Credits: S. Dahan, LZJ. Williams

This repository provides a reference algorithm Docker container for SLCN 2022 Challenge submission, on the grand-challenge plateform.

It should serve as an example or/and a template for your own algorithm container implementaion.

Here, a Surface Vision Trasnformer (SiT) model is used for the task of birth age prediction as an example. Code is based on this Github.

More information about algorithm container and submission can be found here.

1. Prerequisites
2. Requirements for Grand Challenge submission

Submissions are based on Docker containers and the evalutils library (provided by Grand-Challenge).

First, you will need to install localy Docker.

Then, you will need to install evalutils, that you can pip install:

pip install evalutils

You Docker container (via process.py) is supposed to read .mha image files.

Important: Images will be read successively and predictions will be made one by one, ie there will be one birth-age.json file per predicition.