All Projects → DLTK → Dltk

DLTK / Dltk

Licence: apache-2.0
Deep Learning Toolkit for Medical Image Analysis

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Dltk

Models
DLTK Model Zoo
Stars: ✭ 101 (-91.91%)
Mutual labels:  data-science, deep-neural-networks, cnn, medical-imaging, medical
Livianet
This repository contains the code of LiviaNET, a 3D fully convolutional neural network that was employed in our work: "3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study"
Stars: ✭ 143 (-88.55%)
Mutual labels:  deep-neural-networks, neural-networks, cnn, neuroimaging, medical-imaging
Codesearchnet
Datasets, tools, and benchmarks for representation learning of code.
Stars: ✭ 1,378 (+10.33%)
Mutual labels:  data-science, neural-networks, cnn, ml
Niftynet
[unmaintained] An open-source convolutional neural networks platform for research in medical image analysis and image-guided therapy
Stars: ✭ 1,276 (+2.16%)
Mutual labels:  deep-neural-networks, ml, medical-imaging
Deephyper
DeepHyper: Scalable Asynchronous Neural Architecture and Hyperparameter Search for Deep Neural Networks
Stars: ✭ 117 (-90.63%)
Mutual labels:  deep-neural-networks, neural-networks, ml
Iresnet
Improved Residual Networks (https://arxiv.org/pdf/2004.04989.pdf)
Stars: ✭ 163 (-86.95%)
Mutual labels:  deep-neural-networks, neural-networks, cnn
Hyperdensenet
This repository contains the code of HyperDenseNet, a hyper-densely connected CNN to segment medical images in multi-modal image scenarios.
Stars: ✭ 124 (-90.07%)
Mutual labels:  deep-neural-networks, neural-networks, cnn
Learning Deep Learning
Paper reading notes on Deep Learning and Machine Learning
Stars: ✭ 388 (-68.94%)
Mutual labels:  cnn, medical-imaging, medical
Andrew Ng Notes
This is Andrew NG Coursera Handwritten Notes.
Stars: ✭ 180 (-85.59%)
Mutual labels:  data-science, deep-neural-networks, ml
Radio
RadIO is a library for data science research of computed tomography imaging
Stars: ✭ 198 (-84.15%)
Mutual labels:  data-science, neural-networks, medical-imaging
Awesome Distributed Deep Learning
A curated list of awesome Distributed Deep Learning resources.
Stars: ✭ 277 (-77.82%)
Mutual labels:  data-science, deep-neural-networks, neural-networks
Quickdraw
Implementation of Quickdraw - an online game developed by Google
Stars: ✭ 805 (-35.55%)
Mutual labels:  deep-neural-networks, neural-networks, cnn
Convisualize nb
Visualisations for Convolutional Neural Networks in Pytorch
Stars: ✭ 57 (-95.44%)
Mutual labels:  neural-networks, cnn
Meme Generator
MemeGen is a web application where the user gives an image as input and our tool generates a meme at one click for the user.
Stars: ✭ 57 (-95.44%)
Mutual labels:  neural-networks, cnn
Lstm Context Embeddings
Augmenting word embeddings with their surrounding context using bidirectional RNN
Stars: ✭ 57 (-95.44%)
Mutual labels:  neural-networks, cnn
Bidaf Keras
Bidirectional Attention Flow for Machine Comprehension implemented in Keras 2
Stars: ✭ 60 (-95.2%)
Mutual labels:  deep-neural-networks, neural-networks
Data Science Bowl 2018
End-to-end one-class instance segmentation based on U-Net architecture for Data Science Bowl 2018 in Kaggle
Stars: ✭ 56 (-95.52%)
Mutual labels:  cnn, medical-imaging
Deep Kernel Gp
Deep Kernel Learning. Gaussian Process Regression where the input is a neural network mapping of x that maximizes the marginal likelihood
Stars: ✭ 58 (-95.36%)
Mutual labels:  deep-neural-networks, neural-networks
Ai Platform
An open-source platform for automating tasks using machine learning models
Stars: ✭ 61 (-95.12%)
Mutual labels:  data-science, neural-networks
Deeplearning4j
All DeepLearning4j projects go here.
Stars: ✭ 68 (-94.56%)
Mutual labels:  deep-neural-networks, neural-networks

Deep Learning Toolkit (DLTK) for Medical Imaging

Gitter Coverage Status Build Status

DLTK logo

DLTK is a neural networks toolkit written in python, on top of TensorFlow. It is developed to enable fast prototyping with a low entry threshold 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.

Documentation

The DLTK API can be found here

Referencing and citing DLTK

If you use DLTK in your work please refer to this citation for the current version:

@article{pawlowski2017state,
  title={DLTK: State of the Art Reference Implementations for Deep Learning on Medical Images},
  author={Nick Pawlowski and S. Ira Ktena, and Matthew C.H. Lee and Bernhard Kainz and Daniel Rueckert and Ben Glocker and Martin Rajchl},
  journal={arXiv preprint arXiv:1711.06853},
  year={2017}
}

If you use any application from the DLTK Model Zoo, additionally refer to the respective README.md files in the applications' folder to comply with its authors' instructions on referencing.

Introduction to Biomedical Image Analysis

To ease into the subject, we wrote a quick overview blog entry (12 min read) for the new TensorFlow blog. It covers some of the speciality information required for working with medical images and we suggest to read it, if you are new to the topic. The code we refer to in the blog can be found in examples/tutorials and examples/applications.

Installation

  1. Setup a virtual environment and activate it. Although DLTK<=0.2.1 supports and python 2.7, we will not support it future releases, similarly to our dependencies (i.e. SciPy, NumPy). We highly recommend using python3. If you intend to run this on machines with different system versions, use the --always-copy flag:

    virtualenv -p python3 --always-copy venv_tf
    source venv_tf/bin/activate
    
  2. Install TensorFlow (>=1.4.0) (preferred: with GPU support) for your system as described here:

    pip install "tensorflow-gpu>=1.4.0"
    
  3. Install DLTK: There are two installation options available: You can simply install dltk as is from pypi via

    pip install dltk
    

    or you can clone the source and install DLTK in edit mode (preferred):

    cd MY_WORKSPACE_DIRECTORY
    git clone https://github.com/DLTK/DLTK.git 
    cd DLTK
    pip install -e .
    

    This will allow you to modify the actual DLTK source code and import that modified source wherever you need it via import dltk.

Start playing

  1. Downloading example data You will find download and preprocessing scripts for publicly available datasets in data. To download the IXI HH dataset, navigate to data/IXI_HH and run the download script with python download_IXI_HH.py.

  2. Tutorial notebooks In examples/tutorials you will find tutorial notebooks to better understand on how DLTK interfaces with TensorFlow, how to write custom read functions and how to write your own model_fn.

    To run a notebook, navigate to the DLTK source root folder and open a notebook server on MY_PORT (default 8888):

    cd MY_WORKSPACE_DIRECTORY/DLTK
    jupyter notebook --ip=* --port MY_PORT
    

    Open a browser and enter the address http://localhost:MY_PORT or http://MY_DOMAIN_NAME:MY_PORT. You can then navigate to a notebook in examples/tutorials, open it (c.f. extension .ipynb) and modify or run it.

  3. Example applications There are several example applications in examples/applications using the data in 1. Each folder contains an experimental setup with an application. Please note that these are not tuned to high performance, but rather to showcase how to produce functioning scripts with DLTK models. For additional notes and expected results, refer to the notes in the individual example's README.md.

DLTK Model Zoo

We also provide a zoo with (re-)implementations of current research methodology in a separate repository DLTK/models. Each model in the zoo is maintained by the respective authors and implementations often differ to those in examples/applications. For instructions and information on the individual application in the zoo, please refer to the respective README.md files.

How to contribute

We appreciate any contributions to the DLTK and its Model Zoo. If you have improvements, features or patches, please send us your pull requests! You can find specific instructions on how to issue a PR on github here. Feel free to open an issue if you find a bug or directly come chat with us on our gitter channel Gitter.

Basic contribution guidelines

  • Python coding style: Like TensorFlow, we loosely adhere to google coding style and google docstrings.
  • Entirely new features should be committed to dltk/contrib before we can sensibly integrate it into the core.
  • Standalone problem-specific applications or (re-)implementations of published methods should be committed to the DLTK Model Zoo repo and provide a README.md file with author/coder contact information.

Running tests locally

To run the tests on your machine, you can install the tests extras by running pip install -e '.[tests]' inside the DLTK root directory. This will install all necessary dependencies for testing. You can then run pytest --cov dltk --flake8 --cov-append to see whether your code passes.

Building docs locally

To run the tests on your machine, you can install the docs extras by running pip install -e '.[docs]' inside the DLTK root directory. This will install all necessary dependencies for the documentation. You can then run make -C docs html to build the documentation. You can access this documentation in a web browser of your choice by pointing it at docs/build/html/index.html.

The team

DLTK is currently maintained by @pawni and @mrajchl with greatly appreciated contributions coming from individual researchers and engineers listed here in alphabetical order: @CarloBiffi @ericspod @ghisvail @mauinz @michaeld123 @sk1712

License

See LICENSE

Acknowledgments

We would like to thank NVIDIA GPU Computing for providing us with hardware for our research.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].