Rao, Vaishnavi

The legacy of Stanford University's Department of Neurosurgery began in 1858, with the establishment of a new medical school on the West Coast. Stanford Neurosurgery instilled an atmosphere of dedication to neurosurgical care, scientific research, education, and innovation. We highlight key historical events leading to the formation of the medical school and neurosurgical department, the individuals who shaped the department's vision and expansion, as well as pioneering advances in research and clinical care. The residency program was started in 1961, establishing the basis of the current education model with a strong emphasis on training future leaders, and the Moyamoya Center, founded in 1991, became the largest Moyamoya referral center in the United States. The opening of Stanford Stroke Center (1992) and seminal clinical trials resulted in a significant impact on cerebrovascular disease by expanding the treatment window of IV thrombolysis and intra-arterial thrombectomy. The invention and implementation of CyberKnife ® (1994) marks another important event that revolutionized the field of radiosurgery, and the development of Stanford's innovative Brain Computer Interface program is pushing the boundaries of this specialty. The more recent launch of the Neurosurgery Virtual Reality and Simulation Center (2017) exemplifies how Stanford is continuing to evolve in this ever-changing field. The department also became a model for diversity within the school as well as nationwide. The growth of Stanford Neurosurgery from one of the youngest neurosurgery departments in the country to a prominent comprehensive neurosurgery center mirrors the history of neurosurgery itself: young, innovative, and willing to overcome challenges.

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.