27 September 2017 in Journal of NeuroInterventional Surgery
Stroke is a leading cause of long-term disability, and outcome is directly related to timely intervention. Not all patients benefit from rapid intervention, however. Thus a significant amount of attention has been paid to using neuroimaging to assess potential benefit by identifying areas of ischemia that have not yet experienced cellular death. The perfusion–diffusion mismatch, is used as a simple metric for potential benefit with timely intervention, yet penumbral patterns provide an inaccurate predictor of clinical outcome. Machine learning research in the form of deep learning (artificial intelligence) techniques using deep neural networks (DNNs) excel at working with complex inputs. The key areas where deep learning may be imminently applied to stroke management are image segmentation, automated featurization (radiomics), and multimodal prognostication. The application of convolutional neural networks, the family of DNN architectures designed to work with images, to stroke imaging data is a perfect match between a mature deep learning technique and a data type that is naturally suited to benefit from deep learning’s strengths. These powerful tools have opened up exciting opportunities for data-driven stroke management for acute intervention and for guiding prognosis. Deep learning techniques are useful for the speed and power of results they can deliver and will become an increasingly standard tool in the modern stroke specialist’s arsenal for delivering personalized medicine to patients with ischemic stroke.
1 June 2019 in World Neurosurgery
1 April 2017 in World Neurosurgery
1 August 2017 in World Neurosurgery
28 August 2024 in Interventional Neuroradiology
Background: Endovascular embolization is an adjunct to meningioma resection. Isolating the effectiveness of embolization is difficult as MR imaging is typically performed before embolization and after resection, and volumetric assessment of embolization on 2D angiographic imaging is challenging. We investigated the correlation between 2D angiographic and 3D MR measurements of meningioma devascularization following embolization. Methods: We implemented a protocol for postembolization, preresection MRI. Angiographic devascularization was graded according to reduction of tumor blush from 1 (partial embolization) to 4 (complete embolization with no residual circulation supply). Volumetric extent of embolization was quantified as the percent of tumor contrast enhancement lost following embolization. Tumor embolization was analyzed according to tumor location and vascular supply. Results: Thirty consecutive patients met inclusionary criteria. Grade 1 devascularization was achieved in 7% of patients, grade 2 in 43%, grade 3 in 20%, and grade 4 in 30%. Average extent of embolization was 37 ± 6%. Extent of tumor embolization was low (75%) in 20% of patients. Convexity, parasagittal/falcine and sphenoid wing tumors were found to have distinct vascular supply patterns and extent of embolization. Angiographic devascularization grade was significantly correlated with volumetric extent of tumor embolization ( p < 0.001, r = 0.758). Conclusion: This is the first study to implement postembolization, preoperative MRI to assess extent of embolization prior to meningioma resection. The study demonstrates that volumetric assessment of contrast reduction following embolization provides a quantitative and spatially resolved framework for assessing extent of tumor embolization.
1 March 2018 in World Neurosurgery