The basic nonuniformity of the cerebral cortex

Abstract

Evolutionary changes in the size of the cerebral cortex, a columnar structure, often occur through the addition or subtraction of columnar modules with the same number of neurons underneath a unit area of cortical surface. This view is based on the work of Rockel et al. [Rockel AJ, Hiorns RW, Powell TP (1980) The basic uniformity in structure of the neocortex. Brain 103:221-244], who found a steady number of approximately 110 neurons underneath a surface area of 750 microm(2) (147,000 underneath 1 mm(2)) of the cerebral cortex of five species from different mammalian orders. These results have since been either corroborated or disputed by different groups. Here, we show that the number of neurons underneath 1 mm(2) of the cerebral cortical surface of nine primate species and the closely related Tupaia sp. is not constant and varies by three times across species. We found that cortical thickness is not inversely proportional to neuronal density across species and that total cortical surface area increases more slowly than, rather than linearly with, the number of neurons underneath it. The number of neurons beneath a unit area of cortical surface varies linearly with neuronal density, a parameter that is neither related to cortical size nor total number of neurons. Our finding of a variable number of neurons underneath a unit area of the cerebral cortex across primate species indicates that models of cortical organization cannot assume that cortical columns in different primates consist of invariant numbers of neurons.

Fig. 1.

Coordinate increase in cerebral cortical mass, surface area, and number of neurons of the different primate species and the tree shrew. Points represent the average values for each of the 10 species analyzed. (a) Cortical surface area increases more slowly than the number of neurons in the cortex as a power function of exponent 0.805. (b) Cortical mass increases slightly faster than cortical surface as a power function with exponent 1.123. (c) Cortical mass increases as a power function of cortical number of neurons with exponent 0.934.

Fig. 2.

Cortical thickness covaries with cortical surface area but not with neuronal density. Points represent the average values for each of the 10 species analyzed. (a) Cortical thickness does not correlate with neuronal density in the cerebral cortex. (b) Cortical thickness increases slowly as a power function of cortical surface. (c) Neuronal density in the cortex does not covary with cortical surface area. P values of the plotted power functions are indicated.

Fig. 3.

The average number of neurons beneath the cortical surface (N/A) varies across species as a linear function of the product of neuronal density and cortical thickness (D × T) as expected from the equation N = A × D × T. Points represent the average values for each of the 10 species analyzed.

Fig. 4.

The average number of neurons beneath the cortical surface (N/A) varies across species as a power function of neuronal density (d), but not of cortical mass (a), cortical thickness (b), or cortical surface area (c). Points represent the average values for each of the 10 species analyzed. P values for the plotted power functions are indicated.

Fig. 5.

The number of neurons beneath the cortical surface (N/A) varies across individuals as a power function of exponent 0.915 of neuronal density. Each point represents the values for each of 20 individuals of the 10 species analyzed.