Shape effects on reflexive spatial selective attention and a plausible neurophysiological model

Abstract

If a peripheral, behaviorally irrelevant cue is followed by a target at the same position, response time for the target is either facilitated or inhibited relative to the response at an uncued position, depending on the delay between target and cue (Posner, 1980; Posner & Cohen, 1984). A few studies have suggested that this spatial cueing effect (termed reflexive spatial attention) is affected by non-spatial cue and target attributes such as orientation or shape. We measured the dependence of the spatial cueing effect on the shapes of the cue and the target for a range of cue onset to target onset asynchronies (CTOAs). When cue and target shapes were different, the spatial cueing effect was facilitatory for short CTOAs and inhibitory for longer CTOAs. The facilitatory spatial effect at short CTOAs was substantially reduced when cue and target shapes were the same. We present a simple neural network to explain our data, providing a unified explanation for the spatial cueing effect and its dependence on shape similarities between the cue and the target. Our modeling suggests that one does not need independent mechanisms to explain both facilitatory and inhibitory spatial cueing effects. Because the neuronal properties (repetition suppression) and the network connectivity (mutual inhibition) of the model are present throughout many visual brain regions, it is possible that reflexive attentional effects may be distributed throughout the brain with different regions expressing different types of reflexive attention depending on their sensitivities to various aspects of visual stimuli.

Fig. 1.

Experimental paradigm. There were four types of trials (TT1–TT4) intermixed randomly in a single run. In this example, trials for a single cue shape (cross) and a single target location (left) are illustrated. The horizontal arrow at the bottom represents time. After fixation (left column; random duration between 800 and 1200 ms), a cue is flashed (83 or 200 ms) either to the left or right of the fixation point (middle column). After a random delay (33–1600 ms), a target is presented which remains on the screen until the observer responds. The observer’s correct response in any of these trials is ‘left’.

Fig. 2.

Neural network model of reflexive spatial attention. The pattern of network connectivity is illustrated for two spatial locations (Location 1, Location 2). Shape selective neurons (N_1a, N_1b) and (N_2a, N_2b) encode spatial Locations 1 and 2 respectively. Neurons encoding a given location with different shape selectivity mutually inhibit each other (e.g., N_1a inhibits N^1b and N_1b inhibits N_1a) via inter-neurons (IN_1ab and IN_1ba, respectively). The dynamic firing rate activity from all shape selective neurons encoding a location are summed (Sum1 and Sum2). The output of the model is equal to the larger sum and its target related responses represent the modulatory component of the behavioral response to the target.

Fig. 3.

Cueing effects as a function of CTOA. The four types of cueing effects shown are: (a) Same-shape spatial cueing effect (top, left panel; CE1). (b) Different-shape spatial cueing effect (top, right panel; CE2). (c) Same-location shape effect (bottom, left panel; CE3). (d) Different-location shape effect (CE4; bottom, right panel). The asterisk in each plot indicates that at that particular CTOA the corresponding cueing effect is significant. The error bars represent ± 1 SE of median. The solid (dashed) lines correspond to data from the long (short) duration cue experiment.

Fig. 4.

Comparison of cueing effects in the short and long cue duration experiments. The four types of cueing effects (CE1–CE4) are shown separately for short (black bars) and long (clear bars) cue duration experiments. For each experiment and each type of cueing effect, cueing effects are shown for CTOAs of 350 and 600 ms. The error bars represent 95% confidence interval of the median.

Fig. 5.

Simulated neuronal activity traces in response to a single pulse input simulating the presentation of shape “a” in location 1. (a) A 50 ms pulse is applied to N_1a at time 0 (dotted vertical lines). The inputs to the other three neurons were set to zero. The top panel shows the firing rate output of N_1a. Other shape selective neurons in the model have similar dynamic properties. It shows a rapid increase in firing rate followed by a slow decay to an elevated baseline. The middle panel shows the gain change that occurs within N_1a for the excitatory input of N_1a. The lower panel shows the firing rate changes in the inter-neuron IN_1ab. (b) Responses of model neurons for a cue and a target presentation. Each column of traces represents one of three types of cueing protocol: column 1, TT1 – cue (C) and target (T) have same shapes and are presented at the same location (left column), column 2, TT2 – cue and target have different shapes but are presented at the same location (middle column), and column 3, TT3 – cue and target have same shapes but are presented at different locations (right column). The cue duration is 50 ms and CTOA is 400 ms. The target stays on until the end of simulation. The left (right) vertical dotted line in each column represents the onset of cue (target). The first four rows show the firing rates of N_1a, N_1b, N_2a and N_2b respectively. The following two rows show the summed activity for each encoded location (Sum1, Sum2). The output of the model is shown in the bottom row. The vertical gray bar in each column of the bottom row indicates the temporal window over which the model’s output is integrated for computations of the cueing effects presented in the following two figures.

Fig. 6.

Simulated cueing effect as a function of CTOA for a typical reflexive spatial attention paradigm in which cue and target have different shapes. Note that the unit for the y-axis is simulation unit (SU) and is also used in Fig. 7. To convert the integrated activity of model’s output to SU, it was divided by 0.001. The conversion to SU was performed to keep the plotted data in a reasonable range. A facilitatory cueing effect occurs for short CTOAs while an inhibitory cueing effect (IOR) occurs for long CTOAs. The duration of the cue is 50 ms and CTOAs range from 75 to 1800 ms. The target remains on until the end of simulation.

Fig. 7.

Simulated cueing effects as a function of CTOA in normal and lesioned models. Lesioned models explore the effects of adaptive gain control and mutual inhibition on these cueing effects. The unit for the y-axis is SU as defined in Fig. 6. The top and middle rows represent two spatial cueing conditions: Top row – cue and target have same shapes (CE1). And middle row – cue and target have different shapes (CE2). The bottom row shows the shape cueing effect when cue and target are at the same location (CE3). The different columns show simulations for a model in which: Column 1 – both adaptive gain control and mutual inhibition are enabled. Column 2 – adaptive gain control is disabled. Column 3 – mutual inhibition is disabled. And, column 4 – both adaptive gain control and mutual inhibition are disabled. The duration of the cue is 200 ms for CTOAs ranging from 300 to 1800 ms and 83 ms for a CTOA of 100 ms. These cue durations are used because they match the empirical data in Fig. 3. The target is left on until the end of simulation.