Neuroanatomic Markers of Posttraumatic Epilepsy Based on MR Imaging and Machine Learning.

BACKGROUND AND PURPOSE: Although posttraumatic epilepsy is a common complication of traumatic brain injury, the relationship between these conditions is unclear and early posttraumatic epilepsy detection and prevention remain major unmet clinical challenges. This study aimed to identify imaging biomarkers that predict posttraumatic epilepsy among survivors of traumatic brain injury on the basis of an MR imaging data set. MATERIALS AND METHODS: We performed tensor-based morphometry to analyze brain-shape changes associated with traumatic brain injury and to derive imaging features for statistical group comparison. Additionally, machine learning was used to identify structural anomalies associated with brain lesions. Automatically generated brain lesion maps were used to identify brain regions where lesion load may indicate an increased incidence of posttraumatic epilepsy. We used 138 non-posttraumatic epilepsy subjects for training the machine learning method. Validation of lesion delineation was performed on 15 subjects. Group analysis of the relationship between traumatic brain injury and posttraumatic epilepsy was performed on an independent set of 74 subjects (37 subjects with and 37 randomly selected subjects without epilepsy). RESULTS: We observed significant F-statistics related to tensor-based morphometry analysis at voxels close to the pial surface, which may indicate group differences in the locations of edema, hematoma, or hemorrhage. The results of the F-test on lesion data showed significant differences between groups in both the left and right temporal lobes. We also saw significant differences in the right occipital lobe and cerebellum. CONCLUSIONS: Statistical analysis suggests that lesions in the temporal lobes, cerebellum, and the right occipital lobe are associated with an increased posttraumatic epilepsy incidence.

Perfusion and permeability MR imaging of gliomas.

Conventional contrast-enhanced MR imaging is the current standard technique for the diagnosis and treatment evaluation of gliomas and other brain neoplasms. However, this method is quite limited in its ability to characterize the complex biology of gliomas and so there is a need to develop more quantitative imaging methods. Perfusion and permeability MR imaging are two such techniques that have shown promise in this regard. This review will highlight the underlying principles, applications, and pitfalls of these evolving advanced MRI methods.

The trigeminal nerve.

The trigeminal nerve is the largest of the cranial nerves, serving as a major conduit for sensory information from the head and neck and primarily providing motor innervation to the muscles of mastication. An understanding of the pathologic processes that may involve this nerve requires a detailed knowledge of its origin within the brain stem as well as its course intracranially. This article describes the neuroanatomy of the nerve and divides it into its various segments to provide a differential diagnosis of common and some uncommon pathologic processes.

Imaging of neurocysticercosis.

Neurocysticercosis produces a variety of neurologic syndromes resulting from the cysticerci infestation of the central nervous system by the larvae of Taenia solium. Because of increased immigration to the United States from endemic areas, the incidence of neurocysticercosis has increased, especially in California, Texas, Arizona, and other southwestern states. Neuroimaging studies play a significant role in the diagnosis and management of patients with neurocysticercosis.

Fungal infections of the central nervous system.

The diagnosis and treatment of central nervous system fungal infections typically pose problems for the clinician. With an increased incidence of fungal infections in immunocompromised patients, neuroradiologic imaging has become essential in determining complications and outcomes. This article provides a summary of the more common organisms encountered in fungal infections of the central nervous system and the imaging features primarily seen with CT and MR imaging.

Association of invasive pneumococcal disease with season, atmospheric conditions, air pollution, and the isolation of respiratory viruses.

We examined the relation of invasive pneumococcal disease to season, atmospheric conditions, and the rate of respiratory virus isolation in a community-wide surveillance program in Houston. Among adults, the number of cases of pneumococcal bacteremia peaked in midwinter and declined strikingly in midsummer, indicating a high degree of inverse correlation with the ambient temperature. We detected significant correlations between the occurrence of pneumococcal disease and the isolation of respiratory syncytial virus (P < .001), influenza virus (P < .001), and all viruses except influenza virus (P < .001), as well as with air pollution, as measured by SO2 levels (P < .001). In contrast, the rate of invasive pneumococcal disease among infants and children was relatively more sustained from October through May, with a notable decrease in summer months; the incidence of pneumococcal disease was therefore less strongly correlated with cold weather and less closely associated with the isolation of respiratory syncitial virus or influenza virus. However, pneumococcal disease among infants and children was associated with isolation of these viruses after a 4-week lag period as well as with isolation of adenovirus and ragweed pollen counts. The finding, with regard to children, that correlations tended to be stronger for events that occurred 1 month previously than for those that occurred contemporaneously is consistent with the concept that viral or allergic events predispose to otitis media with effusion, which becomes suppurative and leads to pneumococcal bacteremia or meningitis. For adults, a more immediate predisposition to pneumococcal pneumonia and bacteremia because of viral infection or air pollution was suggested.

The radiologic evaluation of craniocerebral missile injuries.

A brief overview of the imaging findings in craniocerebral missile injury is presented here. CT scanning has established itself as the primary imaging modality for the complex injuries seen in CMI as well as its acute and delayed complications. Plain x-ray, angiography, and magnetic resonance imaging have more limited but sometimes important roles in the management of these injuries. With regard to outcome prediction, imaging has also proved to be of some, albeit limited, usefulness, primarily as adjuncts to clinical criteria such as the GCS. Future research with CT as well as magnetic resonance imaging will likely expand the clinical role of these modalities, particularly in the realm of outcome analysis.