New deep learning toolkit for medical imaging released!


We are pleased to announce the release of the DLTK. DLTK is a neural networks toolkit written in python, on top of Tensorflow. Its modular architecture is closely inspired by Deepmind sonnet and it was developed to enable fast prototyping and ensure reproducibility in image analysis applications, with a particular focus on medical imaging. Its goal is to provide the community with state of the art methods and models and to accelerate research in this exciting field.

We provide example code and tutorials for

  • Image classification
  • Image segmentation
  • Generative adversarial networks
  • Graph convolution networks
  • Representation learning with autoencoders

Source code:
License: Apache v2.0

Follow us on Twitter @dltk_ !

Martin Rajchl, Nick Pawlowski, Ira Ktena and Matthew Lee
Biomedical Image Analysis (BioMedIA) Group,
Imperial College London