Name
Abstract | ||
|---|---|---|
We address the issue of jointly detecting brain activity and estimating brain hemodynamics from functional MRI data. To this end, we adopt the so-called Joint-Detection-Estimation (JDE) framework introduced in [1] and augmented in [2]. An inherent difficulty is to find the right spatial scale at which brain hemodynamics estimation makes sense. The voxel level is clearly not appropriate as estimating a full hemodynamic response function (HRF) from a single voxel time course may suffer from a poor signal-to-noise-ratio and lead to potentially misleading results (non-physiological HRF shapes). More robust estimation can be obtained by considering groups of voxels (i.e. parcels) with some functional homogeneity properties. Current JDE approaches are therefore based on an initial parcellation but with no guarantee of its optimality or goodness. In this work, we propose a joint parcellation-detection-estimation (JPDE) procedure that incorporates an additional parcel estimation step solving this way both the parcellation choice and robust HRF estimation issues. As in [3], inference is carried out in a Bayesian setting using variational approximation techniques for computational efficiency. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/ICIP.2012.6467099 | ICIP |
Keywords | Field | DocType |
belief networks,biomedical MRI,brain,medical image processing,object detection,Bayesian setting,HRF,JDE framework,JPDE procedure,brain activity,brain hemodynamics estimation,functional MRI data,hemodynamic response function,initial parcellation,parcel estimation step,robust voxel-wise joint detection estimation framework,single voxel time course,using variational approximation techniques,Biomedical signal detection,MRF,Magnetic resonance imaging,Variational EM | Voxel,Computer vision,Object detection,Homogeneity (statistics),Pattern recognition,Computer science,Inference,Brain activity and meditation,Artificial intelligence,Machine learning,Bayesian probability | Conference |
ISSN | Citations | PageRank |
1522-4880 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lotfi Chaâri | 1 | 111 | 13.30 |
| Florence Forbes | 2 | 381 | 19.21 |
| Thomas Vincent | 3 | 320 | 27.52 |
| Philippe Ciuciu | 4 | 452 | 50.82 |