OBJECTIVEAutomatic segmentation of vestibular schwannomas (VSs) from MRI could significantly improve clinical workflow and assist in patient management. Accurate tumor segmentation and volumetric measurements provide the best indicators to detect subtle VS growth, but current techniques are labor intensive and dedicated software is not readily available within the clinical setting. The authors aim to develop a novel artificial intelligence (AI) framework to be embedded in the clinical routine for automatic delineation and volumetry of VS.METHODSImaging data (contrast-enhanced T1-weighted [ceT1] and high-resolution T2-weighted [hrT2] MR images) from all patients meeting the study’s inclusion/exclusion criteria who had a single sporadic VS treated with Gamma Knife stereotactic radiosurgery were used to create a model. The authors developed a novel AI framework based on a 2.5D convolutional neural network (CNN) to exploit the different in-plane and through-plane resolutions encountered in standard clinical imaging protocols. They used a computational attention module to enable the CNN to focus on the small VS target and propose a supervision on the attention map for more accurate segmentation. The manually segmented target tumor volume (also tested for interobserver variability) was used as the ground truth for training and evaluation of the CNN. We quantitatively measured the Dice score, average symmetric surface distance (ASSD), and relative volume error (RVE) of the automatic segmentation results in comparison to manual segmentations to assess the model’s accuracy.RESULTSImaging data from all eligible patients (n = 243) were randomly split into 3 nonoverlapping groups for training (n = 177), hyperparameter tuning (n = 20), and testing (n = 46). Dice, ASSD, and RVE scores were measured on the testing set for the respective input data types as follows: ceT1 93.43%, 0.203 mm, 6.96%; hrT2 88.25%, 0.416 mm, 9.77%; combined ceT1/hrT2 93.68%, 0.199 mm, 7.03%. Given a margin of 5% for the Dice score, the automated method was shown to achieve statistically equivalent performance in comparison to an annotator using ceT1 images alone (p = 4e−13) and combined ceT1/hrT2 images (p = 7e−18) as inputs.CONCLUSIONSThe authors developed a robust AI framework for automatically delineating and calculating VS tumor volume and have achieved excellent results, equivalent to those achieved by an independent human annotator. This promising AI technology has the potential to improve the management of patients with VS and potentially other brain tumors.

There is renewed interest in film dosimetry for the verification of dose delivery of complex treatments, particularly small fields, compared to treatment planning system calculations. A new radiochromic film, Gafchromic EBT-XD, is available for high-dose treatment verification and we present the first published evaluation of its use. We evaluate the new film for MV photon dosimetry, including calibration curves, performance with single- and triple-channel dosimetry, and comparison to existing EBT3 film. In the verification of a typical 25 Gy stereotactic radiotherapy (SRS) treatment, compared to TPS planned dose distribution, excellent agreement was seen with EBT-XD using triple-channel dosimetry, in isodose overlay, maximum 1.0 mm difference over 200-2400 cGy, and gamma evaluation, mean passing rate 97% at 3% locally-normalised, 1.5 mm criteria. In comparison to EBT3, EBT-XD gave improved evaluation results for the SRS-plan, had improved calibration curve gradients at high doses, and had reduced lateral scanner effect. The dimensions of the two films are identical. The optical density of EBT-XD is lower than EBT3 for the same dose. The effective atomic number for both may be considered water-equivalent in MV radiotherapy. We have validated the use of EBT-XD for high-dose, small-field radiotherapy, for routine QC and a forthcoming multi-centre SRS dosimetry intercomparison.

Automatic segmentation of vestibular schwannoma (VS) tumors from magnetic resonance imaging (MRI) would facilitate efficient and accurate volume measurement to guide patient management and improve clinical workflow. The accuracy and robustness is challenged by low contrast, small target region and low through-plane resolution. We introduce a 2.5D convolutional neural network (CNN) able to exploit the different in-plane and through-plane resolutions encountered in standard of care imaging protocols. We use an attention module to enable the CNN to focus on the small target and propose a supervision on the learning of attention maps for more accurate segmentation. Additionally, we propose a hardness-weighted Dice loss function that gives higher weights to harder voxels to boost the training of CNNs. Experiments with ablation studies on the VS tumor segmentation task show that: 1) the proposed 2.5D CNN outperforms its 2D and 3D counterparts, 2) our supervised attention mechanism outperforms unsupervised attention, 3) the voxel-level hardness-weighted Dice loss can improve the performance of CNNs. Our method achieved an average Dice score and ASSD of 0.87 and 0.43 mm respectively. This will facilitate patient management decisions in clinical practice.