BACKGROUND Clinicoradiologic differentiation between benign and malignant peripheral nerve sheath tumors (PNSTs) has important management implications. OBJECTIVE To develop and evaluate machine-learning approaches to differentiate benign from malignant PNSTs. METHODS We identified PNSTs treated at 3 institutions and extracted high-dimensional radiomics features from gadolinium-enhanced, T1-weighted magnetic resonance imaging (MRI) sequences. Training and test sets were selected randomly in a 70:30 ratio. A total of 900 image features were automatically extracted using the PyRadiomics package from Quantitative Imaging Feature Pipeline. Clinical data including age, sex, neurogenetic syndrome presence, spontaneous pain, and motor deficit were also incorporated. Features were selected using sparse regression analysis and retained features were further refined by gradient boost modeling to optimize the area under the curve (AUC) for diagnosis. We evaluated the performance of radiomics-based classifiers with and without clinical features and compared performance against human readers. RESULTS A total of 95 malignant and 171 benign PNSTs were included. The final classifier model included 21 imaging and clinical features. Sensitivity, specificity, and AUC of 0.676, 0.882, and 0.845, respectively, were achieved on the test set. Using imaging and clinical features, human experts collectively achieved sensitivity, specificity, and AUC of 0.786, 0.431, and 0.624, respectively. The AUC of the classifier was statistically better than expert humans (P = .002). Expert humans were not statistically better than the no-information rate, whereas the classifier was (P = .001). CONCLUSION Radiomics-based machine learning using routine MRI sequences and clinical features can aid in evaluation of PNSTs. Further improvement may be achieved by incorporating additional imaging sequences and clinical variables into future models.
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 107 schwannomas and 59 neurofibroma 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 AUC for the Logistic Regression (AUC=0.923) and K Nearest Neighbor (AUC=0.923) classifiers was 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.
No abstract
Opioids produce profound and diverse effects on a range of behaviors, many driven by brainstem activity; however, the presence of opioid and opioid-like receptors at this level has been poorly studied outside of nociceptive structures and components of respiratory circuitry. While previous studies identified expression of these receptors in the brainstem, patterns have not been fully delineated and neither has coexpression of receptors nor the behavioral implications of their expression in most structures. We aimed to elucidate expression of all four receptors across somatosensory-motor, auditory, and respiratory brainstem circuits; identify recurring themes to provide insight into the mechanisms by which exogenous opioids affect broader brainstem circuits; and characterize the function of endogenous opioids in subcortical processing and behavior modulation. Using a fluorescent reporter mouse line for each receptor, we created a three-dimensional, comprehensive atlas of brainstem receptor distribution and identified novel expression patterns in modality-specific circuits. Each receptor showed unique expression patterns across the brainstem with minimal correlation between receptors. Orofacial somatosensory-motor circuits expressed all four receptors, though generally in distinct nuclei, suggesting differential opiate modulation of afferent and efferent trigeminal signaling. Within the auditory circuit, receptors segregated along the vertical and horizontal processing pathways with minimal colocalization. Finally, the respiratory circuit strongly expressed the μ opioid receptor in multiple crucial structures with minimal presence of the other three receptors. We further assessed the functional significance of this expression pattern in the respiratory circuitry by characterization respiratory responses to selective opioid agonists, finding that each agonist caused unique alterations in breathing pattern and/or breath shape. Together, the results establish a comprehensive atlas of opioid and opioid-like receptor expression throughout the brainstem, laying the essential groundwork for further evaluation of opioid neuromodulation across the spectrum of behaviors.
BACKGROUND Wyburn-Mason syndrome (WMS) is a neurocutaneous disorder consisting of vascular malformations of the brain, eye, and skin. These include characteristically high-flow intracranial and intraorbital arteriovenous malformations (AVMs) that present commonly with visual deterioration, headache, and hemiplegia. Complete removal of these lesions is challenging. Most patients are followed closely, and intervention occurs only in the setting of worsening symptoms secondary to AVM growth or hemorrhage. Here the authors present the first known case of a patient with WMS and a pituitary macroadenoma. OBSERVATIONS A 62-year-old man with a 30-year history of WMS with right basal ganglia and orbital AVMs and right eye blindness presented for new-onset left-sided vision loss. A pituitary adenoma was identified compressing the optic chiasm and left optic nerve. Magnetic resonance imaging and digital subtraction angiography studies were obtained for surgical planning, and the patient underwent an endoscopic transnasal transsphenoidal resection, with significant postoperative vision improvement. LESSONS Given the variable presentation and poor characterization of this rare syndrome, patients with WMS presenting with new symptoms must undergo evaluation for growth and hemorrhage of known AVMs, as well as new lesions. Further, in patients undergoing intracranial surgery, extensive preoperative imaging and planning are crucial for safe and successful procedures.
PURPOSE/OBJECTIVE(S) Brain metastases from thyroid carcinoma are rare. Although stereotactic radiosurgery (SRS) is a standard of care for patients with brain metastases across many histologies, the current NCCN guidelines do not support a universal role for this modality in thyroid cancer. MATERIALS AND METHODS Thyroid cancer patients with brain metastases treated with radiotherapy at our institution from 2002-2020 were studied. Cumulative risk of local failure, distant intracranial failure and radiation necrosis were calculated using a competing risk of death analysis and censored at the last imaging follow-up. Overall survival was analyzed using Kaplan-Meier method. Stratified cox regression was used to study per-lesion outcomes. RESULTS We identified 34 patients with 203 treated brain metastases. 179 (88.2%) lesions were of differentiated histology; the remainder were anaplastic histology. Four patients received whole brain radiotherapy (WBRT) while 30 patients received SRS (SFED 22, interquartile (IQ) range 20-22). Of the patients receiving WBRT, one (25%) had anaplastic histology, and the median number of lesions was 15 (as compared to 2 for SRS). Median follow up among survivors was 32.3 months and median survival was 10.8 months. There were no observed failures (local or distant intracranial) observed at 1 year in the 24 metastases with anaplastic histology, although competing risk of death was high (91.7%). The 1 year cumulative incidences of local failure and distant intracranial failures were 9.8% (95CI 5.7%-13.9%) and 35.0% (95CI 29.0%-41.0%), respectively, in differentiated tumors. 6 (10.2%) of the distant intracranial failures were new cases of leptomeningeal disease. The 1 year risk of radiation necrosis was 15.5%. Of these cases, most were Grade 2 (57.1%); 3 (42.9%) were Grade 4 (there were no Grade 1 or 3 events). CONCLUSION In the largest known cohort of thyroid cancer brain metastasis patients, radiotherapy and SRS appear to be safe and effective treatment modalities.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.