RESUMEN
Automatic segmentation of vestibular schwannoma (VS) from routine clinical MRI has potential to improve clinical workflow, facilitate treatment decisions, and assist patient management. Previous work demonstrated reliable automatic segmentation performance on datasets of standardized MRI images acquired for stereotactic surgery planning. However, diagnostic clinical datasets are generally more diverse and pose a larger challenge to automatic segmentation algorithms, especially when post-operative images are included. In this work, we show for the first time that automatic segmentation of VS on routine MRI datasets is also possible with high accuracy. We acquired and publicly release a curated multi-center routine clinical (MC-RC) dataset of 160 patients with a single sporadic VS. For each patient up to three longitudinal MRI exams with contrast-enhanced T1-weighted (ceT1w) (n = 124) and T2-weighted (T2w) (n = 363) images were included and the VS manually annotated. Segmentations were produced and verified in an iterative process: (1) initial segmentations by a specialized company; (2) review by one of three trained radiologists; and (3) validation by an expert team. Inter- and intra-observer reliability experiments were performed on a subset of the dataset. A state-of-the-art deep learning framework was used to train segmentation models for VS. Model performance was evaluated on a MC-RC hold-out testing set, another public VS datasets, and a partially public dataset. The generalizability and robustness of the VS deep learning segmentation models increased significantly when trained on the MC-RC dataset. Dice similarity coefficients (DSC) achieved by our model are comparable to those achieved by trained radiologists in the inter-observer experiment. On the MC-RC testing set, median DSCs were 86.2(9.5) for ceT1w, 89.4(7.0) for T2w, and 86.4(8.6) for combined ceT1w+T2w input images. On another public dataset acquired for Gamma Knife stereotactic radiosurgery our model achieved median DSCs of 95.3(2.9), 92.8(3.8), and 95.5(3.3), respectively. In contrast, models trained on the Gamma Knife dataset did not generalize well as illustrated by significant underperformance on the MC-RC routine MRI dataset, highlighting the importance of data variability in the development of robust VS segmentation models. The MC-RC dataset and all trained deep learning models were made available online.
RESUMEN
There have been anecdotal reports of vasculopathy associated with Neurofibromatosis Type 2 (NF2). Given the increasing use of bevacizumab, a vascular endothelial growth factor inhibitor which results in an increased risk of bleeding, it is important to ascertain if there is a predisposition to vascular abnormalities in NF2. In our unit NF2 patients undergo annual MRI brain and internal auditory meatus imaging. We noted incidental intracranial aneurysms in some patients and sought to determine the prevalence of intracranial aneurysms in our cohort of NF2 patients. We conducted a retrospective audit of the MRI images of 104 NF2 patients from 2014 to 2016. Axial T2 brain MRI images were assessed for vascular abnormalities by two neuroradiologists blinded to patient's clinical details. Intracranial aneurysms were detected in four patients and an aneurysm clip related to previous surgery was noted in one additional patient. Using standard MRI imaging sequences alone we provide evidence of intracranial aneurysms in 4.4% of our cohort. This compares with an estimated overall prevalence of 3% in the general population. We discuss these findings as well as other evidence for a vasculopathy associated with NF2.
