Heterogeneous Effects of Cognitive Arousal on the Contrast Response in Human Visual Cortex

Abstract

While animal studies have found that arousal states modulate visual responses, direct evidence for effects of arousal on human vision remains limited. Here, we used fMRI to examine effects of cognitive arousal on the gain of contrast response functions (CRFs) in human visual cortex. To measure CRFs, we measured BOLD responses in early visual cortex (V1-V3) while participants (n = 20, 14 females and 6 males) viewed stimuli that parametrically varied in contrast. To induce different cognitive arousal states, participants solved auditory arithmetic problems categorized as either Easy (low arousal) or Hard (high arousal). We found diversity in the modulatory effects across individuals: some individuals exhibited enhanced neural response with increased arousal, whereas others exhibited the opposite effect-a decrease in response with increased arousal. The pattern of overall BOLD modulation showed within-individual stability and was correlated with the degree of arousal-driven change in pupil size. Individuals who exhibited larger increases in pupil size with the arousal manipulation tended to show greater arousal-related decreases in visuocortical responses. We speculate that the polarity of the modulatory effect by cognitive arousal may relate to individual differences in cognitive effort expended in the high-difficulty condition, with individuals reaching different points on an underlying non-monotonic function.

Keywords: BOLD; arousal; contrast response functions; fMRI; vision.

Figure 1.

a, Experimental stimulus composed of gratings with radial orientations (relative to fixation) and varying spatial frequencies, which are cortically magnified. b, Illustration of how sustained contrast adaptation may induce nonlinear population CRFs by bringing units within the population into closer alignment via recalibration of semisaturation point of individual CRFs. c, Example timeline of an experimental run.

Figure 2.

Potential modulations of the CRFs. Arousal may modulate the CRFs through (1) a response gain (red), or a multiplicative gain increasing the amplitude of the CRF; (2) a contrast gain (salmon pink), or a horizontal shift increasing sensitivity; or (3) a baseline shift (light pink), or an additive increase of the CRF.

Figure 3.

The effect of cognitive arousal on visuocortical CRFs in V1, V2, and V3. a, Deconvolved HRF from the BOLD response as a function of stimulus contrast for each cognitive arousal condition, Easy (blue), Hard (red). To obtain CRFs, we measured the average response in each condition within a fixed window of 5–10 s (gray area). b, CRFs for the Hard and Easy condition for each ROI. Error bars represent bootstrapped SEM across subjects. c, Difference in BOLD response at each contrast level subtracting Hard from Easy. The black line represents the group average difference with the error bars representing SEM. The gray lines and dots represent the difference in BOLD CRFs for individuals, and the dashed line indicates no difference in neural response between the Hard and Easy condition. There is large heterogeneity in responses with some subjects displaying a larger CRF BOLD response in the Easy compared with Hard, others displaying a larger BOLD in Hard than Easy, and others showing little-to-no difference.

Figure 4.

Scatterplots of Naka–Rushton parameter estimates comparing Easy versus Hard Rmax (top row), C50 (middle row), and Baseline (bottom row), for each ROI. The dashed line indicates the unity line of no difference in parameter estimates between Easy versus Hard. Overall, there is large variability in parameter estimates across participants.

Figure 5.

a, Exemplar subjects’ contrast response functions (CRFs) from visual area V3. b, The modulatory patterns that best capture the modulation by cognitive arousal across subjects and visual areas V1–V3. The boxes represent the different modulations by arousal, with each color indicating a different modulatory effect. The shades and color placement within a given modulatory effect (gray box) indicate different visual areas: V1 (top color), V2 (middle color), V3 (bottom color). The colored boxes display the modulation or combinations of modulations that best capture arousal's effect within and across observers and visual areas. Across observers, there is large heterogeneity in the modulatory effect of arousal on the CRF, with groups of subjects displaying neural gain enhancements in the Easy and other individuals displaying enhancements in Hard, characterized by various combinations of response gain, contrast gain, and baseline shift patterns. Within participants, there is also variability in modulatory effects by arousal on the CRF across visual areas.

Figure 6.

Occurrence of baseline shift, response gain, and contrast gain modulation across voxels in V1, V2, and V3. The percentage was calculated by collapsing across all combinations, irrespective of modulation direction. Overall, the most prevalent modulatory effect induced by cognitive arousal on the CRF across voxels and the entire group is the baseline shift, which remains consistent across visual areas. Each colored data point represents an individual.

Figure 7.

Pupil size and visuocortical response correlations (n = 19). Correlation between Hard-minus-Easy pupil size and Hard-minus-Easy overall BOLD response, indicative of the overall direction of modulation by arousal (i.e., increasing cognitive arousal enhances neural response or decreases neural response). Overall, there is a correlation between pupil size and overall BOLD response in V1 and V2.

Figure 8.

Average BOLD response in the default mode network and dorsal attention network ROIs under the Easy and Hard condition.

Figure 9.

Illustration of the potential inverted U relationship between cognitive arousal and corresponding neural response of contrast response functions (CRFs), as observed in the study. Subjects displaying minimal arousal difference between difficulty conditions (Easy, Hard), as measured by pupil size, show enhanced neural responses with increasing arousal, which may be due arousal levels falling along the peak of the curve. However, as the arousal difference between the two conditions increases, a shift in the modulatory pattern occurs, resulting in a decrease in neural response for individuals with the largest pupillary difference, which could be a result of arousal levels exceeding the peak of the curve, leading to diminishing responses. It is important to note that this relationship assumes all subjects start at the same level of arousal in the Easy condition.