DLTK: State of the Art Reference Implementations for Deep Learning on Medical Images
This provides accessible state-of-the-art tools for researchers and practitioners in medical imaging, though it is incremental as it builds on existing methods.
The authors tackled the problem of applying deep learning to medical images by developing DLTK, a toolkit with reference implementations, which achieved a new top performance of 81.5 average test Dice similarity coefficient on a public challenge dataset, exceeding previous methods.
We present DLTK, a toolkit providing baseline implementations for efficient experimentation with deep learning methods on biomedical images. It builds on top of TensorFlow and its high modularity and easy-to-use examples allow for a low-threshold access to state-of-the-art implementations for typical medical imaging problems. A comparison of DLTK's reference implementations of popular network architectures for image segmentation demonstrates new top performance on the publicly available challenge data "Multi-Atlas Labeling Beyond the Cranial Vault". The average test Dice similarity coefficient of $81.5$ exceeds the previously best performing CNN ($75.7$) and the accuracy of the challenge winning method ($79.0$).