A proof-of-principle study of multi-site real-time functional imaging at 3T and 7T: Implementation and validation

Abstract

Real-time functional Magnetic Resonance Imaging (rtfMRI) is used mainly for neurofeedback or for brain-computer interfaces (BCI). But multi-site rtfMRI could in fact help in the application of new interactive paradigms such as the monitoring of mutual information flow or the controlling of objects in shared virtual environments. For that reason, a previously developed framework that provided an integrated control and data analysis of rtfMRI experiments was extended to enable multi-site rtfMRI. Important new components included a data exchange platform for analyzing the data of both MR scanners independently and/or jointly. Information related to brain activation can be displayed separately or in a shared view. However, a signal calibration procedure had to be developed and integrated in order to permit the connecting of sites that had different hardware and to account for different inter-individual brain activation levels. The framework was successfully validated in a proof-of-principle study with twelve volunteers. Thus the overall concept, the calibration of grossly differing signals, and BCI functionality on each site proved to work as required. To model interactions between brains in real-time, more complex rules utilizing mutual activation patterns could easily be implemented to allow for new kinds of social fMRI experiments.

Figure 1

(a–c) Results of the functional localizer: Individual and mean BOLD signals of the 3T and 7T group. (a) 3T single subject BOLD signals from the functional localizer with standard error. Max. amplitude: subj01 = 2.69%, subj02 = 2.95%, subj03 = 3.19%, subj04 = 1.28%, subj05 = 1.87%, subj06 = 1.51%; (b) 7T single subject BOLD signals from the functional localizer with standard error. Max. amplitude: subj07 = 4.81%, subj08 = 3.07%, subj09 = 2.79%, subj10 = 2.12%, subj11 = 4.13%, subj12 = 4.10%; (c) Mean BOLD signals from the functional localizer for 3T and 7T with standard deviation. Max. amplitude: 3T = 2.17%, 7T = 3.48%. (d) Maximum amplitudes in the low and high sensorimotor activation at 3T and 7T in the main experiment, averaged over all three tasks. The bars represent the mean percentage increase of the BOLD signals with the according standard errors. The number in the green circle represents the total number of successful runs. Subject 1 was excluded from the analysis, subjects 2–6 were measured at 3T, subjects 7–12 were measured at 7T. A highly significant difference between weak and strong tapping was found.

Figure 2. Activation patterns as a function of motor execution in the main experiment.

Statistical maps (p < 0.001 FDR corrected, cluster threshold 30 voxels) of two representative volunteers overlaid on the anatomical group average. (a) 3T single-subject analysis – weak tapping task; b) 3T single-subject analysis – strong tapping task; (c) 7T single-subject analysis – weak tapping task; (d) 7T single-subject analysis – strong tapping task.

Figure 3. Representative slices of the random effects analysis of the group data for both tapping conditions superimposed on the averaged T1-weighted images of all eleven subjects (radiologic convention).

The slices display the main parts of the sensorimotor system (primary contralateral and ipsilateral SMC, bilateral basal ganglia and supplementary motor area (SMA). Upper row: 3T (without subject 1 for details s. text), p < 0.005, FDR corrected. Lower row: 7T, p < 0.005, FDR corr. (cerebellum was not scanned at 7T). For a detailed cluster description, see Table 1.

Figure 4. Schematic flow chart of the main processing modules.

The data flow starts with the image acquisition at each MR scanner. In each local MR environment a component for pre-processing and statistical analysis (S1 and S2) and a component for signal comparison and presentation (P1 and P2) is installed. Although not used in the validation procedure the system contains a module Mutual Signal Exchange (E) where information of each connected site can be exchanged and processed if required. The number of environments can be extended if necessary.

Figure 5. Overview of the experimental setup of the main experiment.

Each block consisted of 15 scans. At the beginning of each block, the task to be performed was presented visually on the screen for 10 s (‘single', ‘competition', ‘cooperation'). In the single task only the own sphere was visible thus excluding information exchange between both partners. The next five scans (TR 2 s) were used to determine the current baseline. The sphere had to be moved into the upper (U) or lower (L) part of the field depicted as a light gray rectangle (here, the task required to move the sphere to the upper part). An auditory signal ('start' or 'stop') delivered by earphones started the finger tapping block lasting two scans. To allow the BOLD signal to build up and decay (which was important for a reliable data analysis) a rest period of seven scans followed the finger tapping. Then the spheres moved to the position according to the individual BOLD signal strengths along with the visual presentation whether the task was fulfilled (and paid off) or whether the task was not fulfilled. Thereafter, the presentation was reset and a new round was started.