Long-term sensorimotor adaptation in the ocular following system of primates

Abstract

The sudden movement of a wide-field image leads to a reflexive eye tracking response referred to as short-latency ocular following. If the image motion occurs soon after a saccade the initial speed of the ocular following is enhanced, a phenomenon known as post-saccadic enhancement. We show in macaque monkeys that repeated exposure to the same stimulus regime over a period of months leads to progressive increases in the initial speeds of ocular following. The improvement in tracking speed occurs for ocular following with and without a prior saccade. As a result of the improvement in ocular following speeds, the influence of post-saccadic enhancement wanes with increasing levels of training. The improvement in ocular following speed following repeated exposure to the same oculomotor task represents a novel form of sensori-motor learning in the context of a reflexive movement.

Fig 1. Visual stimuli, task and sample eye traces.

A. Visual stimuli and task. Monkeys viewed vertical cosine gratings and were required to fixate a small target (red). The fixation target was initially presented 10° either to the left, to the right or below the center of the screen. This peripheral target was then removed and replaced with a central target that the monkeys were required to saccade to and fixate for either 50 ms (short-delay condition) or 300 ms (long-delay condition). At the end of this delay the grating began moving either to the left or to the right. This motion elicited robust ocular following eye movements. B. Sample eye traces. Example vertical (top) and horizontal (middle) eye position, and horizontal eye speed (bottom) traces from one monkey for both the short- and long-delay conditions. Eye traces for all trials (gray) were aligned at the start of the motion. Red and blue traces show mean eye position and speed signals for the long- and short-delay conditions respectively. The rectangular box on the horizontal eye speed trace indicates the analysis window for calculation of initial ocular following eye speeds.

Fig 2. Initial eye speeds of the two monkeys over sessions.

A,B. Mean ocular following eye speed for monkey 1 for rightward (A) and leftward (B) image motion plotted against binned sessions following saccades to the center of the screen at short (circles) and long (squares) delays. Error bars represent 95% confidence intervals. D,E. The same plots for monkey 2. C,F. The ratio of ocular following speed for the short-delay versus the long-delay conditions (Enhancement, Eq 1) for rightward and leftward motion in monkey 1 (C) and monkey 2 (F). In general, ocular following eye speed was faster in the short-delay condition. Over time, initial ocular following eye speed increased such that this post-saccadic enhancement of the ocular following response was completely (monkey 1) or partly (monkey 2) abolished.

Fig 3. Time course of ocular following adaptation in the two monkeys.

Comparison of the ocular following speed and of the post-saccadic enhancement across an equal number of sessions (A-C) and across time (D-F) between the two monkeys. Ocular following speeds increase over time (with ongoing exposure to the same paradigm), but mainly for rightward motion. Both Monkeys had slight differences in eye speed related to saccade direction, with Monkey 1 showing larger and sustained increases over time in ocular following responses for rightward background motion, and Monkey 2 reaching peak ocular following responses for rightward motion over fewer sessions.

Fig 4. Analysis of ocular following speed following saccades at 0, 90 and 180 degrees.

Comparison of the ocular following speed for Monkey 1 (A-C) and Monkey 2 (D-F). Each plot: 1) shows the saccade direction across a stationary vertical grating (abscissa) plotted against the ocular following eye speed (ordinate); 2) Open circles show the responses at short delay (50ms) conditions, while the x’s show the responses at the long delay (300ms) conditions; 3) Solid and dashed lines indicate that the background motion driving the ocular following response was rightward (0deg) or leftward (180deg) respectively. Monkey 1 shows a tendency for ocular following responses to be reduced when the background motion during ocular following is in the opposite direction to the preceding saccade, compared to the same or vertical conditions. This effect is strongest and equal for short delay conditions (circles) in the first 7 sessions (A). Monkey 2 shows a tendency for ocular following responses to increase when background motion is in the same direction as the preceding saccade, compared to the opposite and vertical directions. This effect is strongest for the short delay conditions (circles 50ms) and is consistently strong across sessions (D-F).