Changes in resting state effective connectivity in the motor network following rehabilitation of upper extremity poststroke paresis

Abstract

Background: A promising paradigm in human neuroimaging is the study of slow (<0.1 Hz) spontaneous fluctuations in the hemodynamic response measured by functional magnetic resonance imaging (fMRI). Spontaneous activity (i.e., resting state) refers to activity that cannot be attributed to specific inputs or outputs, that is, activity intrinsically generated by the brain.

Method: This article presents pilot data examining neural connectivity in patients with poststroke hemiparesis before and after 3 weeks of upper extremity rehabilitation in the Accelerated Skill Acquisition Program (ASAP). Resting-state fMRI data acquired pre and post therapy were analyzed using an exploratory adaptation of structural equation modeling (SEM) to evaluate therapy-related changes in motor network effective connectivity.

Results: Each ASAP patient showed behavioral improvement. ASAP patients also showed increased influence of the affected hemisphere premotor cortex (a-PM) upon the unaffected hemisphere premotor cortex (u-PM) following therapy. The influence of a-PM on affected hemisphere primary motor cortex (a-M1) also increased with therapy for 3 of 5 patients, including those with greatest behavioral improvement.

Conclusions: Our findings suggest that network analyses of resting-state fMRI constitute promising tools for functional characterization of functional brain disorders, for intergroup comparisons, and potentially for assessing effective connectivity within single subjects; all of which have important implications for stroke rehabilitation.

Figure 1

Selection of regions of interest (ROIs). (A) Horizontal section of a T1 anatomic image of single patient’s brain following transformation to MNI space (z=50 mm). Arrow and contour indicate the location of the left motor “hand knob.” (B) A correlation map using left M1 as a seed is shown overlaid atop the T1 anatomic image. The thresholded (0.3 ≤ r ≤ 1.0) correlation map guided ROI placement. (C) Five ROIs: supplementary motor area (SMA), left and right lateral premotor (LPM, RPM), and left and right primary motor (LM1, RM1) were defined as 6-mm radius spheres set atop the T1 anatomic image.

Figure 2

Motor system network for each stroke survivor, before (session 1) and after (session 2) therapy. Shading indicates the hemisphere that is affected by stroke. SEM models are shown for each patient’s first session (left) and second session (right) after therapy. The numbers above each line represent the path coefficients and are standardized measures of direct influence. Solid lines with arrows indicate direction of effective connectivity influence. LM1=left primary motor cortex; RM1=right primary motor cortex; LPM = left premotor cortex; RPM=premotor cortex; SMA=supplementary motor area.