Wilson, Thomas J

Abstract Background 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. Methods 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. Results 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). Conclusions 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.

A “perineal” branch of the sciatic nerve has been visualized during surgery, but there is currently no description of this nerve branch in the literature. Our study investigates the presence and frequency of occurrence of perineal innervation by the sciatic nerve and characterizes its anatomy in the posterior thigh. Fifteen cadavers were obtained for dissection. Descriptive results were recorded and analyzed statistically. Twenty‐one sciatic nerves were adequately anatomically preserved. Six sciatic nerves contained a perineal branch. Five sciatic nerves had a branch contributing to the perineal branch of the posterior femoral cutaneous (PFC) nerve. In specimens with adequate anatomical preservation, the perineal branch of the sciatic nerve passed posterior to the ischial tuberosity in three specimens and posterior to the conjoint tendon of the long head of biceps femoris and semitendinosus muscles (conjoint tendon) in one. In specimens in which the perineal branch of the PFC nerve received a contribution from the sciatic nerve, the branch passed posterior to the sacrotuberous ligament in one case and posterior to the conjoint tendon in three. Unilateral nerve anatomy was found to be a poor predictor of contralateral anatomy (Cohen's kappa = 0.06). Our study demonstrates for the first time the presence and frequency of occurrence of the perineal branch of the sciatic nerve and a sciatic contribution to the perineal branch of the PFC nerve. Clinicians should be cognizant of this nerve and its varying anatomy so their practice is better informed. Clin. Anat. 31:357–363, 2018. © 2018 Wiley Periodicals, Inc.