Multiple parietal-frontal pathways mediate grasping in macaque monkeys

Abstract

The nodes of a parietal-frontal pathway that mediates grasping in primates are in anterior intraparietal area (AIP) and ventral premotor cortex (PMv). Nevertheless, multiple somatosensory and motor representations of the hand, in parietal and frontal cortex, respectively, suggest that additional pathways remain unrealized. We explored this possibility in macaque monkeys by injecting retrograde tracers into grasp zones identified in primary motor cortex (M1), PMv, and area 2 with long train electrical stimulation. The M1 grasp zone was densely connected with other frontal cortex motor regions. The remainder of the connections originated from somatosensory areas 3a and second somatosensory cortex/parietal ventral area (S2/PV), and from the medial bank and fundus of the intraparietal sulcus (IPS). The PMv grasp zone was also densely connected with frontal cortex motor regions, albeit to a lesser extent than the M1 grasp zone. The remainder of the connections originated from areas S2/PV and aspects of the inferior parietal lobe such as PF, PFG, AIP, and the tip of the IPS. The area 2 grasp zone was densely connected with the hand representations of somatosensory areas 3b, 1, and S2/PV. The remainder of the connections was with areas 3a and 5 and the medial bank and fundus of the IPS. Connections with frontal cortex were relatively weak and concentrated in caudal M1. Thus, the three grasp zones may be nodes of parallel parietal-frontal pathways. Differential points of origin and termination of each pathway suggest varying functional specializations. Direct and indirect connections between those parietal-frontal pathways likely coordinate their respective functions into an accurate grasp.

Figure 1.

Select stages of flattening the frontal and parietal cortex from the left hemisphere of a macaque monkey brain. A, Medial and dorsolateral views of the left hemisphere. B, The medial and lateral banks of the intraparietal sulcus are partially separated from one another. The rostral and caudal banks of the inferior arcuate sulcus are also partially separated from one another. The upper bank and fundus of the lateral sulcus are separated from the lower bank. C, The occipital lobe and most of the temporal lobe are removed. D, The banks of the intraparietal sulcus and the arcuate sulcus are further separated. The rostral and caudal banks of the central sulcus are partially separated. The medial wall and the insular cortex are unfolded. Most of the prefrontal cortex is removed and the remaining banks of the principal sulcus are separated. E, The cortex is blocked into two pieces, which are flattened between two glass slides. The top block includes most of the medial wall. Scale bar applies to all panels. Abbreviations are described in Table 1.

Figure 2.

Representative sections of the cortex shown in Figure 1E after staining for cytochrome oxidase (A) and myelinated fibers (B). The solid white lines represent cortical borders apparent in the preset sections. The dashed white lines represent less apparent cortical borders. The solid gray lines represent the lips of sulci, and the dashed gray lines represent the fundi of the sulci. Abbreviations are described in Table 1.

Figure 3.

Photomicrographs of tracer injection sites in cortex (top panels) and examples of the corresponding cells labeled in cortex (bottom panels). Images were captured with a digital camera mounted onto a light microscope to show cholera toxin B subunit (A), or a fluorescent microscope to show Fluoro Ruby (B), Fast Blue (C), and Diamidino Yellow (D). The inner dashed outline marks the core of each tracer injection, whereas the surrounding dashed outline marks a halo of intense tracer diffusion. Examples of labeled cells (arrowheads) are in E–H, which were sampled from the same cortical section as the panel directly above it. Scale bars: A–D, 250 μm; E–H, 50 μm. Contrast was digitally enhanced in all panels to improve illustration.

Figure 4.

Sequential still frames captured from a video recording of a grasp evoked in the right hand with long train electrical stimulation in the contralateral PMv. A, Hand posture before electrical stimulation. B–E, Successive hand postures after ∼50, 83, 117, and 150 ms of electrical stimulation.

Figure 5.

Maps of movements evoked with long train electrical stimulation (each train is comprised of 150 biphasic pulses delivered over 500 ms) aligned to the respective flattened cortex (A–D). Microelectrode penetration sites are color-coded to reflect evoked movements. Dual movements are represented in two colors. Each Hamilton syringe represents the location of a tracer injection including CTB, FR, DY, and FB. The solid black lines represent cortical borders identified from adjacent sections stained for cytochrome oxidase and myelinated fibers. The solid gray lines mark different banks of sulci. The border between motor M1, PMd, and PMv was estimated from current thresholds for evoking movements and is marked with a dashed black line. Receptive fields were mapped in cases 10-29 and 09-51 with multiunit recordings. In both cases, the territories mapped were between area 1 and the medial bank of the intraparietal sulcus. In case 09-51, the solid line separating areas 2 and 5 represents the mediolateral extent of the mapped territory. The remainder of this border was estimated from architectonic results and is represented by a dashed black line. Scale bar: A–D, 5 mm. E, The yellow box on the dorsolateral view of a macaque brain shows the approximate area of cortex in A–D. F, Legend for the motor maps.

Figure 6.

The distributions of cells labeled from a DY injection into the M1 grasp zone (blue) and a CTB injection into the PMv grasp zone (red). Each filled circle represents a labeled cell. Injection cores are represented in light blue and pink to facilitate identification from dense concentrations of labeled cells. The illustration is a composite of multiple flattened sections that were aligned according to the locations of blood vessels, tissue artifact, and microlesions. Cells labeled from the PMv injection completely obscure the PMv grasp zone; cross-reference the map in Figure 5A. The distributions of the two cell populations were similar in frontal cortex, but they were largely segregated in parietal cortex. The cortical borders of areas 3a, 3b, 1, were readily apparent from architectonic sections and are marked with solid black lines. Receptive field mapping confirmed the borders of areas 1 and 2. The solid line separating areas 2 and 5 represents the mediolateral extent of receptive field mapping. The medial and lateral extensions of this border were estimated from architectonic sections and are represented with dashed lines. The border separating M1 from premotor cortex was estimated from current thresholds for evoking movements with electrical stimulation and is marked with a dashed line. The lips of sulci are represented as solid gray lines, whereas the fundi are represented as dashed gray lines.

Figure 7.

The distributions of cells labeled from a FR injection into the M1 grasp zone (blue) and a CTB injection into the PMv grasp zone (red). Cells labeled from the PMv injection completely obscure the PMv grasp zone; cross-reference the map in Figure 5B. The distributions of the two cell populations were similar in frontal cortex, but they were largely segregated in parietal cortex. The cortical borders of areas 3a, 3b, 1, and 2 were readily apparent from architectonic sections and are marked with solid black lines. The border separating M1 from premotor cortex was estimated from current thresholds for evoking movements with electrical stimulation and is marked with a dashed line. The lips of sulci are represented as solid gray lines, whereas the fundi are represented as dashed gray lines.

Figure 8.

The distributions of cells labeled from a CTB injection into the M1 grasp zone (blue) and a FR injection into the area 2 grasp zone (red). Cells labeled from the M1 grasp injection obscure most of the M1 grasp zone; cross-reference the map in Figure 5C. The two cell populations intermingled in caudal aspects of M1, PFG, and S2/PV, but were otherwise spatially segregated. The cortical borders of areas 3a, 3b, and 1 were readily apparent from architectonic sections and are marked with solid black lines. Receptive field mapping confirmed the borders of areas 1 and 2. The solid line separating areas 2 and 5 represents the mediolateral extent of receptive field mapping. The medial extension of this border was estimated from architectonic sections and is represented as a dashed line. The border separating M1 from premotor cortex was estimated from current thresholds for evoking movements with electrical stimulation and is marked with a dashed line. The lips of sulci are represented as solid gray lines, whereas the fundi are represented as dashed gray lines.

Figure 9.

The distributions of cells labeled from a FB injection into the M1 grasp zone (blue) and a CTB injection into the area 2 grasp zone (red). The two cell populations intermingled in the medial bank of the IPS, area 3a, caudal M1, PMv, and motor areas on the medial wall, but were otherwise spatially segregated. The cortical borders of areas 3a, 3b, and 1 were readily apparent from architectonic sections and are marked with solid black lines. The border separating M1 from premotor cortex was estimated from current thresholds for evoking movements with electrical stimulation and is marked with a dashed line. The lips of sulci are represented as solid gray lines, whereas the fundi are represented as dashed gray lines.

Figure 10.

The distributions of cells labeled from a DY injection into the M1 grasp zone (blue) and a FR injection into the M1 orofacial zone (red). The two cell populations intermingled in PMd, PMv, and SMA, but were otherwise spatially segregated. Conventions for cortical borders are the same as in Figure 6.

Figure 11.

The distributions of cells labeled from a CTB injection into the area 2 grasp zone (red) and a DY injection into area PFG in the inferior parietal lobe (blue). The two cell populations intermingled in the medial bank of the IPS and the upper bank of the lateral sulcus, but were otherwise spatially segregated. Conventions for cortical borders are the same as in Figure 9.

Figure 12.

The distributions of cells labeled from a FB injection into the M1 grasp zone (blue) and a DY injection into area PFG (red). The two cell populations intermingled in the medial bank of the IPS, upper and lower banks of the lateral sulcus, PMv, and the medial wall, but were otherwise spatially segregated. Conventions for cortical borders are the same as in Figure 9.

Figure 13.

Summary of the main sensory and motor connections for three grasp zones (gray zones) in M1 (A), PMv (B), and area 2 (C). Flattened cortical sections were cropped to focus on frontal and parietal cortex. The thickness of each arrow is proportional to the mean density of the connection and was calculated from the values in Tables 2 and 3. Illustrations are limited to connections that formed at least 1% of the total connections of a given zone. Scale bar: 5 mm (applies to all panels).

Figure 14.

Summary of the parietal–frontal pathways identified for the three grasp zones (gray zones). The flattened cortical section was cropped to focus on frontal and parietal cortex. The thickness of each arrow is proportional to the density of the connections. The PMv grasp zone was densely connected with parietal cortex; connections were primarily with rostral aspects of the lateral bank of the intraparietal sulcus and adjacent cortex in the inferior parietal lobe. The M1 grasp zone was moderately connected with parietal cortex; connections were primarily with the medial bank of the intraparietal sulcus and adjacent area 5. The area 2 grasp zone was sparsely connected with frontal cortex; connections were primarily with caudal aspects of M1 in the rostral bank of the central sulcus.