OBJECTIVE: This study aimed to define a set of clinicoradiological parameters with a high specificity for the diagnosis of intraneural perineurioma, obviating the need for operative tissue diagnosis.METHODS: The authors retrospectively reviewed MR images obtained in a large cohort of patients who underwent targeted fascicular biopsy and included only those patients for whom the biopsy yielded a diagnosis. Clinical and radiological findings were then tested for their ability to predict a tissue diagnosis of intraneural perineurioma. The authors propose a new set of diagnostic criteria, referred to as the Perineurioma Diagnostic Criteria. The sensitivity, specificity, positive predictive value, and negative predictive value of several clinicoradiological methods of diagnosis were compared.RESULTS: A total of 195 patients who underwent targeted fascicular biopsy were included in the cohort, of whom 51 had a tissue diagnosis of intraneural perineurioma. When the clinicoradiological methods used in this study were compared, the highest sensitivity (0.86), negative predictive value (0.95), and F1 score (0.88) were observed for the decision trees generated in C5.0 and rPart, whereas the highest specificity (1.0) and positive predictive value (1.0) were observed for the Perineurioma Diagnostic Criteria.CONCLUSIONS: This study identified clinical and radiological features that are associated with a diagnosis of perineurioma. The Perineurioma Diagnostic Criteria were determined to be the following: 1) no cancer history, 2) unifocal disease, 3) moderate to severe hyperintensity on T2-weighted MR images, 4) moderate to severe contrast enhancement, 5) homogeneous contrast enhancement, 6) fusiform shape, 7) enlargement of the involved nerves, and 8) age ≤ 40 years. Use of the Perineurioma Diagnostic Criteria obviates the need for tissue diagnosis when all of the criteria are satisfied.
Non-invasive differentiation between schwannomas and neurofibromas is important for appropriate management, preoperative counseling, and surgical planning, but has proven difficult using conventional imaging. The objective of this study was to develop and evaluate machine learning approaches for differentiating peripheral schwannomas from neurofibromas. We assembled a cohort of schwannomas and neurofibromas from 3 independent institutions and extracted high-dimensional radiomic features from gadolinium-enhanced, T1-weighted MRI using the PyRadiomics package on Quantitative Imaging Feature Pipeline. Age, sex, neurogenetic syndrome, spontaneous pain, and motor deficit were recorded. We evaluated the performance of 6 radiomics-based classifier models with and without clinical features and compared model performance against human expert evaluators. One hundred and seven schwannomas and 59 neurofibromas were included. The primary models included both clinical and imaging data. The accuracy of the human evaluators (0.765) did not significantly exceed the no-information rate (NIR), whereas the Support Vector Machine (0.929), Logistic Regression (0.929), and Random Forest (0.905) classifiers exceeded the NIR. Using the method of DeLong, the AUCs for the Logistic Regression (AUC = 0.923) and K Nearest Neighbor (AUC = 0.923) classifiers were significantly greater than the human evaluators (AUC = 0.766; p = 0.041). The radiomics-based classifiers developed here proved to be more accurate and had a higher AUC on the ROC curve than expert human evaluators. This demonstrates that radiomics using routine MRI sequences and clinical features can aid in differentiation of peripheral schwannomas and neurofibromas.
1 February 2019 in Journal of Trauma and Acute Care Surgery
Acute nerve injuries are routinely encountered in multisystem trauma patients. Advances in surgical treatment of nerve injuries now mean that good outcomes can be achieved. Despite this, old mantras associated with management of nerve injuries, including “wait a year to see if recovery occurs” and “there's nothing we can do”, persist. Practicing by these mantras places these patients at a disadvantage. Changes begin to occur in the nerve, neuromuscular junction, and muscle from the moment a nerve injury occurs. These changes can become irreversible approximately 18 to 24 months following denervation. Thus, it is a race to reestablish a functional nerve-muscle connection before these irreversible changes. Good outcomes rely on appropriate acute management and avoiding delays in care. Primary nerve surgery options include direct primary repair, nerve graft repair, and nerve transfer. Acute management of nerve injuries proceeds according to the rule of 3's and requires early cooperation between trauma surgeons who recognize the nerve injury and consultant nerve surgeons. Care of patients with acute traumatic nerve injuries should not be delayed. Awareness of current management paradigms among trauma surgeons will help facilitate optimal upfront management. With the ever-expanding surgical options for management of these injuries and the associated improvement of outcomes, early multidisciplinary approaches to these injuries have never been more important. Old mantras must be replaced with new paradigms to continue to see improvements in outcomes for these patients. The importance of this review is to raise awareness among trauma surgeons of new paradigms for management of traumatic nerve injuries.
29 December 2014 in Journal of Neurological Surgery Part A: Central European Neurosurgery
Objective We hypothesized that the subset of patients with early hydrocephalus following aneurysmal subarachnoid hemorrhage may represent a subset of patients with a more vehement inflammatory reaction to blood products in the subarachnoid space. We thus examined risk factors for early hydrocephalus and examined the relationship between early hydrocephalus and symptomatic vasospasm as well as clinical outcome. Methods We retrospectively analyzed all patients presenting to our institution with subarachnoid hemorrhage over a 7-year period. We examined for risk factors, including early hydrocephalus, for poor clinical outcome and symptomatic vasospasm. Results We found intraventricular hemorrhage to be strongly associated with the development of early hydrocephalus. In univariate analysis, early hydrocephalus was strongly associated with both poor functional outcome and symptomatic vasospasm. In multivariate analysis, intraventricular hemorrhage and tobacco use were associated with symptomatic vasospasm; intraventricular hemorrhage, intraparenchymal hemorrhage, and symptomatic vasospasm were associated with poor functional outcome. Conclusions We found that intraventricular hemorrhage was strongly associated with early hydrocephalus. Further exploration of the mechanistic explanation is needed, but we suggest this may be from a combination of obstruction of cerebrospinal fluid pathways by blood products and inflammation in the choroid plexus resulting in increased cerebrospinal fluid production. Further, we suggest that both early hydrocephalus and cerebral vasospasm may be parts of the overall inflammatory cascade that occurs with intraventricular hemorrhage and ultimately results in a poorer clinical outcome.