Diminished reward responsiveness is associated with lower reward network GluCEST: an ultra-high field glutamate imaging study

Abstract

Low reward responsiveness (RR) is associated with poor psychological well-being, psychiatric disorder risk, and psychotropic treatment resistance. Functional MRI studies have reported decreased activity within the brain's reward network in individuals with RR deficits, however the neurochemistry underlying network hypofunction in those with low RR remains unclear. This study employed ultra-high field glutamate chemical exchange saturation transfer (GluCEST) imaging to investigate the hypothesis that glutamatergic deficits within the reward network contribute to low RR. GluCEST images were acquired at 7.0 T from 45 participants (ages 15-29, 30 females) including 15 healthy individuals, 11 with depression, and 19 with psychosis spectrum symptoms. The GluCEST contrast, a measure sensitive to local glutamate concentration, was quantified in a meta-analytically defined reward network comprised of cortical, subcortical, and brainstem regions. Associations between brain GluCEST contrast and Behavioral Activation System Scale RR scores were assessed using multiple linear regressions. Analyses revealed that reward network GluCEST contrast was positively and selectively associated with RR, but not other clinical features. Follow-up investigations identified that this association was driven by the subcortical reward network and network areas that encode the salience of valenced stimuli. We observed no association between RR and the GluCEST contrast within non-reward cortex. This study thus provides new evidence that reward network glutamate levels contribute to individual differences in RR. Decreased reward network excitatory neurotransmission or metabolism may be mechanisms driving reward network hypofunction and RR deficits. These findings provide a framework for understanding the efficacy of glutamate-modulating psychotropics such as ketamine for treating anhedonia.

Figure 1.. Overview of Structural and GluCEST Processing.

Structural: Structural images acquired as part of the 7.0T Magnetization Prepared 2 Rapid Acquisition Gradient Echoes (MP2RAGE) sequence were bias field corrected and used to generate tissue segmentation maps (cerebrospinal fluid voxels shown in white, brain tissue in gray). Atlases were registered from MNI space to participant images. GluCEST: B₀ and B₁ inhomogeneity-corrected GluCEST images were generated from raw Chemical Exchange Saturation Transfer (CEST) images, and voxels labeled as cerebrospinal fluid (CSF) by tissue segmentation maps were removed from final GluCEST images. The GluCEST contrast was then estimated in the meta-analytic reward network. The color bar (bottom right) represents the average GluCEST contrast in each 1 × 1 × 5 mm³ GluCEST voxel, scaled from 1% contrast (dark blue) to 15% contrast (light yellow).

Figure 2.. Association Between Dimensional Reward Responsiveness and Reward Network GluCEST.

A) The meta-analytically defined reward network comprised of cortical, subcortical, and upper brainstem regions. B) Reward network GluCEST contrast was positively associated with BAS Reward Responsiveness scores across typically developing and clinical groups. Data points are differently colored for typically developing (TD) individuals, individuals with a depressive disorder (DEP), and individuals with a psychosis spectrum disorder (PSY).

Figure 3.. Association Between Dimensional Reward Responsiveness and Subcortical Reward Network GluCEST.

A) Cortical (purple) and subcortical (yellow) components of the reward network. B) GluCEST imaging revealed a significant association between BAS Reward Responsiveness scores and the GluCEST contrast in the subcortical reward network. Individual data points are colored based on diagnosis; TD: typically developing, DEP: depressive disorder, PSY: psychosis spectrum disorder.

Figure 4.. Effect Size Determined by Valence Encoding.

Effect sizes for the association between brain GluCEST contrast and BAS Reward Responsiveness scores for the total reward network, appetitive-encoding reward network regions, aversive-encoding reward network regions, salience-encoding reward network regions, and non-reward regions (left to right). Partial R values were derived from independent multiple linear regressions, as reported in the text.