Tommaso Di Noto1, Guillaume Marie1, Sebastien Tourbier1, Yasser Alemán-Gómez1,2, Oscar Esteban1, Guillaume Saliou1, Meritxell Bach Cuadra1,3, Patric Hagmann1, and Jonas Richiardi1
1Department of Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland, 2Center for Psychiatric Neuroscience, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland, 3Medical Image Analysis Laboratory (MIAL), Centre d’Imagerie BioMédicale (CIBM), Lausanne, Switzerland
1Department of Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland, 2Center for Psychiatric Neuroscience, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland, 3Medical Image Analysis Laboratory (MIAL), Centre d’Imagerie BioMédicale (CIBM), Lausanne, Switzerland
Participating in machine learning challenges provides valuable insights for medical imaging problems. In our case, the expedients learnt from a public challenge helped us to improve the sensitivity of our model both on one in-house test dataset and on the challenge test data.
MRA orthogonal views of a 31-year-old female subject: blue patches are the ones which are retained in the anatomically-informed sliding-window approach. (top-right): 3D schematic representation of sliding-window approach; out of all the patches in the volume (white patches), we only retain those located in the proximity of the Willis polygon (blue ones).
(left): 24 landmark points (in pink) located in specific positions of the Willis polygon (white segmentation) in MNI space. (right): same landmark points co-registered to the MRA space of one subject
