Unreliability of putative fMRI biomarkers during emotional face processing

Abstract

There is considerable need to develop tailored approaches to psychiatric treatment. Numerous researchers have proposed using functional magnetic resonance imaging (fMRI) biomarkers to predict therapeutic response, in particular by measuring task-evoked subgenual anterior cingulate (sgACC) and amygdala activation in mood and anxiety disorders. Translating this to the clinic relies on the assumption that blood-oxygen-level dependent (BOLD) responses in these regions are stable within individuals. To test this assumption, we scanned a group of 29 volunteers twice (mean test-retest interval=14.3 days) and calculated the within-subject reliability of the amplitude of the amygdalae and sgACC BOLD responses to emotional faces using three paradigms: emotion identification; emotion matching; and gender classification. We also calculated the reliability of activation in a control region, the right fusiform face area (FFA). All three tasks elicited robust group activations in the amygdalae and sgACC (which changed little on average over scanning sessions), but within-subject reliability was surprisingly low, despite excellent reliability in the control right FFA region. Our findings demonstrate low statistical reliability of two important putative treatment biomarkers in mood and anxiety disorders.

Keywords: Amygdala; Biomarker; Emotion; Psychiatry; Subgenual cingulate; fMRI.

Fig. 1

Whole-brain activation maps and parameter estimates for the three functionally-defined regions of interest (left and right amygdala, and subgenual anterior cingulate cortex, sgACC), and the comparison region, the right fusiform face area (FFA), for all runs (both days). Coloured arrows and stars indicate coordinates used in the analysis: cyan arrows correspond to peak activation in the left amygdala; green arrows to peak activation in the right; yellow arrows indicate the coordinate from a previous study (McKeeff and Tong, 2007) used for the FFA analysis; magenta arrows indicate peak activation in the sgACC. Images were thresholded at p<0.001 (uncorrected) and at the minimum cluster size surviving whole-brain cluster-level correction for each contrast; the heat bars indicate t-values. Please see Table 2 for statistics. A, E, I: faces vs fixation (1) and faces vs shapes (1) include all subjects; faces vs fixation (2) and faces vs shapes (2) (B, F, J) exclude the four subjects whose FFA was not included in the mask. Asterisk over the EM (*) bar chart depicts the only main or interaction effect of day or run: the effect of day on sgACC activation (p=0.045).

Fig. 2

Distribution of parameter estimates for the left amygdala (A) and sgACC (B) in day 1 and day 2 for the gender classification task, for the main contrast (faces vs fixation). Note that for this task, parameter estimates are moderately correlated between scan days in both regions.