A Multi-Atlas Labeling Approach for Identifying Subject-Specific Functional Regions of Interest

Zonglei Zhen,Xiaobin Dang,Jia Liu,Yiying Song,Guangfu Zhou,Lijie Huang,Huiguang He,Zhaoguo Liu,Xu Wang,Xiang-Zhen Kong,Zetian Yang

doi:10.1371/journal.pone.0146868

Abstract

The functional region of interest (fROI) approach has increasingly become a favored methodology in functional magnetic resonance imaging (fMRI) because it can circumvent inter-subject anatomical and functional variability, and thus increase the sensitivity and functional resolution of fMRI analyses. The standard fROI method requires human experts to meticulously examine and identify subject-specific fROIs within activation clusters. This process is time-consuming and heavily dependent on experts’ knowledge. Several algorithmic approaches have been proposed for identifying subject-specific fROIs; however, these approaches cannot easily incorporate prior knowledge of inter-subject variability. In the present study, we improved the multi-atlas labeling approach for defining subject-specific fROIs. In particular, we used a classifier-based atlas-encoding scheme and an atlas selection procedure to account for the large spatial variability across subjects. Using a functional atlas database for face recognition, we showed that with these two features, our approach efficiently circumvented inter-subject anatomical and functional variability and thus improved labeling accuracy. Moreover, in comparison with a single-atlas approach, our multi-atlas labeling approach showed better performance in identifying subject-specific fROIs.

Highlights

The functional region of interest approach has increasingly become an important methodology in functional magnetic resonance imaging studies [1,2,3,4,5,6]
After assessing the impact of the randomized forest (RF)-based atlasencoding scheme and atlas selection procedure in accounting for the large variability of functional region of interest (fROI), we evaluated the performance of the multi-atlas labeling (MAL) approach with both customizations in identifying fROIs compared with the single-atlas labeling (SAL) approach
We encoded each atlas with an RF classifier to account for the large fROI variability across individuals

Summary

Introduction

The functional region of interest (fROI) approach has increasingly become an important methodology in functional magnetic resonance imaging (fMRI) studies [1,2,3,4,5,6]. In this approach, the fROIs are typically defined functionally in individuals. A short functional localizer is typically acquired in each subject to define subject-specific fROIs according to their response profiles, and a main task is used to test specific functional hypotheses concerning these regions [5,7,8]. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript

Objectives

Methods

Results