brain tumor segmentation on BRATS with anisotropic nets
This page describes how to acquire and use the whole tumor segmentation network
as a part of the pipeline described in:
Wang et al., Automatic Brain Tumor Segmentation using
Cascaded Anisotropic Convolutional Neural Networks, MICCAI BRATS 2017
[https://arxiv.org/abs/1709.00382](https://arxiv.org/abs/1709.00382)
*[1] This implementation ranked the first (in terms of averaged Dice score 0.90499) according
to the online validation leaderboard of [BRATS challenge 2017](https://www.cbica.upenn.edu/BraTS17/lboardValidation.html).*
## Downloading model zoo files
If you cloned the NiftyNet repository,
the network weights and examples data can be downloaded with the command
```bash
python net_download.py anisotropic_nets_brats_challenge_model_zoo
```
## Generating segmentations for example data
Generate segmentations for the included example image with the command
```bash
net_segment inference -c ~/niftynet/extensions/anisotropic_nets_brats_challenge/whole_tumor_axial.ini
net_segment inference -c ~/niftynet/extensions/anisotropic_nets_brats_challenge/whole_tumor_coronal.ini
net_segment inference -c ~/niftynet/extensions/anisotropic_nets_brats_challenge/whole_tumor_sagittal.ini
```
Replace `net_segment` with `python net_segment.py` if you cloned the NiftyNet repository.
Replace `~/niftynet/` if you specified a custom download path in the `net_download` command.
\ No newline at end of file
[config]
version = 1.0
[network_inference_config]
local_id = anisotropic_nets_brats_challenge
url = https://www.dropbox.com/s/fncslr3ink0jnup/anisotropic_nets_brats_challenge_code_config.tar.gz?dl=1
action = expand
destination = extensions
\ No newline at end of file
[config]
version = 1.0
[data]
local_id = BRATS_examples
url = https://www.dropbox.com/s/jyxnm3cqokjghje/BRATS_examples.tar.gz?dl=1
action = expand
destination = data
\ No newline at end of file
[config]
version = 1.0
[weights]
local_id = anisotropic_nets_brats_challenge
url = https://www.dropbox.com/s/cnbsszxa418xc1x/anisotropic_nets_brats_challenge_weights.tar.gz?dl=1
action = expand
destination = models
\ No newline at end of file
......@@ -7,3 +7,4 @@ This page lists NiftyNet networks pre-trained for specific tasks. Information ab
| [dense_vnet_abdominal_ct_model_zoo](./dense_vnet_abdominal_ct_model_zoo.md) | Segment multiple organs from abdominal CT |
| [ultrasound_simulator_gan_model_zoo](./ultrasound_simulator_gan_model_zoo.md) | Generate simulated ultrasound images at specified poses |
| [highres3dnet_brain_parcellation_model_zoo](./highres3dnet_brain_parcellation_model_zoo.md) | Brain parcellation from T1 MR images |
| [anisotropic_nets_brats_challenge_model_zoo](./anisotropic_nets_brats_challenge_model_zoo.md) | Brain tumor segmentation with anisotropic nets |
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment