<b><i>Introduction:</i></b> Deep brain stimulation (DBS) surgery is an established treatment for movement disorders. Advances in neuroimaging techniques have resulted in improved targeting accuracy that may improve clinical outcomes. This study aimed to evaluate the safety and feasibility of using the Medtronic O-arm device for the acquisition of intraoperative stereotactic imaging, targeting, and localization of DBS electrodes compared with standard stereotactic MRI or computed tomography (CT). <b><i>Methods:</i></b> Patients were recruited prospectively into the study. Routine frame-based stereotactic DBS surgery was performed. Intraoperative imaging was used to facilitate and verify the accurate placement of the intracranial electrodes. The acquisition of coordinates and verification of the position of the electrodes using the O-arm were evaluated and compared with conventional stereotactic MRI or CT. Additionally, a systematic review of the literature on the use of intraoperative imaging in DBS surgery was performed. <b><i>Results:</i></b> Eighty patients were included. The indications for DBS surgery were dystonia, Parkinson’s disease, essential tremor, and epilepsy. The globus pallidus internus was the most commonly targeted region (43.7%), followed by the subthalamic nucleus (35%). Stereotactic O-arm imaging reduced the overall surgical time by 68 min, reduced the length of time of acquisition of stereotactic images by 77%, reduced patient exposure to ionizing radiation by 24.2%, significantly reduced operating room (OR) costs per procedure by 31%, and increased the OR and neuroradiology suite availability. <b><i>Conclusions:</i></b> The use of the O-arm in DBS surgery workflow significantly reduced the duration of image acquisition, the exposure to ionizing radiation, and costs when compared with standard stereotactic MRI or CT, without reducing accuracy.

No abstract

ObjectiveThe 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.MethodsWe 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.ResultsEligible 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.ConclusionsWe 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.

Deep-seated brain tumours represent a unique neurosurgical challenge as they are often surrounded by eloquent structures. We describe a minimally invasive technique using tubular retractors and intraoperative neurophysiology monitoring for open biopsy of a deep-seated lesion surrounded by the corticospinal tract. We used preoperative functional mapping with diffusion tensor imaging tractography and navigated transcranial magnetic stimulation to identify a safe surgical corridor. We also used 5-Aminolevulinic Acid induced fluorescence to identify the lesion intraoperatively and optimize tissue samples obtained for histopathological diagnosis. We found the use of these tools improved the safety of surgery and reduced the risk of surgical morbidity.

No abstract