VoxHRNet - Whole Brain Segmentation with Full Volume Neural Network

Last update: Nov 24, 2022

Related tags

Overview

VoxHRNet

This is the official implementation of the following paper:

Whole Brain Segmentation with Full Volume Neural Network

Yeshu Li, Jonathan Cui, Yilun Sheng, Xiao Liang, Jingdong Wang, Eric I-Chao Chang, Yan Xu

Computerized Medical Imaging and Graphics

[arXiv]

Network

Installation

The following environments/libraries are required:

Python 3
yacs
SimpleITK
apex
pytorch
nibabel
numpy
scikit-image
scipy

Quick Start

Data Preparation

Download the LPBA40 and Hammers n30r95 datasets.

After renaming, your directory tree should look like:

$ROOT
├── data
│   └── LPBA40_N4_RN
│       ├── aseg_TEST001.nii.gz
│       ├── ...
│       ├── aseg_TEST010.nii.gz
│       ├── aseg_TRAIN001.nii.gz
│       ├── ...
│       ├── aseg_TRAIN027.nii.gz
│       ├── aseg_VALIDATE001.nii.gz
│       ├── ...
│       ├── aseg_VALIDATE003.nii.gz
│       ├── orig_TEST001.nii.gz
│       ├── ...
│       ├── orig_TEST010.nii.gz
│       ├── orig_TRAIN001.nii.gz
│       ├── ...
│       ├── orig_TRAIN027.nii.gz
│       ├── orig_VALIDATE001.nii.gz
│       ├── ...
│       └── orig_VALIDATE003.nii.gz
└── VoxHRNet
    ├── voxhrnet.py
    ├── ...
    └── train.py

Create a YACS configuration file and make changes for specific training/test settings accordingly. We use config_lpba.yaml as an example as follows.

Train

Run

python3 train.py --cfg config_lpba.yaml

Test

Run

python3 test.py --cfg config_lpba.yaml

Pretrained Models

For the LPBA40 dataset, we number the subjects from 1-40 alphabetically and split them into 4 folds sequentially. The k-th fold is selected as the test set in the k-th split.

For the Hammers n30r95 dataset, the first 20 subjects and last 10 subjects are chosen as the training and test set respectively.

Their pretrained models can be found in the release page of this repository.

Citation

Please cite our work if you find it useful in your research:

@article{LI2021101991,
title = {Whole brain segmentation with full volume neural network},
journal = {Computerized Medical Imaging and Graphics},
volume = {93},
pages = {101991},
year = {2021},
issn = {0895-6111},
doi = {https://doi.org/10.1016/j.compmedimag.2021.101991},
url = {https://www.sciencedirect.com/science/article/pii/S0895611121001403},
author = {Yeshu Li and Jonathan Cui and Yilun Sheng and Xiao Liang and Jingdong Wang and Eric I.-Chao Chang and Yan Xu},
keywords = {Brain, Segmentation, Neural networks, Deep learning},
abstract = {Whole brain segmentation is an important neuroimaging task that segments the whole brain volume into anatomically labeled regions-of-interest. Convolutional neural networks have demonstrated good performance in this task. Existing solutions, usually segment the brain image by classifying the voxels, or labeling the slices or the sub-volumes separately. Their representation learning is based on parts of the whole volume whereas their labeling result is produced by aggregation of partial segmentation. Learning and inference with incomplete information could lead to sub-optimal final segmentation result. To address these issues, we propose to adopt a full volume framework, which feeds the full volume brain image into the segmentation network and directly outputs the segmentation result for the whole brain volume. The framework makes use of complete information in each volume and can be implemented easily. An effective instance in this framework is given subsequently. We adopt the 3D high-resolution network (HRNet) for learning spatially fine-grained representations and the mixed precision training scheme for memory-efficient training. Extensive experiment results on a publicly available 3D MRI brain dataset show that our proposed model advances the state-of-the-art methods in terms of segmentation performance.}
}

Acknowledgement

A large part of the code is borrowed from HRNet.

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.

You might also like...

BraTs-VNet - BraTS(Brain Tumour Segmentation) using V-Net

Comments

How to get the LPBA40_N4_RN dataset for the example

Thanks for your great work. I'm trying to run the example but stuck by the dataset. It seems there are multiple LPBA40 datasets on the give site LPBA40, and the data file format are not nii as in the example. Is there a downloadable LPBA40_N4_RN dataset or could you give some details on how to generate the dataset in the example?

opened by mgcyung 2
ACTION REQUIRED: Microsoft needs this private repository to complete compliance info
There are open compliance tasks that need to be reviewed for your VoxHRNet repo.

Action required: 4 compliance tasks

To bring this repository to the standard required for 2021, we require administrators of this and all Microsoft GitHub repositories to complete a small set of tasks within the next 60 days. This is critical work to ensure the compliance and security of your microsoft GitHub organization.

Please take a few minutes to complete the tasks at: https://repos.opensource.microsoft.com/orgs/microsoft/repos/VoxHRNet/compliance

The GitHub AE (GitHub inside Microsoft) migration survey has not been completed for this private repository

No Service Tree mapping has been set for this repo. If this team does not use Service Tree, they can also opt-out of providing Service Tree data in the Compliance tab.

No repository maintainers are set. The Open Source Maintainers are the decision-makers and actionable owners of the repository, irrespective of administrator permission grants on GitHub.

Classification of the repository as production/non-production is missing in the Compliance tab.

You can close this work item once you have completed the compliance tasks, or it will automatically close within a day of taking action.

If you no longer need this repository, it might be quickest to delete the repo, too.

GitHub inside Microsoft program information

More information about GitHub inside Microsoft and the new GitHub AE product can be found at https://aka.ms/gim.

FYI: current admins at Microsoft include @scarlett2018, @EricChangMSR, @simon1727
opened by microsoft-github-operations[bot] 0

VoxHRNet - Whole Brain Segmentation with Full Volume Neural Network

Related tags

Overview

VoxHRNet

Network

Installation

Quick Start

Data Preparation

Train

Test

Pretrained Models

Citation

Acknowledgement

Contributing

You might also like...

BraTs-VNet - BraTS(Brain Tumour Segmentation) using V-Net

Recovering Brain Structure Network Using Functional Connectivity

PyZebrascope - an open-source Python platform for brain-wide neural activity imaging in behaving zebrafish

An attempt at the implementation of GLOM, Geoffrey Hinton's paper for emergent part-whole hierarchies from data

HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation

minimizer-space de Bruijn graphs (mdBG) for whole genome assembly

Official implementation of the paper Visual Parser: Representing Part-whole Hierarchies with Transformers

CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching（CVPR2021）

Using this you can control your PC/Laptop volume by Hand Gestures (pinch-in, pinch-out) created with Python.

Comments

How to get the LPBA40_N4_RN dataset for the example

ACTION REQUIRED: Microsoft needs this private repository to complete compliance info

Action required: 4 compliance tasks

GitHub inside Microsoft program information

Releases(dataset)

dataset(Jul 23, 2022)

pretrained(Oct 29, 2021)

Owner

Microsoft

YOLTv5 rapidly detects objects in arbitrarily large aerial or satellite images that far exceed the ~600×600 pixel size typically ingested by deep learning object detection frameworks

Efficient Training of Audio Transformers with Patchout

Experimental code for paper: Generative Adversarial Networks as Variational Training of Energy Based Models

Cartoon-StyleGan2 🙃 : Fine-tuning StyleGAN2 for Cartoon Face Generation

Wenet STT Python

A Closer Look at Invalid Action Masking in Policy Gradient Algorithms

JDet is Object Detection Framework based on Jittor.

Torch-ngp - A pytorch implementation of the hash encoder proposed in instant-ngp

AnimationKit: AI Upscaling & Interpolation using Real-ESRGAN+RIFE

TensorFlow-LiveLessons - "Deep Learning with TensorFlow" LiveLessons

Convert dog pictures into various painting styles. Try LimnPet

Rotary Transformer

We propose a new method for effective shadow removal by regarding it as an exposure fusion problem.

The code for SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network.

This repo contains the official code of our work SAM-SLR which won the CVPR 2021 Challenge on Large Scale Signer Independent Isolated Sign Language Recognition.

Code and dataset for ACL2018 paper "Exploiting Document Knowledge for Aspect-level Sentiment Classification"

Tensorflow Implementation of ECCV'18 paper: Multimodal Human Motion Synthesis

Medical Insurance Cost Prediction using Machine earning

Heterogeneous Deep Graph Infomax

So-ViT: Mind Visual Tokens for Vision Transformer