Learning the integral connectional template of the brain



Check out our recent NormNets publications, videos, open source codes and more ~

24 May 2020

step 0

This is the first work on estimating a connectional brain template of a population of multi-view brain networks.

netNorm can be used to integrate a population of multi-view network datasets with heterogeneous distributions, given that they have the same size.

Source code in Matlab:

Source code in Python:


23 June 2020

Output 1


The first geometric deep learning model for multiview brain network integration and connectional brain template estimation is now accepted for publication in MICCAI (class A1) conference Springer proceedings.


Publication: M.B. Gurbuz and I. Rekik. Deep Graph Normalizer: A Geometric Deep Learning Approach for Estimating Connectional Brain Templates. MICCAI (2020), Lima, Peru (acceptance rate ~30%). —in press

23 June 2020

Output 2


Our work on supervised brain multigraph diffusion and fusion  for estimating population-driven connectional brain templates is now accepted for publication in MICCAI (class A1) conference Springer proceedings.


Publication: I. Mhiri, M.A. Mahjoub, and I. Rekik. Supervised Multi-topology Network Cross-diffusion for Population-Driven Brain Network Atlas Estimation. MICCAI (2020), Lima, Peru (acceptance rate ~30%). 

check out more BASIRA lab publications

Acknowledgements: This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 101003403.

Feel free to contact us at to apply for positions at BASIRA lab or establish synergetic collaborations!