NiftyNet is a TensorFlow-based open-source convolutional neural networks (CNN) platform for research in medical image analysis and image-guided therapy. NiftyNet's modular structure is designed for sharing networks and pre-trained models. Using this modular structure you can:
- Get started with established pre-trained networks using built-in tools
- Adapt existing networks to your imaging data
- Quickly build new solutions to your own image analysis problems
NiftyNet is a consortium of research groups (WEISS -- Wellcome EPSRC Centre for Interventional and Surgical Sciences, CMIC -- Centre for Medical Image Computing, HIG -- High-dimensional Imaging Group), where WEISS acts as the consortium lead.
NiftyNet currently supports medical image segmentation and generative adversarial networks. NiftyNet is not intended for clinical use. Other features of NiftyNet include:
- Easy-to-customise interfaces of network components
- Sharing networks and pretrained models
- Support for 2-D, 2.5-D, 3-D, 4-D inputs*
- Efficient discriminative training with multiple-GPU support
- Implementation of recent networks (HighRes3DNet, 3D U-net, V-net, DeepMedic)
- Comprehensive evaluation metrics for medical image segmentation
*2.5-D: volumetric images processed as a stack of 2D slices; 4-D: co-registered multi-modal 3D volumes
- Please install the appropriate TensorFlow package*:
pip install tensorflow-gpu==1.2
for TensorFlow with GPU supportpip install tensorflow==1.2
for CPU-only TensorFlow
pip install niftynet
*All other NiftyNet dependencies are installed automatically as part of the pip installation process.
Please see the NiftyNet demos.
Please see the list of network (re-)implementations in NiftyNet.
The API reference is available on Read the Docs.
Feature requests and bug reports are collected on Issues.
Contributors are encouraged to take a look at CONTRIBUTING.md.
If you use NiftyNet in your work, please cite Li et. al. 2017:
- Li W., Wang G., Fidon L., Ourselin S., Cardoso M.J., Vercauteren T. (2017) On the Compactness, Efficiency, and Representation of 3D Convolutional Networks: Brain Parcellation as a Pretext Task. In: Niethammer M. et al. (eds) Information Processing in Medical Imaging. IPMI 2017. Lecture Notes in Computer Science, vol 10265. Springer, Cham. DOI: 10.1007/978-3-319-59050-9_28
BibTeX entry:
@InProceedings{niftynet17,
author = {Li, Wenqi and Wang, Guotai and Fidon, Lucas and Ourselin, Sebastien and Cardoso, M. Jorge and Vercauteren, Tom},
title = {On the Compactness, Efficiency, and Representation of 3D Convolutional Networks: Brain Parcellation as a Pretext Task},
booktitle = {International Conference on Information Processing in Medical Imaging (IPMI)},
year = {2017}
}
Copyright 2017 University College London and the NiftyNet Contributors. NiftyNet is released under the Apache License, Version 2.0. Please see the LICENSE file for details.
This project is grateful for the support from the Wellcome Trust, the Engineering and Physical Sciences Research Council (EPSRC), the National Institute for Health Research (NIHR), the Department of Health (DoH), University College London (UCL), the Science and Engineering South Consortium (SES), the STFC Rutherford-Appleton Laboratory, and NVIDIA.