Application of mean-shift clustering to Blood oxygen level dependent functional MRI activation detection

Application of mean-shift clustering to Blood oxygen level dependent functional MRI activation detection

BACKGROUND Functional magnetic resonance imaging (fMRI) analysis is commonly done with cross-correlation analysis (CCA) and the General Linear Model (GLM). Both CCA and GLM techniques, however, typically perform calculations on a per-voxel basis and do not consider relationships neighboring voxels may have. Clustered voxel analyses have then been developed to improve fMRI signal detections by t...

Author's response to reviews Title: Application of Mean-Shift Clustering to Blood Oxygen Level Dependent Functional MRI Activation Detection

Resting-State Blood Oxygen Level-Dependent Functional MRI: A Paradigm Shift in Preoperative Brain Mapping.

Currently, functional magnetic resonance imaging (fMRI) facilitates a preoperative awareness of an association of an eloquent region with a tumor. This information gives the neurosurgeon helpful information that can aid in creating a surgical strategy. Typically, task-based fMRI has been employed to preoperatively localize speech and motor function. Task-based fMRI depends on the patient's abil...

Application of sensitivity-encoded echo-planar imaging for blood oxygen level-dependent functional brain imaging.

The benefits of sensitivity-encoded (SENSE) echo-planar imaging (EPI) for functional MRI (fMRI) based on blood oxygen level-dependent (BOLD) contrast were quantitatively investigated at 1.5 T. For experiments with 3.4 x 3.4 x 4.0 mm(3) resolution, SENSE allowed the single-shot EPI image acquisition duration to be shortened from 24.1 to 12.4 ms, resulting in a reduced sensitivity to geometric di...

Mean shift spectral clustering

In recent years there has been a growing interest in clustering methods stemming from the spectral decomposition of the data affinity matrix, which are shown to present good results on a wide variety of situations. However, a complete theoretical understanding of these methods in terms of data distributions is not yet well understood. In this paper, we propose a spectral clustering based mode m...