NiftyNet is a [TensorFlow][tf]-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
- Uncertainty estimation and spatially adaptive weighting in multi-task learning
- Multi-input multi-task learning
- Probabilistic multi-task architecture learning
Demos for specific papers will be hosted elsewhere. TBC..