Native installation

Notes:

  • The current installation has been tested on Ubuntu 18.04

  • The native installation is not supported

Prerequisites

Anaconda

We use Anaconda to manage the environment and dependencies. Please follow instructions to install Anaconda.

HippUnfold

AID-HS extracts volume- and surface-based features of the hippocampus using HippUnfold. Please follow instructions to install HippUnfold v1.1.0.

Workbench Connectom

AID-HS uses Workbench Connectom to create additional surface-based features. Please follow instructions to install Workbench Connectom.

AID-HS license

In order to run AID-HS you need to have a aidhs_license.txt in the aidhs folder. To get this file, please fill out the AID-HS registration form. Once submitted, your application will be automatically reviewed and the aidhs_license.txt file will be send to your email.

Installation & configuration

In order to run the pipeline, you’ll need to configure a couple of files

  1. Download aidhs.zip from the latest github release and extract it.

  2. Copy the aidhs_license.txt into the extracted folder (see above how to get the AID-HS license)

Create the environment

Run the commands below in your terminal to create the conda environment

# enter the aid_hs directory
cd aidhs
# create the aidhs_env environment with all the dependencies 
conda env create -f environment.yml
# activate the environment
conda activate aidhs
# install aid_hs package with pip (with `-e`, the development mode, to allow changes in the code to be immediately visible in the installation)
pip install -e .

Set up paths and download model

Before being able to use AID-HS on your data, some paths need to be set up and the pretrained model needs to be downloaded. For this, run:

python prepare_aidhs.py

This script will ask you if you want to change the path to the data folder, answer ‘y’ for yes.
Then, it will ask for the the location of your AID-HS data folder where you would like to store MRI data to run the classifier. Create the AID-HS data folder, if it doesn’t exist, and provide the path. It will download the pretrained model and test data to a folder inside your AID-HS data folder

Verify installation

To verify that you have installed all packages, set up paths correctly, and downloaded all data, this verification script will run the pipeline to predict the HS side on a test patient which already has the hippocampal segmentation done. It takes approximately 1 minutes to run.

# enter the aid_hs directory
cd aidhs
# run the test
pytest

Errors

The native installation is not supported as it is very system and software dependant. If you encounter any issues at this stage we recommend to install the docker version.

You will find pytest_errors.log in the folder where you launched the command.

FAQs

Please see our FAQs for common installation problems.

Contact

If have any question please contact meld.study@gmail.com