Comparison of 2 Robotic Systems for Pediatric Stereoelectroencephalography Implantation.

BACKGROUND: Stereoelectroencephalography (SEEG) remains critical in guiding epilepsy surgery. Robot-assisted techniques have shown promise in improving SEEG implantation outcomes but have not been directly compared. In this single-institution series, we compared ROSA and Stealth AutoGuide robots in pediatric SEEG implantation. METHODS: We retrospectively reviewed 21 sequential pediatric SEEG implantations consisting of 6 ROSA and 15 AutoGuide procedures. We determined mean operative time, time per electrode, root mean square (RMS) registration error, and surgical complications. Three-dimensional radial distances were calculated between each electrode's measured entry and target points with respective errors from the planned trajectory line. RESULTS: Mean overall/per electrode operating time was 73.5/7.5 minutes for ROSA and 126.1/10.9 minutes for AutoGuide (P = 0.030 overall, P = 0.082 per electrode). Mean RMS registration error was 0.77 mm (0.55-0.93 mm) for ROSA and 0.6 mm (0.2-1.0 mm) for AutoGuide (P = 0.26). No procedures experienced complications. The mean radial (entry point error was 1.23 ± 0.11 mm for ROSA and 2.65 ± 0.12 mm for AutoGuide (P < 0.001), while the mean radial target point error was 1.86 ± 0.15 mm for ROSA and 3.25 ± 0.16 mm for AutoGuide (P < 0.001). CONCLUSIONS: Overall operative time was greater for AutoGuide procedures, although there was no statistically significant difference in time per electrode. Both systems are highly accurate with no significant RMS error difference. While the ROSA robot yielded significantly lower entry and target point errors, both robots are safe and reliable for deep electrode insertion in pediatric epilepsy.

A comparison of machine learning classifiers for pediatric epilepsy using resting-state functional MRI latency data.

Epilepsy affects 1 in 150 children under the age of 10 and is the most common chronic pediatric neurological condition; poor seizure control can irreversibly disrupt normal brain development. The present study compared the ability of different machine learning algorithms trained with resting-state functional MRI (rfMRI) latency data to detect epilepsy. Preoperative rfMRI and anatomical MRI scans were obtained for 63 patients with epilepsy and 259 healthy controls. The normal distribution of latency z-scores from the epilepsy and healthy control cohorts were analyzed for overlap in 36 seed regions. In these seed regions, overlap between the study cohorts ranged from 0.44-0.58. Machine learning features were extracted from latency z-score maps using principal component analysis. Extreme Gradient Boosting (XGBoost), Support Vector Machines (SVM), and Random Forest algorithms were trained with these features. Area under the receiver operating characteristics curve (AUC), accuracy, sensitivity, specificity and F1-scores were used to evaluate model performance. The XGBoost model outperformed all other models with a test AUC of 0.79, accuracy of 74%, specificity of 73%, and a sensitivity of 77%. The Random Forest model performed comparably to XGBoost across multiple metrics, but it had a test sensitivity of 31%. The SVM model did not perform >70% in any of the test metrics. The XGBoost model had the highest sensitivity and accuracy for the detection of epilepsy. Development of machine learning algorithms trained with rfMRI latency data could provide an adjunctive method for the diagnosis and evaluation of epilepsy with the goal of enabling timely and appropriate care for patients.

Indications for Inpatient Magnetoencephalography in Children - An Institution's Experience.

Magnetoencephalography (MEG) is recognized as a valuable non-invasive clinical method for localization of the epileptogenic zone and critical functional areas, as part of a pre-surgical evaluation for patients with pharmaco-resistant epilepsy. MEG is also useful in localizing functional areas as part of pre-surgical planning for tumor resection. MEG is usually performed in an outpatient setting, as one part of an evaluation that can include a variety of other testing modalities including 3-Tesla MRI and inpatient video-electroencephalography monitoring. In some clinical circumstances, however, completion of the MEG as an inpatient can provide crucial ictal or interictal localization data during an ongoing inpatient evaluation, in order to expedite medical or surgical planning. Despite well-established clinical indications for performing MEG in general, there are no current reports that discuss indications or considerations for completion of MEG on an inpatient basis. We conducted a retrospective institutional review of all pediatric MEGs performed between January 2012 and December 2020, and identified 34 cases where MEG was completed as an inpatient. We then reviewed all relevant medical records to determine clinical history, all associated diagnostic procedures, and subsequent treatment plans including epilepsy surgery and post-surgical outcomes. In doing so, we were able to identify five indications for completing the MEG on an inpatient basis: (1) super-refractory status epilepticus (SRSE), (2) intractable epilepsy with frequent electroclinical seizures, and/or frequent or repeated episodes of status epilepticus, (3) intractable epilepsy with infrequent epileptiform discharges on EEG or outpatient MEG, or other special circumstances necessitating inpatient monitoring for successful and safe MEG data acquisition, (4) MEG mapping of eloquent cortex or interictal spike localization in the setting of tumor resection or other urgent neurosurgical intervention, and (5) international or long-distance patients, where outpatient MEG is not possible or practical. MEG contributed to surgical decision-making in the majority of our cases (32 of 34). Our clinical experience suggests that MEG should be considered on an inpatient basis in certain clinical circumstances, where MEG data can provide essential information regarding the localization of epileptogenic activity or eloquent cortex, and be used to develop a treatment plan for surgical management of children with complicated or intractable epilepsy.

Convolutional Neural Networks for Pediatric Refractory Epilepsy Classification Using Resting-State Functional Magnetic Resonance Imaging.

OBJECTIVE: This study aims to evaluate the performance of convolutional neural networks (CNNs) trained with resting-state functional magnetic resonance imaging (rfMRI) latency data in the classification of patients with pediatric epilepsy from healthy controls. METHODS: Preoperative rfMRI and anatomic magnetic resonance imaging scans were obtained from 63 pediatric patients with refractory epilepsy and 259 pediatric healthy controls. Latency maps of the temporal difference between rfMRI and the global mean signal were calculated using voxel-wise cross-covariance. Healthy control and epilepsy latency z score maps were pseudorandomized and partitioned into training data (60%), validation data (20%), and test data (20%). Healthy control individuals and patients with epilepsy were labeled as negative and positive, respectively. CNN models were then trained with the designated training data. Model hyperparameters were evaluated with a grid-search method. The model with the highest sensitivity was evaluated using unseen test data. Accuracy, sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve were used to evaluate the ability of the model to classify epilepsy in the test data set. RESULTS: The model with the highest validation sensitivity correctly classified 74% of unseen test patients with 85% sensitivity, 71% specificity, F1 score of 0.56, and an area under the receiver operating characteristic curve of 0.86. CONCLUSIONS: Using rfMRI latency data, we trained a CNN model to classify patients with pediatric epilepsy from healthy controls with good performance. CNN could serve as an adjunct in the diagnosis of pediatric epilepsy. Identification of pediatric epilepsy earlier in the disease course could decrease time to referral to specialized epilepsy centers and thus improve prognosis in this population.

An Infant Born to a Mother With Anti-N-Methyl-d-Aspartate Receptor Encephalitis.

BACKGROUND: Anti-N-Methyl-D-Aspartate receptor (NMDAR) encephalitis is an autoimmune disorder that often affects women of childbearing age, and maternal-fetal transfer of anti-NMDAR antibodies during pregnancy has been documented in both symptomatic and asymptomatic women. The effects of these antibodies on the fetus, however, are incompletely understood. PATIENT DESCRIPTION: This term infant exhibited depressed respiratory effort, poor feeding, and abnormal movements after birth. Magnetic resonance imaging revealed diffuse cerebral edema with ischemic and hemorrhagic injury. Her mother had experienced anti-NMDAR encephalitis secondary to an ovarian teratoma 18 months earlier. The baby's serum NMDAR antibody titer was elevated at 1:320. Intravenous immunoglobulin did not result in clinical improvement, and care was withdrawn on day of life 20. Her mother had an elevated serum NMDAR antibodies (1:80), positive CSF antibody titers, and a new ovarian teratoma. CONCLUSION: Routine testing of NMDAR antibodies in pregnant women with a previous history of anti-NMDAR encephalitis may be warranted. Infants born to these mothers should be closely monitored throughout pregnancy and after birth.