Dorsal horn spatial representation of simple cutaneous stimuli

A model of lamina III-IV dorsal horn cell receptive fields (RFs) has been developed to visualize the spatial patterns of cells activated by light touch stimuli. Low-threshold mechanoreceptive fields (RFs) of 551 dorsal horn neurons recorded in anesthetized cats were characterized by location of RF center in cylindrical coordinates, area, length/width ratio, and orientation of long axis. Best-fitting ellipses overlapped actual RFs by 90%. Exponentially smoothed mean and variance surfaces were estimated for these five variables, on a grid of 40 points mediolaterally by 20/segment rostrocaudally in dorsal horn segments L-4-S-1. The variations of model RF location, area, and length/width ratio with map location were all similar to previous observations. When elliptical RFs were simulated at the locations of the original cells, the RFs of real and simulated cells overlapped by 64%. The densities of cell representations of skin points on the hindlimb were represented as pseudocolor contour plots on dorsal view maps, and segmental representations were plotted on the standard views of the leg. Overlap of modeled and real segmental representations was at the 84% level. Simulated and observed RFs had similar relations between area and length/width ratio and location on the hindlimb: r(A) = 0.52; r(L/W) = 0.56. Although the representation of simple stimuli was orderly, and there was clearly only one somatotopic map of the skin, the representation of a single point often was not a single cluster of active neurons. When two-point stimuli were simulated, there usually was no fractionation of response zones or addition of new zones. Variation of stimulus size (area of skin contacted) produced less variation of representation size (number of cells responding) than movement of stimuli from one location to another. We conclude that stimulus features are preserved poorly in their dorsal horn spatial representation and that discrimination mechanisms that depend on detection of such features in the spatial representation would be unreliable.