Early nonischemic oxidative metabolic dysfunction leads to chronic brain atrophy in traumatic brain injury

Abstract

Chronic brain atrophy after traumatic brain injury (TBI) is a well-known phenomenon, the causes of which are unknown. Early nonischemic reduction in oxidative metabolism is regionally associated with chronic brain atrophy after TBI. A total of 32 patients with moderate-to-severe TBI prospectively underwent positron emission tomography (PET) and volumetric magnetic resonance imaging (MRI) within the first week and at 6 months after injury. Regional lobar assessments comprised oxidative metabolism and glucose metabolism. Acute MRI showed a preponderance of hemorrhagic lesions with few irreversible ischemic lesions. Global and regional chronic brain atrophy occurred in all patients by 6 months, with the temporal and frontal lobes exhibiting the most atrophy compared with the occipital lobe. Global and regional reduction in cerebral metabolic rate of oxygen (CMRO(2)), cerebral blood flow (CBF), oxygen extraction fraction (OEF), and cerebral metabolic rate of glucose were observed. The extent of metabolic dysfunction was correlated with the total hemorrhage burden on initial MRI (r=0.62, P=0.01). The extent of regional brain atrophy correlated best with CMRO(2) and CBF. Lobar values of OEF were not in the ischemic range and did not correlate with chronic brain atrophy. Chronic brain atrophy is regionally specific and associated with regional reductions in oxidative brain metabolism in the absence of irreversible ischemia.

Figure 1

Comparison of coregistered acute MRI and PET images used for analysis. Regions of interest (ROIs) for each lobe were hand drawn for PET and MRI. An example of a single-slice ROI of the frontal lobe was drawn on the cerebral blood flow image to exclude the contusion on the left. CMRO₂, cerebral oxidative rate of oxygen; OEF, oxygen extraction fraction; CBF, cerebral blood flow; CMRG, cerebral metabolic rate of glucose.

Figure 2

Example of ROI drawing for volume analysis. A two-example series of manual ROIs drawn using a stereotactic atlas (A, B) is shown. An overlapping cascade of frontal lobe ROIs drawn in the same patient outlined in Figure 1, with the orientation of superior to inferior as the images move from left to right. The acute scan is shown in panel A and the chronic scan in panel B.

Figure 3

Example of structural lesion characterization: Two different patients are shown (A–F) and (G–L). Two separate axial slices per subject are shown with three image sequences per axial slice consisting of the DTI (left), DTA-ADC (middle), and GRE (right) in each sequence (panels A–F). The top row shows that the single patient had evidence of DTI-ADC hypointense (black arrowhead) and diffusion-weighted hyperintense lesions (black arrow) in the absence of obvious hemorrhage (panels C, F). The bottom row (E–H) shows an example of a patient with diffuse hemorrhagic lesions (white arrowhead) that colocalize with ADC (white arrow) and DWI areas. In 31 of 32 patients, DTI diffusion lesions were uniformly colocalized with GRE lesions as in panels G–L.

Figure 4

Example of chronic brain atrophy: Three-dimensional rendering of skull-stripped SPGR MRI T1 image in an example patient. The top row shows the acute MRI and the bottom row shows the chronic MRI at 6 months after trauma. The widespread atrophy, sulcal enlargement, and ventricular enlargement must be noted.

Figure 5

Correlations between CMRO₂ and atrophy in the temporal (A), frontal (B), and parietal lobes (C); between CBF and atrophy in the temporal (D), frontal (E), and parietal lobes (F); and between CMRglc and atrophy in the frontal lobe (G). The solid elliptical circles indicate the 50% confidence interval, and the dashed elliptical circle indicates the 99% confidence interval of the correlation coefficient.