Skip to Main content Skip to Navigation
Conference papers

A Bayesian estimation formulation to voxel-based lesion-symptom mapping

Abstract : Studying brain-injured patients is important for investigating structure-function relationships using neuroimaging techniques. Voxel-based lesion-symptom mapping (VLSM) has increasingly been advocated as a relevant approach to detect structure-function associations in neuroimaging studies. The VLSM method involves mapping the relationship between brain injuries and behavioral performance on a voxel-byvoxel basis. This means that the statistical relationship between damage and behavior (across patients) is computed separately for each voxel. However, one could expect voxels characterizing group differences to be localized into spatially consistent regions rather than randomly distributed over the brain. Thus, in this paper, we propose to depart from conventional models to characterize and exploit this spatial consistency. More precisely, we derive a Bayesian model that explicitly accounts for spatial correlations between neighboring voxels using a Markov random field. Our results highlight that the proposed approach outperforms the conventional ones. Besides, it has the great advantage of possibly reducing the number of patients and identifying new language areas, which are two crucial insights in the targeted medical context.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03704681
Contributor : Nicolas Dobigeon Connect in order to contact the contributor
Submitted on : Saturday, June 25, 2022 - 2:43:09 PM
Last modification on : Monday, July 4, 2022 - 9:16:00 AM

File

Fall_EUSIPCO_2022.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03704681, version 1

Citation

Mame Diarra Fall, Nicolas Dobigeon, Pascal Auzou. A Bayesian estimation formulation to voxel-based lesion-symptom mapping. 30th European Signal Processing Conference (EUSIPCO 2022), European Association for Signal Processing (EURASIP), Aug 2022, Belgrade, Serbia. ⟨hal-03704681⟩

Share

Metrics

Record views

9

Files downloads

0