The InteractiveVis software framework provides a blueprint for evaluating 3D datasets with convolutional neural networks (CNNs), and for deriving and visualizing CNN relevance maps. This tool was developed and tested for disease detection in MRI scans. We plan to extend it to other domains.


What InteractiveVis can do for you

Deep Learning Interactive Visualization

This project provides a software framework and all source code to learn a 3D convolutional neural network model for disease detection (e.g. Alzheimer's disease) and for visualization of contributing image regions with high relevance.

Further details on the procedures including samples, image processing, neural network modeling, evaluation, and validation were published in:

Dyrba et al. (2021) Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: evaluation in Alzheimer’s disease. Alzheimer's research & therapy 13. DOI: 10.1186/s13195-021-00924-2.

Screenshot of the InteractiveVis appScreenshot of the InteractiveVis app

Running the interactive visualization

The interactive Bokeh web application InteractiveVis can be used for deriving and inspecting the relevance maps overlaid on the original input images.

To run it, there are three options.

  1. We set up a public web service to quickly try it out:

  2. Alternatively, download the docker container from DockerHub: sudo docker pull martindyrba/interactivevis
    Then use theprovided scripts sudo ./ and sudo ./ to run or stop the Bokeh app. (You find both files above in this repository.)
    After starting the docker container, the app will be available from your web browser: http://localhost:5006/InteractiveVis

  3. Download the Git repository. Install the required Python modules (see below). Then point the Anaconda prompt or terminal console to the DeepLearningInteractiveVis main directory and run the Bokeh app using:
    bokeh serve InteractiveVis --show

Requirements and installation:

To be able to run the interactive visualization from the Git sources, you will need Python 2 or 3 (specifically Python <3.8, in order to install tensorflow==1.15).
Note: We recommend to use Anaconda as development environment as it is capable of dynamically switching between virtual environments with different Python versions and packages.

Also, it is recommended to first create a new Python environment (using conda or virtualenv/venv) to avoid messing up your local Python modules/versions when you have other coding projects.

conda create -n InteractiveVis python=3.7
conda activate InteractiveVis

Run pip to install the dependencies:

pip install -r requirements.txt

Then you can start the Bokeh application:

bokeh serve InteractiveVis --show
Logo of InteractiveVis
Programming languages
  • Jupyter Notebook 79%
  • HTML 18%
  • MATLAB 2%
  • Python 1%
  • MIT
</>Source code

Participating organisations

German Center for Neurodegenerative Diseases


Martin Dyrba
Martin Dyrba
German Center for Neurodegenerative Diseases (DZNE)