IntuitivePlan inverse planning performance evaluation for Gamma Knife radiosurgery of AVMs.

PURPOSE: To compare planning indices achieved using manual and inverse planning approaches for Gamma Knife radiosurgery of arterio-venous malformations (AVMs). METHODS AND MATERIALS: For a series of consecutive AVM patients, treatment plans were manually created by expert planners using Leksell GammaPlan (LGP). Patients were re-planned using a new commercially released inverse planning system, IntuitivePlan. Plan quality metrics were calculated for both groups of plans and compared. RESULTS: Overall, IntuitivePlan created treatment plans of similar quality to expert planners. For some plan quality metrics statistically significant higher scores were achieved for the inversely generated plans (Coverage 96.8% vs 96.3%, P = 0.027; PCI 0.855 vs 0.824, P = 0.042), but others did not show statistically significant differences (Selectivity 0.884 vs 0.856, P = 0.071; GI 2.85 vs 2.76, P = 0.096; Efficiency Index 47.0% vs 48.1%, P = 0.242; Normal Brain V12 (cc) 5.81 vs 5.79, P = 0.497). Automatic inverse planning demonstrated significantly shorter planning times over manual planning (3.79 vs 11.58 min, P < 10-6 ) and greater numbers of isocentres (40.4 vs 10.8, P < 10-6 ), with an associated cost of longer treatment times (57.97 vs 49.52 min, P = 0.009). When planning and treatment time were combined, there was no significant difference in the overall time between the two methods (61.76 vs 61.10, P = 0.433). CONCLUSIONS: IntuitivePlan can offer savings on the labor of treatment planning. In many cases, it achieves higher quality indices than those achieved by an "expert planner".

Benchmarking Tests of Contemporary SRS Platforms: Have Technological Developments Resulted in Improved Treatment Plan Quality?

PURPOSE: Stereotactic radiosurgery treatment delivery can be performed with a range of devices, each of which have evolved over recent years. We sought to evaluate the differences in performance of contemporary stereotactic radiosurgery platforms and also to compare them with earlier platform iterations from a previous benchmarking study. METHODS AND MATERIALS: The following platforms were selected as "state of the art" in 2022: Gamma Knife Icon (GK), CyberKnife S7 (CK), Brainlab Elements (Elekta VersaHD and Varian TrueBeam), Varian Edge with HyperArc (HA), and Zap-X. Six benchmarking cases were used from a 2016 study. To reflect the evolution of increasing numbers of metastases treated per patient, a 14-target case was added. The 28 targets among the 7 patients ranged from 0.02 to 7.2 cc in volume. Participating centers were sent images and contours for each patient and asked to plan them to the best of their ability. Although some variation in local practice was allowed (eg, margins), groups were asked to prescribe a specified dose to each target and tolerance doses to organs at risk were agreed upon. Parameters compared included coverage, selectivity, Paddick conformity index, gradient index (GI), R50%, efficiency index, doses to organs at risk, and planning and treatment times. RESULTS: Mean coverage for all targets ranged from 98.2% (Brainlab/Elekta) to 99.7% (HA-6X). Paddick conformity index values ranged from 0.722 (Zap-X) to 0.894 (CK). GI ranged from a mean of 3.52 (GK), representing the steepest dose gradient, to 5.08 (HA-10X). The GI appeared to follow a trend with beam energy, with the lowest values from the lower energy platforms (GK, 1.25 MeV; Zap-X, 3 MV) and the highest value from the highest energy (HA-10X). Mean R50% values ranged from 4.48 (GK) to 5.98 (HA-10X). Treatment times were lowest for C-arm linear accelerators. CONCLUSIONS: Compared with earlier studies, newer equipment appears to deliver higher quality treatments. CyberKnife and linear accelerator platforms appear to give higher conformity whereas lower energy platforms yield a steeper dose gradient.

ISRS Technical Guidelines for Stereotactic Radiosurgery: Treatment of Small Brain Metastases (≤1 cm in Diameter).

PURPOSE: The objective of this literature review was to develop International Stereotactic Radiosurgery Society (ISRS) consensus technical guidelines for the treatment of small, ≤1 cm in maximal diameter, intracranial metastases with stereotactic radiosurgery. Although different stereotactic radiosurgery technologies are available, most of them have similar treatment workflows and common technical challenges that are described. METHODS AND MATERIALS: A systematic review of the literature published between 2009 and 2020 was performed in Pubmed using the Preferred Reporting Items for Systematic Review and Meta-analyses (PRISMA) methodology. The search terms were limited to those related to radiosurgery of brain metastases and to publications in the English language. RESULTS: From 484 collected abstract 37 articles were included into the detailed review and bibliographic analysis. An additional 44 papers were identified as relevant from a search of the references. The 81 papers, including additional 7 international guidelines, were deemed relevant to at least one of five areas that were considered paramount for this report. These areas of technical focus have been employed to structure these guidelines: imaging specifications, target volume delineation and localization practices, use of margins, treatment planning techniques, and patient positioning. CONCLUSIONS: This systematic review has demonstrated that Stereotactic Radiosurgery (SRS) for small (1 cm) brain metastases can be safely performed on both Gamma Knife (GK) and CyberKnife (CK) as well as on modern LINACs, specifically tailored for radiosurgical procedures, However, considerable expertise and resources are required for a program based on the latest evidence for best practice.

Automated Koos Classification of Vestibular Schwannoma.

Objective: The Koos grading scale is a frequently used classification system for vestibular schwannoma (VS) that accounts for extrameatal tumor dimension and compression of the brain stem. We propose an artificial intelligence (AI) pipeline to fully automate the segmentation and Koos classification of VS from MRI to improve clinical workflow and facilitate patient management. Methods: We propose a method for Koos classification that does not only rely on available images but also on automatically generated segmentations. Artificial neural networks were trained and tested based on manual tumor segmentations and ground truth Koos grades of contrast-enhanced T1-weighted (ceT1) and high-resolution T2-weighted (hrT2) MR images from subjects with a single sporadic VS, acquired on a single scanner and with a standardized protocol. The first stage of the pipeline comprises a convolutional neural network (CNN) which can segment the VS and 7 adjacent structures. For the second stage, we propose two complementary approaches that are combined in an ensemble. The first approach applies a second CNN to the segmentation output to predict the Koos grade, the other approach extracts handcrafted features which are passed to a Random Forest classifier. The pipeline results were compared to those achieved by two neurosurgeons. Results: Eligible patients (n = 308) were pseudo-randomly split into 5 groups to evaluate the model performance with 5-fold cross-validation. The weighted macro-averaged mean absolute error (MA-MAE), weighted macro-averaged F1 score (F1), and accuracy score of the ensemble model were assessed on the testing sets as follows: MA-MAE = 0.11 ± 0.05, F1 = 89.3 ± 3.0%, accuracy = 89.3 ± 2.9%, which was comparable to the average performance of two neurosurgeons: MA-MAE = 0.11 ± 0.08, F1 = 89.1 ± 5.2, accuracy = 88.6 ± 5.8%. Inter-rater reliability was assessed by calculating Fleiss' generalized kappa (k = 0.68) based on all 308 cases, and intra-rater reliabilities of annotator 1 (k = 0.95) and annotator 2 (k = 0.82) were calculated according to the weighted kappa metric with quadratic (Fleiss-Cohen) weights based on 15 randomly selected cases. Conclusions: We developed the first AI framework to automatically classify VS according to the Koos scale. The excellent results show that the accuracy of the framework is comparable to that of neurosurgeons and may therefore facilitate management of patients with VS. The models, code, and ground truth Koos grades for a subset of publicly available images (n = 188) will be released upon publication.

Segmentation of vestibular schwannoma from MRI, an open annotated dataset and baseline algorithm.

Automatic segmentation of vestibular schwannomas (VS) from magnetic resonance imaging (MRI) could significantly improve clinical workflow and assist patient management. We have previously developed a novel artificial intelligence framework based on a 2.5D convolutional neural network achieving excellent results equivalent to those achieved by an independent human annotator. Here, we provide the first publicly-available annotated imaging dataset of VS by releasing the data and annotations used in our prior work. This collection contains a labelled dataset of 484 MR images collected on 242 consecutive patients with a VS undergoing Gamma Knife Stereotactic Radiosurgery at a single institution. Data includes all segmentations and contours used in treatment planning and details of the administered dose. Implementation of our automated segmentation algorithm uses MONAI, a freely-available open-source framework for deep learning in healthcare imaging. These data will facilitate the development and validation of automated segmentation frameworks for VS and may also be used to develop other multi-modal algorithmic models.