Reference : Random Forests based group importance scores and their statistical interpretation: ap...
Scientific journals : Article
Engineering, computing & technology : Multidisciplinary, general & others
http://hdl.handle.net/2268/226085
Random Forests based group importance scores and their statistical interpretation: application for Alzheimer’s disease
English
Wehenkel, Marie mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Sutera, Antonio mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique >]
Bastin, Christine mailto [Université de Liège - ULiège > Département des sciences cliniques > Neuroimagerie des troubles de la mémoire et révalid. cogn. >]
Geurts, Pierre* mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique >]
Phillips, Christophe* mailto [Université de Liège - ULiège > > GIGA-CRC In vivo Imaging >]
* These authors have contributed equally to this work.
29-Jun-2018
Frontiers in Neuroscience
Frontiers Media S.A.
12
Machine Learning in Imaging Neurodevelopment and Neurodegeneration
411
Yes (verified by ORBi)
International
1662-453X
Switzerland
[en] Machine learning ; Random forests ; Feature selection ; Group based method ; Prognosis system ; FDG PET ; Alzheimer's disease
[en] Machine learning approaches have been increasingly used in the neuroimaging field for the design of computer-aided diagnosis systems. In this paper, we focus on the ability of these methods to provide interpretable information about the brain regions that are the most informative about the disease or condition of interest. In particular, we investigate the benefit of group-based, instead of voxel-based, analyses in the context of Random forests. Assuming a prior division of the voxels into non overlapping groups (defined by an atlas), we propose several procedures to derive group importances from individual voxel importances derived from random forests models. We then adapt several permutation schemes to turn group importance scores into more interpretable statistical scores that allow to determine the truly relevant groups in the importance rankings. The good behavior of these methods is first assessed on artificial datasets. Then, they are applied on our own dataset of FDG-PET scans to identify the brain regions involved in the prognosis of Alzheimer's disease.
Centre de Recherches du Cyclotron - CRC
Fonds de la Recherche Scientifique (Communauté française de Belgique) - F.R.S.-FNRS
Researchers ; Professionals
http://hdl.handle.net/2268/226085
10.3389/fnins.2018.00411

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
fnins-12-00411.pdfPublisher postprint3.15 MBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.