Technique, Results, and Complications Related to Robot-Assisted Stereoelectroencephalography

ABSTRACT BACKGROUND: Robot-assisted stereoelectroencephalography (SEEG) may represent a simplified, precise, and safe alternative to the more traditional SEEG techniques. OBJECTIVE: To report our clinical experience with robotic SEEG implantation and to define its utility in the management of patients with medically refractory epilepsy. METHODS: The prospective observational analyses included all patients with medically refractory focal epilepsy who underwent robot-assisted stereotactic placement of depth electrodes for extraoperative brain monitoring between November 2009 and May 2013. Technical nuances of the robotic implantation technique are presented, as well as an analysis of demographics, time of planning and procedure, seizure outcome, in vivo accuracy, and procedure-related complications. RESULTS: One hundred patients underwent 101 robot-assisted SEEG procedures. Their mean age was 33.2 years. In total, 1245 depth electrodes were implanted. On average, 12.5 electrodes were implanted per patient. The time of implantation planning was 30 minutes on average (range, 15-60 minutes). The average operative time was 130 minutes (range, 45-160 minutes). In vivo accuracy (calculated in 500 trajectories) demonstrated a median entry point error of 1.2 mm (interquartile range, 0.78-1.83 mm) and a median target point error of 1.7 mm (interquartile range, 1.20-2.30 mm). Of the group of patients who underwent resective surgery (68 patients), 45 (66.2%) gained seizure freedom status. Mean follow-up was 18 months. The total complication rate was 4%. CONCLUSION: The robotic SEEG technique and method were demonstrated to be safe, accurate, and efficient in anatomically defining the epileptogenic zone and subsequently promoting sustained seizure freedom status in patients with difficult-to-localize seizures.

Download Full-text

Stereoelectroencephalography

Neurosurgery ◽

10.1227/neu.0b013e31827d1161 ◽

2012 ◽

Vol 72 (3) ◽

pp. 353-366 ◽

Cited By ~ 267

Author(s):

Francesco Cardinale ◽

Massimo Cossu ◽

Laura Castana ◽

Giuseppe Casaceli ◽

Marco Paolo Schiariti ◽

...

Keyword(s):

Interquartile Range ◽

Entry Point ◽

Target Point ◽

Epileptogenic Zone ◽

Localization Error ◽

Drug Resistant ◽

Robot Assisted ◽

Data Set ◽

Essential Information

Abstract BACKGROUND: Stereoelectroencephalography (SEEG) methodology, originally developed by Talairach and Bancaud, is progressively gaining popularity for the presurgical invasive evaluation of drug-resistant epilepsies. OBJECTIVE: To describe recent SEEG methodological implementations carried out in our center, to evaluate safety, and to analyze in vivo application accuracy in a consecutive series of 500 procedures with a total of 6496 implanted electrodes. METHODS: Four hundred nineteen procedures were performed with the traditional 2-step surgical workflow, which was modified for the subsequent 81 procedures. The new workflow entailed acquisition of brain 3-dimensional angiography and magnetic resonance imaging in frameless and markerless conditions, advanced multimodal planning, and robot-assisted implantation. Quantitative analysis for in vivo entry point and target point localization error was performed on a sub-data set of 118 procedures (1567 electrodes). RESULTS: The methodology allowed successful implantation in all cases. Major complication rate was 12 of 500 (2.4%), including 1 death for indirect morbidity. Median entry point localization error was 1.43 mm (interquartile range, 0.91-2.21 mm) with the traditional workflow and 0.78 mm (interquartile range, 0.49-1.08 mm) with the new one (P < 2.2 × 10−16). Median target point localization errors were 2.69 mm (interquartile range, 1.89-3.67 mm) and 1.77 mm (interquartile range, 1.25-2.51 mm; P < 2.2 × 10−16), respectively. CONCLUSION: SEEG is a safe and accurate procedure for the invasive assessment of the epileptogenic zone. Traditional Talairach methodology, implemented by multimodal planning and robot-assisted surgery, allows direct electrical recording from superficial and deep-seated brain structures, providing essential information in the most complex cases of drug-resistant epilepsy.

Download Full-text

Accuracy and Safety of Customized Stereotactic Fixtures for Stereoelectroencephalography in Pediatric Patients

Stereotactic and Functional Neurosurgery ◽

10.1159/000510063 ◽

2020 ◽

pp. 1-8

Author(s):

Constantin Pistol ◽

Andrei Daneasa ◽

Jean Ciurea ◽

Alin Rasina ◽

Andrei Barborica ◽

...

Keyword(s):

Focal Epilepsy ◽

Perioperative Complications ◽

Intractable Epilepsy ◽

Target Point ◽

Seizure Freedom ◽

Epileptogenic Zone ◽

Localization Error ◽

Temporal Area ◽

Lateral Entry ◽

Stereotactic Implantation

Stereoelectroencephalography (SEEG) in children with intractable epilepsy presents particular challenges. Their thin and partially ossified cranium, specifically in the temporal area, is prone to fracture while attaching stereotactic systems to the head or stabilizing the head in robot’s field of action. Postponing SEEG in this special population of patients can have serious consequences, reducing their chances of becoming seizure-free and impacting their social and cognitive development. This study demonstrates the safety and accuracy offered by a frameless personalized 3D printed stereotactic implantation system for SEEG investigations in children under 4 years of age. SEEG was carried out in a 3-year-old patient with drug-resistant focal epilepsy, based on a right temporal-perisylvian epileptogenic zone hypothesis. Fifteen intracerebral electrodes were placed using a StarFix patient-customized stereotactic fixture. The median lateral entry point localization error of the electrodes was 0.90 mm, median lateral target point localization error was 1.86 mm, median target depth error was 0.83 mm, and median target point localization error was 1.96 mm. There were no perioperative complications. SEEG data led to a tailored right temporal-insular-opercular resection, with resulting seizure freedom (Engel IA). In conclusion, patient-customized stereotactic fixtures are a safe and accurate option for SEEG exploration in young children.

Download Full-text

Stereoelectroencephalography in Children and Adolescents With Difficult-to-Localize Refractory Focal Epilepsy

Neurosurgery ◽

10.1227/neu.0000000000000453 ◽

2014 ◽

Vol 75 (3) ◽

pp. 258-268 ◽

Cited By ~ 50

Author(s):

Jorge Gonzalez-Martinez ◽

Jeffrey Mullin ◽

Juan Bulacio ◽

Ajay Gupta ◽

Rei Enatsu ◽

...

Keyword(s):

Children And Adolescents ◽

Pediatric Patients ◽

Focal Epilepsy ◽

Early Experience ◽

Morbidity Rate ◽

Seizure Outcome ◽

Seizure Freedom ◽

Epileptogenic Zone ◽

Eloquent Cortex

Abstract BACKGROUND: Although stereoelectroencephalography (SEEG) has been shown to be a valuable tool for preoperative decision making in focal epilepsy, there are few reports addressing the utility and safety of SEEG methodology applied to children and adolescents. OBJECTIVE: To present the results of our early experience using SEEG in pediatric patients with difficult-to-localize epilepsy who were not considered candidates for subdural grid evaluation. METHODS: Thirty children and adolescents with the diagnosis of medically refractory focal epilepsy (not considered ideal candidates for subdural grids and strip placement) underwent SEEG implantation. Demographics, electrophysiological localization of the hypothetical epileptogenic zone, complications, and seizure outcome after resections were analyzed. RESULTS: Eighteen patients (60%) underwent resections after SEEG implantations. In patients who did not undergo resections (12 patients), reasons included failure to localize the epileptogenic zone (4 patients); multifocal epileptogenic zone (4 patients); epileptogenic zone located in eloquent cortex, preventing resection (3 patients); and improvement in seizures after the implantation (1 patient). In patients who subsequently underwent resections, 10 patients (55.5%) were seizure free (Engel class I) and 5 patients (27.7%) experienced seizure improvement (Engel class II or III) at the end of the follow-up period (mean, 25.9 months; range, 12 to 47 months). The complication rate in SEEG implantations was 3%. CONCLUSION: The SEEG methodology is safe and should be considered in children/adolescents with difficult-to-localize epilepsy. When applied to highly complex and difficult-to-localize pediatric patients, SEEG may provide an additional opportunity for seizure freedom in association with a low morbidity rate.

Download Full-text

Implantation technique, safety and complications of robot-assisted stereoelectroencephalography exploration of the limbic thalamus in human focal epilepsy

10.1101/2020.01.27.922195 ◽

2020 ◽

Author(s):

Ganne Chaitanya ◽

Andrew K. Romeo ◽

Adeel Ilyas ◽

Auriana Irannejad ◽

Emilia Toth ◽

...

Keyword(s):

Focal Epilepsy ◽

Clinical Care ◽

Electrode Placement ◽

Implantation Technique ◽

Precentral Gyrus ◽

Thalamic Nuclei ◽

Robot Assisted ◽

Entry Site ◽

Depth Electrodes ◽

Medial Group

AbstractIntroductionDespite numerous imaging studies highlighting the importance of thalamus in surgical prognosis, human electrophysiological studies involving the limbic thalamic nuclei are limited. The objective of this study was to evaluate the safety and accuracy of robot-assisted stereotactic electrode placement in the limbic thalamic nuclei in patients with suspected temporal lobe epilepsy (TLE).MethodsAfter obtaining informed consent, 24 adults with drug-resistant suspected TLE undergoing Stereo-EEG evaluation were enrolled in this prospective study. The trajectory of one electrode planned for clinical sampling the operculo-insular cortex was modified to extend to the thalamus, thereby preventing the need for additional electrode placement for research. The anterior thalamus (ANT) (N=13) and the medial group of thalamic nuclei (MED) (N=11), including mediodorsal (MD) and centromedian (CeM) were targeted. The post-implantation CT was co-registered to the pre-operative MRI, and Morel’s thalamic atlas was used to confirm the accuracy of implantation.ResultsTen out of 13 (77%) in the ANT group and 10 out of 11 patients (90%) in the medial group had electrodes accurately placed in the thalamic nuclei. None of the patients had a thalamic hemorrhage. However, trace asymptomatic hemorrhages at the cortical level entry site were noted in 20.8% of patients and they did not require additional surgical intervention. SEEG data from all the patients were interpretable and analyzable. The trajectories for the ANT implant differed slightly from the medial group at the entry point i.e., precentral gyrus in the former and postcentral gyrus in the latter.ConclusionsUsing judiciously planned robot-assisted SEEG, we demonstrate the safety of electrophysiological sampling from various thalamic nuclei for research recordings, presenting a technique that avoids implanting additional depth electrodes, or comprising clinical care. With these results, we propose that if patients are fully informed of the risks involved, there are potential benefits of gaining mechanistic insights to seizure genesis, which may help to develop neuromodulation therapies.

Download Full-text

A multimodal concept for invasive diagnostics and surgery based on neuronavigated voxel-based morphometric MRI postprocessing data in previously nonlesional epilepsy

Journal of Neurosurgery ◽

10.3171/2016.12.jns161676 ◽

2018 ◽

Vol 128 (4) ◽

pp. 1178-1186 ◽

Cited By ~ 6

Author(s):

Daniel Delev ◽

Carlos M. Quesada ◽

Alexander Grote ◽

Jan P. Boström ◽

Christian Elger ◽

...

Keyword(s):

Focal Epilepsy ◽

Diagnostic Yield ◽

Focal Cortical Dysplasia ◽

Seizure Outcome ◽

Epileptogenic Zone ◽

Mri Findings ◽

Additional Information ◽

Resective Surgery ◽

Depth Electrodes ◽

Class 1

OBJECTIVEDiagnosis and surgical treatment of refractory and apparent nonlesional focal epilepsy is challenging. Morphometric MRI voxel-based and other postprocessing methods can help to localize the epileptogenic zone and thereby support the planning of further invasive electroencephalography (EEG) diagnostics, and maybe resective epilepsy surgery.METHODSThe authors developed an algorithm to implement regions of interest (ROI), based on postprocessed MRI data, into a neuronavigation tool. This was followed by stereotactic ROI-guided implantation of depth electrodes and ROI-navigated resective surgery. Data on diagnostic yield, histology, and seizure outcome were collected and evaluated.RESULTSFourteen consecutive patients with apparently nonlesional epilepsy were included in this study. Reevaluation of the MR images with the help of MRI postprocessing analysis led to the identification of probable subtle lesions in 11 patients. Additional information obtained by SPECT imaging and MRI reevaluation suggested possible lesions in the remaining 3 patients. The ROI-guided invasive implantation of EEG yielded interictal and ictal activity in 13 patients who were consequently referred to resective surgery. Despite the apparently negative MRI findings, focal cortical dysplasia was found in 64% of the patients (n = 9). At the last available outcome, 8 patients (57%) were completely seizure free (International League Against Epilepsy Class 1).CONCLUSIONSThe results demonstrate the feasibility and usefulness of a robust and straightforward algorithm for implementation of MRI postprocessing-based targets into the neuronavigation system. This approach allowed the stereotactic implantation of a low number of depth electrodes only, which confirmed the seizure-onset hypothesis in 90% of the cases without causing any complications. Furthermore, the neuronavigated ROI-guided lesionectomy helped to perform resective surgery in this rather challenging subgroup of patients with apparent nonlesional epilepsy.

Download Full-text

Robot-assisted stereoelectroencephalography exploration of the limbic thalamus in human focal epilepsy: implantation technique and complications in the first 24 patients

Neurosurgical FOCUS ◽

10.3171/2020.1.focus19887 ◽

2020 ◽

Vol 48 (4) ◽

pp. E2 ◽

Cited By ~ 6

Author(s):

Ganne Chaitanya ◽

Andrew K. Romeo ◽

Adeel Ilyas ◽

Auriana Irannejad ◽

Emilia Toth ◽

...

Keyword(s):

Focal Epilepsy ◽

Clinical Care ◽

Electrode Placement ◽

Implantation Technique ◽

Precentral Gyrus ◽

Thalamic Nuclei ◽

Robot Assisted ◽

Entry Site ◽

Depth Electrodes ◽

Electrophysiological Studies

OBJECTIVEDespite numerous imaging studies highlighting the importance of the thalamus in a patient’s surgical prognosis, human electrophysiological studies involving the limbic thalamic nuclei are limited. The objective of this study was to evaluate the safety and accuracy of robot-assisted stereotactic electrode placement in the limbic thalamic nuclei of patients with suspected temporal lobe epilepsy (TLE).METHODSAfter providing informed consent, 24 adults with drug-resistant, suspected TLE undergoing evaluation with stereoelectroencephalography (SEEG) were enrolled in the prospective study. The trajectory of one electrode planned for clinical sampling of the operculoinsular cortex was modified to extend it to the thalamus, thereby preventing the need for additional electrode placement for research. The anterior nucleus of the thalamus (ANT) (n = 13) and the medial group of thalamic nuclei (MED) (n = 11), including the mediodorsal and centromedian nuclei, were targeted. The postimplantation CT scan was coregistered to the preoperative MR image, and Morel’s thalamic atlas was used to confirm the accuracy of implantation.RESULTSTen (77%) of 13 patients in the ANT group and 10 (91%) of 11 patients in the MED group had electrodes accurately placed in the thalamic nuclei. None of the patients had a thalamic hemorrhage. However, trace asymptomatic hemorrhages at the cortical-level entry site were noted in 20.8% of patients, who did not require additional surgical intervention. SEEG data from all the patients were interpretable and analyzable. The trajectories for the ANT implant differed slightly from those of the MED group at the entry point—i.e., the precentral gyrus in the former and the postcentral gyrus in the latter.CONCLUSIONSUsing judiciously planned robot-assisted SEEG, the authors demonstrate the safety of electrophysiological sampling from various thalamic nuclei for research recordings, presenting a technique that avoids implanting additional depth electrodes or compromising clinical care. With these results, we propose that if patients are fully informed of the risks involved, there are potential benefits of gaining mechanistic insights to seizure genesis, which may help to develop neuromodulation therapies.

Download Full-text

The Impact of Lesional Factors on Seizure Outcome Following Lesionectomy as a Surgical Management of Extratemporal Epilepsy, Case Series from a Developing Country and Review of Literature.

10.21203/rs.3.rs-685046/v1 ◽

2021 ◽

Author(s):

Amr Ali Hasanain ◽

Mohamed Sawan ◽

Ahmed Mohamed Ali

Keyword(s):

Focal Epilepsy ◽

Focal Lesion ◽

Seizure Outcome ◽

Seizure Freedom ◽

Low Grade ◽

Epileptogenic Zone ◽

Seizure Semiology ◽

Radiological Data ◽

The Impact

Abstract BACKGROUNDExtratemporal lesional epilepsy can be managed with various surgical techniques such as simple lesionectomy or more extensive resections, all of which aim at targeting the epileptogenic zone which is the key for achieving a favorable outcome. This study aimed at evaluating the effectiveness of lesionectomy in the treatment of extra-temporal epilepsy associated with a lesion on radiological imaging, and to show the effect of lesional factors on seizure outcome including the anatomical location, the relation to cerebral parenchyma, the extent of surgical excision and the histopathological nature of the lesion.METHODSA prospective study on 20 patients presenting with focal epilepsy, or focal epilepsy with secondary generalized seizures with evidence of focal lesion in an extratemporal location on MRI. Lesionectomy was done and we used the Engel’s classification for seizure outcome.RESULTSLesions were mostly tumors (85 %). The frontal lobe is the most frequent locations (60 %). Low-grade glioma represented 35 % while meningioma represented 45 % of all lesions (both intra-axial and extra-axial). Four patients were lost during follow up (mean 23.31 months). For the remaining 16 patients, 13 cases were tumors (81.25%). Lesionectomy achieved seizure freedom in 68.75 %.CONCLUSIONSIn a country with limited resources, lesionectomy is a valid technique for epilepsy surgery as long as the radiological data and the seizure semiology are concordant. Total lesionectomy provides good seizure control when the clinical and radiological data are concordant with seizure semiology, in particular with tumor-related epilepsy. A study comparing postoperative seizure outcome between intra-axial and extra-axial lesions on a larger scale and with a longer follow up period is recommended.

Download Full-text

Frame-based and robot-assisted insular stereo-electroencephalography via an anterior or posterior oblique approach

Journal of Neurosurgery ◽

10.3171/2020.10.jns201843 ◽

2021 ◽

pp. 1-10

Author(s):

Kathrin Machetanz ◽

Florian Grimm ◽

Thomas V. Wuttke ◽

Josua Kegele ◽

Holger Lerche ◽

...

Keyword(s):

Spatial Distribution ◽

Functional Organization ◽

Implantation Technique ◽

Target Point ◽

Seizure Outcome ◽

Anatomical Location ◽

Robot Assisted ◽

Stereotactic Frame ◽

Oblique Approach ◽

Robot Group

OBJECTIVE There is an increasing interest in stereo-electroencephalography (SEEG) for invasive evaluation of insular epilepsy. The implantation of insular SEEG electrodes, however, is still challenging due to the anatomical location and complex functional segmentation in both an anteroposterior and ventrodorsal (i.e., superoinferior) direction. While the orthogonal approach (OA) is the shortest trajectory to the insula, it might insufficiently cover these networks. In contrast, the anterior approach (AOA) or posterior oblique approach (POA) has the potential for full insular coverage, with fewer electrodes bearing a risk of being more inaccurate due to the longer trajectory. Here, the authors evaluated the implantation accuracy and the detection of epilepsy-related SEEG activity with AOA and POA insular trajectories. METHODS This retrospective study evaluated the accuracy of 220 SEEG electrodes in 27 patients. Twelve patients underwent a stereotactic frame-based procedure (frame group), and 15 patients underwent a frameless robot-assisted surgery (robot group). In total, 55 insular electrodes were implanted using the AOA or POA considering the insular anteroposterior and ventrodorsal functional organization. The entry point error (EPE) and target point error (TPE) were related to the implantation technique (frame vs robot), the length of the trajectory, and the location of the target (insular vs noninsular). Finally, the spatial distribution of epilepsy-related SEEG activity within the insula is described. RESULTS There were no significant differences in EPE (mean 0.9 ± 0.6 for the nonsinsular electrodes and 1.1 ± 0.7 mm for the insular electrodes) and TPE (1.5 ± 0.8 and 1.6 ± 0.9 mm, respectively), although the length of trajectories differed significantly (34.1 ± 10.9 and 70.1 ± 9.0 mm, repsectively). There was a significantly larger EPE in the frame group than in the robot group (1.5 ± 0.6 vs 0.7 ± 0.5 mm). However, there was no group difference in the TPE (1.5 ± 0.8 vs 1.6 ± 0.8 mm). Epilepsy-related SEEG activity was detected in 42% (23/55) of the insular electrodes. Spatial distribution of this activity showed a clustering in both anteroposterior and ventrodorsal directions. In purely insular onset cases, subsequent insular lesionectomy resulted in a good seizure outcome. CONCLUSIONS The implantation of insular electrodes via the AOA or POA is safe and efficient for SEEG implantation covering both anteroposterior and ventrodorsal functional organization with few electrodes. In this series, there was no decrease in accuracy due to the longer trajectory of insular SEEG electrodes in comparison with noninsular SEEG electrodes. The results of frame-based and robot-assisted implantations were comparable.

Download Full-text

Future of Neurology & Technology: Stereo-electroencephalography in Presurgical Epilepsy Evaluation

Neurology ◽

10.1212/wnl.0000000000013088 ◽

2021 ◽

pp. 10.1212/WNL.0000000000013088

Author(s):

Guillermo Delgado-Garcia ◽

Birgit Frauscher

Keyword(s):

North America ◽

Temporal Dynamics ◽

Focal Epilepsy ◽

Three Dimensional ◽

Epileptic Seizures ◽

Epileptic Activity ◽

Seizure Freedom ◽

Epileptogenic Zone ◽

Drug Resistant ◽

Depth Electrodes

Stereo-electroencephalography (SEEG) is not only a sophisticated and highly technological investigation but a new and better way to conceptualize the spatial and temporal dynamics of epileptic activity. The first intracranial investigations with SEEG were carried out in France in the mid-twentieth century; however, its use in North America is much more recent. Given its significantly lower risk of complications and its ability to sample both superficial and deep structures as well as both hemispheres simultaneously, SEEG has become the preferred method to conduct intracranial EEG monitoring in most comprehensive epilepsy centers in North America. SEEG is an invasive neurophysiological methodology used for advanced pre-surgical work-up in the 20% of drug-resistant patients with more complex focal epilepsy in whom non-invasive investigations do not allow to decide on surgical candidacy. SEEG uses stereotactically-implanted depth electrodes to map the origin and propagation of epileptic seizures by creating a three-dimensional representation of the abnormal electrical activity in the brain. SEEG analysis takes into account the background, interictal, and ictal activity, as well as the results of cortical electrical stimulation procedures, to reliably delineate the epileptogenic network. By means of a clinical vignette, this article will walk general neurologists, but especially neurology trainees through the immense potential of this methodology. In summary, SEEG enables to accurately identify the epileptogenic zone in patients with drug-resistant focal epilepsy who otherwise would be not amenable to surgical treatment, the best way to improve seizure control and achieve seizure-freedom in this patient population.

Download Full-text

Efficient automated localization of ECoG electrodes in CT images via shape analysis

International Journal of Computer Assisted Radiology and Surgery ◽

10.1007/s11548-021-02325-0 ◽

2021 ◽

Vol 16 (4) ◽

pp. 543-554

Author(s):

Jessica Centracchio ◽

Antonio Sarno ◽

Daniele Esposito ◽

Emilio Andreozzi ◽

Luigi Pavone ◽

...

Keyword(s):

Shape Analysis ◽

Focal Epilepsy ◽

Support Vector ◽

Epileptogenic Zone ◽

Platinum Electrodes ◽

Public Repository ◽

Automated Method ◽

Depth Electrodes ◽

Ethical Approval ◽

Cortical Regions

Abstract Purpose People with drug-refractory epilepsy are potential candidates for surgery. In many cases, epileptogenic zone localization requires intracranial investigations, e.g., via ElectroCorticoGraphy (ECoG), which uses subdural electrodes to map eloquent areas of large cortical regions. Precise electrodes localization on cortical surface is mandatory to delineate the seizure onset zone. Simple thresholding operations performed on patients’ computed tomography (CT) volumes recognize electrodes but also other metal objects (e.g., wires, stitches), which need to be manually removed. A new automated method based on shape analysis is proposed, which provides substantially improved performances in ECoG electrodes recognition. Methods The proposed method was retrospectively tested on 24 CT volumes of subjects with drug-refractory focal epilepsy, presenting a large number (> 1700) of round platinum electrodes. After CT volume thresholding, six geometric features of voxel clusters (volume, symmetry axes lengths, circularity and cylinder similarity) were used to recognize the actual electrodes among all metal objects via a Gaussian support vector machine (G-SVM). The proposed method was further tested on seven CT volumes from a public repository. Simultaneous recognition of depth and ECoG electrodes was also investigated on three additional CT volumes, containing penetrating depth electrodes. Results The G-SVM provided a 99.74% mean classification accuracy across all 24 single-patient datasets, as well as on the combined dataset. High accuracies were obtained also on the CT volumes from public repository (98.27% across all patients, 99.68% on combined dataset). An overall accuracy of 99.34% was achieved for the recognition of depth and ECoG electrodes. Conclusions The proposed method accomplishes automated ECoG electrodes localization with unprecedented accuracy and can be easily implemented into existing software for preoperative analysis process. The preliminary yet surprisingly good results achieved for the simultaneous depth and ECoG electrodes recognition are encouraging. Ethical approval n°NCT04479410 by “IRCCS Neuromed” (Pozzilli, Italy), 30th July 2020.

Download Full-text