This work is based on:

• Jose Dolz, Christian Desrosiers, Ismail Ben Ayed, 3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study, In NeuroImage, 2017
• joseabernal's solution for iSeg2017. Github

Accepted by ISMRM Workshop on Machine Learning 2018.

Some preliminary reports can be found at Medium (Part 1) (Part 2)

• Update 2018-02-04:

Larger kernel size (7, 7, 3), add Batch Normalization and auxiliary feature input of spatial coordinates information.

• Update 2018-03-28:

Add wrapper for segmentation (inference).

1. Put QSM images in datasets/QSM/
2. Put spatial coordinates maps in datasets/X/, datasets/Y/, datasets/Z/
3. Put segmented ROI labels in datasets/label/
4. Run segDGM_3DCNN.ipynb

Example: python3 segDGM_3DCNN.py -i input_filename.nii.gz -o output_label.nii.gz

It uses pre-calculated weights in models/weights_optimal.h5