FMRI Data Analysis Using Dempster-Shafer Method with Estimating Voxel Selectivity by Belief Measure

Abdelouahab Attia (1) , Abdelouahab Moussaoui (1) , Abdelmalik Taleb-Ahmed (2)

1 UFAS1 - Université Ferhat-Abbas Sétif 1 [Sétif]
2 LAMIH - Laboratoire d'Automatique, de Mécanique et d'Informatique industrielles et Humaines - UMR 8201

In the functional Magnetic Resonance Imaging (fMRI) data analysis, detecting the activated voxels is a challenging research problem where the existing methods have shown some limits. We propose a new method wherein brain mapping is done based on Dempster-Shafer theory of evidence (DS) that is a useful method in uncertain representation analysis. Dempster-Shafer allows finding the activated regions by checking the activated voxels in fMRI data. The activated brain areas related to a given stimulus are detected by using a belief measure as a metric for evaluating activated voxels. To test the performance of the proposed method, artificial and real auditory data have been employed. The comparison of the introduced method with the t-test and GLM method has clearly shown that the proposed method can provide a higher correct detection of activated voxels

Mots clés: Dempster-Shafer theory; fMRI; GLM; t-test; HRF; OTSU method

Domaines: Automatique / Robotique

Abdelouahab Attia, Abdelouahab Moussaoui, Abdelmalik Taleb-Ahmed. FMRI Data Analysis Using Dempster-Shafer Method with Estimating Voxel Selectivity by Belief Measure. International journal of advanced computer science and applications (IJACSA), 2016, 7 (1), pp.316-324. ⟨10.14569/IJACSA.2016.070143⟩. ⟨hal-03427002⟩