ivadomed configs for cascaded pipeline

[uzaymacar]

This PR adds the ivadomed config file cascaded.json for running inference on a cascaded pipeline as mentioned in #9.

To Reproduce

0. Make sure you have the following dependencies:

• sct=5.4.0
• ivadomed=(git-master-1d81b32c61891e4b5b4f2ffbbb7923e367111dc9*)

1. Clone the repository:

git clone https://github.com/ivadomed/model_seg_ms_mp2rage.git
cd model_seg_ms_mp2rage

2. Clone the latest version of the data:

git clone [email protected]:datasets/basel-mp2rage
cd basel-mp2rage
git annex get .
cd ..

3. Preprocess the data:

sct_run_batch -script preprocessing/preprocess_data.sh -path-data basel-mp2rage -path-output basel-mp2rage-preprocessed-lesionseg -script-args "svm lesionseg" -jobs <JOBS>

4. Run inference wit the cascaded pipeline:

git checkout um/ivadomed_cascaded_pipeline
ivadomed --test -c config/cascaded.json

[uzaymacar]

As discussed in the previous meeting, the users of these models want to segment the spinal cord precisely. Therefore, we don't need a cascaded pipeline and I'm closing this PR.

[uzaymacar]

Returning back to this closed PR, the recent #45 lays out a good motivation for investing in a cascaded model. I will create a new branch and open a new PR to address this shortly.