Intrasubject reproducibility of functional MR imaging activation in language tasks

Abstract

Background and purpose: The purpose of this study was to examine the reproducibility of functional MR imaging (fMRI) activation (volume and laterality) within both inferior frontal and temporoparietal regions of interest for both receptive and expressive language tasks.

Methods: Ten healthy volunteers participated in fMRI experiments for 6 language tasks: verb generation, confrontation naming, semantic decision making, visual sentence comprehension, auditory sentence comprehension, and story listening. Each subject was scanned during 2 separate sessions separated by a minimum of 4 weeks. Laterality of activation was defined by laterality indices (LIs), which were calculated by 2 methods: one method based on the measured volume of activation and the other method based on the F statistic of the activation. Reproducibility was calculated by using concurrence ratios for the volume of activation (R(overlap), R(volume)) and test-retest correlation for LIs.

Results: All tasks generated reproducible LIs within at least one of the regions of interest, but verb generation produced the highest test-retest correlations (r = 0.99) within both regions of interest. Verb generation was associated with the highest average concurrence ratios within the inferior frontal region of interest (R(overlap) = 45.2; R(volume) = 70.9). In general, the concurrence ratios were lower within the temporoparietal region of interest compared with the inferior frontal region of interest. LIs calculated with F statistics were more reproducible than the LIs calculated by activation volume.

Conclusion: fMRI is able to provide reproducible LIs in both inferior frontal and temporoparietal regions for assessing hemispheric dominance in language processing. The volume of activation, especially within the temporoparietal regions, is less reproducible than the laterality of activation, so the former should be used with caution.

Fig 1.

Reproducibility for fMRI activation: LI and volume. Top row, The LI and test-retest correlation of LI for all tasks and task combinations within both regions of interest. Middle row, The average volume of activation and % subjects with activation during both imaging sessions within the language dominant hemisphere for both regions of interest. Bottom row, Average concurrence ratios (R_volume and R_overlap) within the language dominant hemisphere for both regions of interest. SD = semantic decision; CN = confrontation naming; VG = verb generation; AS = audio sentence comprehension; VS = visual sentence comprehension; SL = story listening; CTa = combination of SD, CN, and VG; CTb = combination of AS,VS, and SL; Ctc = combination of all tasks.

Fig 2.

Verb-generation overlap. Activation for the verb-generation task in 2 example subjects. Images are in radiologic view. Yellow = session 1 only; red = session 2 only; blue = overlap between sessions. Activation information provided in the Table.

Fig 3.

Temporal SNR versus max head motion. Regression analyses: tSNR_med: r = 0.42; P = 2.2 × 10⁻⁶; tSNR_low: r = 0.14; P = .13. White = tSNR_low; black = tSNR_med.