Microelectrode Recordings Validate the Clinical Visualization of Subthalamic-Nucleus Based on 7T Magnetic Resonance Imaging and Machine Learning for Deep Brain Stimulation Surgery

Interleaved Propofol-Ketamine Maintains DBS Physiology and Hemodynamic Stability: A Double-Blind Randomized Controlled Trial

BACKGROUND

The gold standard anesthesia for deep brain stimulation (DBS) surgery is the "awake" approach, using local anesthesia alone. Although it offers high-quality microelectrode recordings and therapeutic-window assessment, it potentially causes patients extreme stress and might result in suboptimal surgical outcomes. General anesthesia or deep sedation is an alternative, but may reduce physiological testing reliability and lead localization accuracy.

OBJECTIVES

The aim is to investigate a novel anesthesia regimen of ketamine-induced conscious sedation for the physiological testing phase of DBS surgery.

METHODS

Parkinson's patients undergoing subthalamic DBS surgery were randomly divided into experimental and control groups. During physiological testing, the groups received 0.25 mg/kg/h ketamine infusion and normal saline, respectively. Both groups had moderate propofol sedation before and after physiological testing. The primary outcome was recording quality. Secondary outcomes included hemodynamic stability, lead accuracy, motor and cognitive outcome, patient satisfaction, and adverse events.

RESULTS

Thirty patients, 15 from each group, were included. Intraoperatively, the electrophysiological signature and lead localization were similar under ketamine and saline. Tremor amplitude was slightly lower under ketamine. Postoperatively, patients in the ketamine group reported significantly higher satisfaction with anesthesia. The improvement in Unified Parkinson's disease rating scale part-III was similar between the groups. No negative effects of ketamine on hemodynamic stability or cognition were reported perioperatively.

CONCLUSIONS

Ketamine-induced conscious sedation provided high quality microelectrode recordings comparable with awake conditions. Additionally, it seems to allow superior patient satisfaction and hemodynamic stability, while maintaining similar post-operative outcomes. Therefore, it holds promise as a novel alternative anesthetic regimen for DBS. © 2024 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Use of a Commercial 7-T MRI Scanner for Clinical Brain Imaging: Indications, Protocols, Challenges, and Solutions-A Single-Center Experience

The first commercially available 7-T MRI scanner (Magnetom Terra) was approved by the FDA in 2017 for clinical imaging of the brain and knee. After initial protocol development and sequence optimization efforts in volunteers, the 7-T system, in combination with an FDA-approved 1-channel transmit/32-channel receive array head coil, can now be routinely used for clinical brain MRI examinations. The ultrahigh field strength of 7-T MRI has the advantages of improved spatial resolution, increased SNR, and increased CNR but also introduces an array of new technical challenges. The purpose of this article is to describe an institutional experience with the use of the commercially available 7-T MRI scanner for routine clinical brain imaging. Specific clinical indications for which 7-T MRI may be useful for brain imaging include brain tumor evaluation with possible perfusion imaging and/or spectroscopy, radiotherapy planning; evaluation of multiple sclerosis and other demyelinating diseases, evaluation of Parkinson disease and guidance of deep brain stimulator placement, high-detail intracranial MRA and vessel wall imaging, evaluation of pituitary pathology, and evaluation of epilepsy. Detailed protocols, including sequence parameters, for these various indications are presented, and implementation challenges (including artifacts, safety, and side effects) and potential solutions are explored.

Utilizing 7-Tesla Subthalamic Nucleus Connectivity in Deep Brain Stimulation for Parkinson Disease

BACKGROUND

Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is a highly effective surgical treatment for patients with advanced Parkinson disease (PD). Combining 7.0-Tesla (7T) T2- and diffusion-weighted imaging (DWI) sequences allows for selective segmenting of the motor part of the STN and, thus, for possible optimization of DBS.

MATERIALS AND METHODS

7T T2 and DWI sequences were obtained, and probabilistic segmentation of motor, associative, and limbic STN segments was performed. Left- and right-sided motor outcome (Movement Disorders Society Unified Parkinson's Disease Rating Scale) scores were used for evaluating the correspondence between the active electrode contacts in selectively segmented STN and the clinical DBS effect. The Bejjani line was reviewed for crossing of segments.

RESULTS

A total of 50 STNs were segmented in 25 patients and proved highly feasible. Although the highest density of motor connections was situated in the dorsolateral STN for all patients, the exact partitioning of segments differed considerably. For all the active electrode contacts situated within the predominantly motor-connected segment of the STN, the average hemi-body Unified Parkinson's Disease Rating Scale motor improvement was 80%; outside this segment, it was 52% (p < 0.01). The Bejjani line was situated in the motor segment for 32 STNs.

CONCLUSION

The implementation of 7T T2 and DWI segmentation of the STN in DBS for PD is feasible and offers insight into the location of the motor segment. Segmentation-guided electrode placement is likely to further improve motor response in DBS for PD. However, commercially available DBS software for postprocessing imaging would greatly facilitate widespread implementation.

Clinician vs. imaging-based subthalamic nucleus deep brain stimulation programming

INTRODUCTION

We sought to explore whether electrode visualization tools (EVT) can accurately predict the selection of optimal Deep Brain Stimulation (DBS) electrode contacts.

METHODS

Twelve patients with Parkinson's disease (PD) undergoing STN-DBS at The Ohio State University were enrolled in a prospective analysis to evaluate the accuracy of EVT-based vs. standard DBS programming. EVTs were generated by the Surgical Information Sciences (SIS) system to develop a 3D model showing the implanted lead location relative to the STN. Then, imaging-based data were compared to the results of a standard monopolar review to evaluate concordance with clinical data and time spent selecting useable, non-useable, and borderline electrode contacts.

RESULTS

A total of 18 DBS leads (n = 68 electrode contacts) were analyzed. The concordance between EVT and standard clinical programming expressed as the kappa coefficient was 0.65 (82.35% raw agreement) for non-useable, 0.52 for useable (64.71% raw agreement), and 0.52 for borderline (58.82% raw agreement). The average time spent determining whether an electrode contact was useable, non-useable, or borderline was 1.46 ± 0.76 min with EVT vs. 61.25 ± 17.47 with standard monopolar review. Eight different categories of side effects were identified, with facial pulling and speech difficulties being observed with the most frequency. The type of side effect observed was accurately predicted using EVT 90% of the time.

CONCLUSIONS

This study demonstrates that next-generation EVT-based programming can be implemented into STN-DBS programming workflows with a considerable saving of time and effort spent in testing combinations of stimulation settings, particularly for the identification of non-useable electrode contacts.

Automatic localization of target point for subthalamic nucleus-deep brain stimulation via hierarchical attention-UNet based MRI segmentation

BACKGROUND

Deep brain stimulation of the subthalamic nucleus (STN-DBS) is an effective treatment for patients with advanced Parkinson's disease, the outcome of this surgery is highly dependent on the accurate placement of the electrode in the optimal target of STN.

PURPOSE

In this study, we aim to develop a target localization pipeline for DBS surgery, considering that the heart of this matter is to achieve the STN and red nucleus segmentation, a deep learning-based automatic segmentation approach is proposed to tackle this issue.

METHODS

To address the problems of ambiguous boundaries and variable shape of the segmentation targets, the hierarchical attention mechanism with two different attention strategies is integrated into an encoder-decoder network for mining both semantics and fine-grained details for segmentation. The hierarchical attention mechanism is utilized to suppress irrelevant regions in magnetic resonance (MR) images while build long-range dependency among segmentation targets. Specifically, the attention gate (AG) is integrated into low-level features to suppress irrelevant regions in an input image while highlighting the salient features useful for segmentation. Besides, the self-attention involved in the transformer block is integrated into high-level features to model the global context. Ninety-nine brain magnetic resonance imaging (MRI) studies were collected from 99 patients with Parkinson's disease undergoing STN-DBS surgery, among which 80 samples were randomly selected as the training datasets for deep learning training, and ground truths (segmentation masks) were manually generated by radiologists.

RESULTS

We applied five-fold cross-validation on these data to train our model, the mean results on 19 test samples are used to conduct the comparison experiments, the Dice similarity coefficient (DSC), Jaccard (JA), sensitivity (SEN), and HD95 of the segmentation for STN are 88.20%, 80.32%, 90.13%, and 1.14 mm, respectively, outperforming the state-of-the-art STN segmentation method with 2.82%, 4.52%, 2.56%, and 0.02 mm respectively. The source code and trained models of this work have been released in the URL below: https://github.com/liuruiqiang/HAUNet/tree/master.

CONCLUSIONS

In this study, we demonstrate the effectiveness of the hierarchical attention mechanism for building global dependency on high-level semantic features and enhancing the fine-grained details on low-level features, the experimental results show that our method has considerable superiority for STN and red nucleus segmentation, which can provide accurate target localization for STN-DBS.

Lead location as a determinant of motor benefit in subthalamic nucleus deep brain stimulation for Parkinson’s disease

Background

Subthalamic nucleus (STN) deep brain stimulation (DBS) is regarded as an effective treatment for patients with advanced Parkinson’s disease (PD). Clinical benefit, however, varies significantly across patients. Lead location has been hypothesized to play a critical role in determining motor outcome and may account for much of the observed variability reported among patients.

Objective

To retrospectively evaluate the relationship of lead location to motor outcomes in patients who had been implanted previously at another center by employing a novel visualization technology that more precisely determines the location of the DBS lead and its contacts with respect to each patient’s individually defined STN.

Methods

Anatomical models were generated using novel imaging in 40 PD patients who had undergone bilateral STN DBS (80 electrodes) at another center. Patient-specific models of each STN were evaluated to determine DBS electrode contact locations with respect to anterior to posterior and medial to lateral regions of the individualized STNs and compared to the change in the contralateral hemi-body Unified Parkinson’s Disease Rating Scale Part III (UPDRS-III) motor score.

Results

The greatest improvement in hemi-body motor function was found when active contacts were located within the posterolateral portion of the STN (71.5%). Motor benefit was 52 and 36% for central and anterior segments, respectively. Active contacts within the posterolateral portion also demonstrated the greatest reduction in levodopa dosage (77%).

Conclusion

The degree of motor benefit was dependent on the location of the stimulating contact within the STN. Although other factors may play a role, we provide further evidence in support of the hypothesis that lead location is a critical factor in determining clinical outcomes in STN DBS.

Advances in DBS Technology and Novel Applications: Focus on Movement Disorders

PURPOSE OF REVIEW

Deep brain stimulation (DBS) is an established treatment in several movement disorders, including Parkinson's disease, dystonia, tremor, and Tourette syndrome. In this review, we will review and discuss the most recent findings including but not limited to clinical evidence.

RECENT FINDINGS

New DBS technologies include novel hardware design (electrodes, cables, implanted pulse generators) enabling new stimulation patterns and adaptive DBS which delivers potential stimulation tailored to moment-to-moment changes in the patient's condition. Better understanding of movement disorders pathophysiology and functional anatomy has been pivotal for studying the effects of DBS on the mesencephalic locomotor region, the nucleus basalis of Meynert, the substantia nigra, and the spinal cord. Eventually, neurosurgical practice has improved with more accurate target visualization or combined targeting. A rising research domain emphasizes bridging neuromodulation and neuroprotection. Recent advances in DBS therapy bring more possibilities to effectively treat people with movement disorders. Future research would focus on improving adaptive DBS, leading more clinical trials on novel targets, and exploring neuromodulation effects on neuroprotection.

Deep brain stimulation for Parkinson’s Disease: A Review and Future Outlook

Parkinson's Disease (PD) is a neurodegenerative disorder that manifests as an impairment of motor and non-motor abilities due to a loss of dopamine input to deep brain structures. While there is presently no cure for PD, a variety of pharmacological and surgical therapeutic interventions have been developed to manage PD symptoms. This review explores the past, present and future outlooks of PD treatment, with particular attention paid to deep brain stimulation (DBS), the surgical procedure to deliver DBS, and its limitations. Finally, our group's efforts with respect to brain mapping for DBS targeting will be discussed.

Clinical applications of magnetic resonance imaging based functional and structural connectivity

Advances in computational neuroimaging techniques have expanded the armamentarium of imaging tools available for clinical applications in clinical neuroscience. Non-invasive, in vivo brain MRI structural and functional network mapping has been used to identify therapeutic targets, define eloquent brain regions to preserve, and gain insight into pathological processes and treatments as well as prognostic biomarkers. These tools have the real potential to inform patient-specific treatment strategies. Nevertheless, a realistic appraisal of clinical utility is needed that balances the growing excitement and interest in the field with important limitations associated with these techniques. Quality of the raw data, minutiae of the processing methodology, and the statistical models applied can all impact on the results and their interpretation. A lack of standardization in data acquisition and processing has also resulted in issues with reproducibility. This limitation has had a direct impact on the reliability of these tools and ultimately, confidence in their clinical use. Advances in MRI technology and computational power as well as automation and standardization of processing methods, including machine learning approaches, may help address some of these issues and make these tools more reliable in clinical use. In this review, we will highlight the current clinical uses of MRI connectomics in the diagnosis and treatment of neurological disorders; balancing emerging applications and technologies with limitations of connectivity analytic approaches to present an encompassing and appropriate perspective.

Prediction of Clinical Deep Brain Stimulation Target for Essential Tremor From 1.5 Tesla MRI Anatomical Landmarks

Background: Deep brain stimulation is an efficacious treatment for refractory essential tremor, though targeting the intra-thalamic nuclei remains challenging. Objectives: We sought to develop an inverse approach to retrieve the position of the leads in a cohort of patients operated on with optimal clinical outcomes from anatomical landmarks identifiable by 1.5 Tesla magnetic resonance imaging. Methods: The learning database included clinical outcomes and post-operative imaging from which the coordinates of the active contacts and those of anatomical landmarks were extracted. We used machine learning regression methods to build three different prediction models. External validation was performed according to a leave-one-out cross-validation. Results: Fifteen patients (29 leads) were included, with a median tremor improvement of 72% on the Fahn-Tolosa-Marin scale. Kernel ridge regression, deep neural networks, and support vector regression (SVR) were used. SVR gave the best results with a mean error of 1.33 ± 1.64 mm between the predicted target and the active contact position. Conclusion: We report an original method for the targeting in deep brain stimulation for essential tremor based on patients' radio-anatomical features. This approach will be tested in a prospective clinical trial.

Deep Brain Stimulation Can Differentiate Subregions of the Human Subthalamic Nucleus Area by EEG Biomarkers

Introduction: Precise lead localization is crucial for an optimal clinical outcome of subthalamic nucleus (STN) deep brain stimulation (DBS) treatment in patients with Parkinson's disease (PD). Currently, anatomical measures, as well as invasive intraoperative electrophysiological recordings, are used to locate DBS electrodes. The objective of this study was to find an alternative electrophysiology tool for STN DBS lead localization.

Methods: Sixty-one postoperative electrophysiology recording sessions were obtained from 17 DBS-treated patients with PD. An intraoperative physiological method automatically detected STN borders and subregions. Postoperative EEG cortical activity was measured, while STN low frequency stimulation (LFS) was applied to different areas inside and outside the STN. Machine learning models were used to differentiate stimulation locations, based on EEG analysis of engineered features.

Results: A machine learning algorithm identified the top 25 evoked response potentials (ERPs), engineered features that can differentiate inside and outside STN stimulation locations as well as within STN stimulation locations. Evoked responses in the medial and ipsilateral fronto-central areas were found to be most significant for predicting the location of STN stimulation. Two-class linear support vector machine (SVM) predicted the inside (dorso-lateral region, DLR, and ventro-medial region, VMR) vs. outside [zona incerta, ZI, STN stimulation classification with an accuracy of 0.98 and 0.82 for ZI vs. VMR and ZI vs. DLR, respectively, and an accuracy of 0.77 for the within STN (DLR vs. VMR)]. Multiclass linear SVM predicted all areas with an accuracy of 0.82 for the outside and within STN stimulation locations (ZI vs. DLR vs. VMR).

Conclusions: Electroencephalogram biomarkers can use low-frequency STN stimulation to localize STN DBS electrodes to ZI, DLR, and VMR STN subregions. These models can be used for both intraoperative electrode localization and postoperative stimulation programming sessions, and have a potential to improve STN DBS clinical outcomes.

Convolutional neural network optimizes the application of diffusion kurtosis imaging in Parkinson's disease

Objectives

The literature regarding the use of diffusion-tensor imaging-derived metrics in the evaluation of Parkinson’s disease (PD) is controversial. This study attempted to assess the feasibility of a deep-learning-based method for detecting alterations in diffusion kurtosis measurements associated with PD.

Methods

A total of 68 patients with PD and 77 healthy controls were scanned using scanner-A (3 T Skyra) (DATASET-1). Meanwhile, an additional five healthy volunteers were scanned with both scanner-A and an additional scanner-B (3 T Prisma) (DATASET-2). Diffusion kurtosis imaging (DKI) of DATASET-2 had an extra b shell compared to DATASET-1. In addition, a 3D-convolutional neural network (CNN) was trained from DATASET-2 to harmonize the quality of scalar measures of scanner-A to a similar level as scanner-B. Whole-brain unpaired t test and Tract-Based Spatial Statistics (TBSS) were performed to validate the differences between the PD and control groups using the model-fitting method and CNN-based method, respectively. We further clarified the correlation between clinical assessments and DKI results.

Results

An increase in mean diffusivity (MD) was found in the left substantia nigra (SN) in the PD group. In the right SN, fractional anisotropy (FA) and mean kurtosis (MK) values were negatively correlated with Hoehn and Yahr (H&Y) scales. In the putamen (Put), FA values were positively correlated with the H&Y scales. It is worth noting that these findings were only observed with the deep learning method. There was neither a group difference nor a correlation with clinical assessments in the SN or striatum exceeding the significance level using the conventional model-fitting method.

Conclusions

The CNN-based method improves the robustness of DKI and can help to explore PD-associated imaging features.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40708-021-00139-z.

Studying Alzheimer disease, Parkinson disease, and amyotrophic lateral sclerosis with 7-T magnetic resonance

Ultra-high-field (UHF) magnetic resonance (MR) scanners, that is, equipment operating at static magnetic field of 7 tesla (7 T) and above, enable the acquisition of data with greatly improved signal-to-noise ratio with respect to conventional MR systems (e.g., scanners operating at 1.5 T and 3 T). The change in tissue relaxation times at UHF offers the opportunity to improve tissue contrast and depict features that were previously inaccessible. These potential advantages come, however, at a cost: in the majority of UHF-MR clinical protocols, potential drawbacks may include signal inhomogeneity, geometrical distortions, artifacts introduced by patient respiration, cardiac cycle, and motion. This article reviews the 7 T MR literature reporting the recent studies on the most widespread neurodegenerative diseases: Alzheimer's disease, Parkinson's disease, and amyotrophic lateral sclerosis.

New Frontiers for Deep Brain Stimulation: Directionality, Sensing Technologies, Remote Programming, Robotic Stereotactic Assistance, Asleep Procedures, and Connectomics

Over the last few years, while expanding its clinical indications from movement disorders to epilepsy and psychiatry, the field of deep brain stimulation (DBS) has seen significant innovations. Hardware developments have introduced directional leads to stimulate specific brain targets and sensing electrodes to determine optimal settings via feedback from local field potentials. In addition, variable-frequency stimulation and asynchronous high-frequency pulse trains have introduced new programming paradigms to efficiently desynchronize pathological neural circuitry and regulate dysfunctional brain networks not responsive to conventional settings. Overall, these innovations have provided clinicians with more anatomically accurate programming and closed-looped feedback to identify optimal strategies for neuromodulation. Simultaneously, software developments have simplified programming algorithms, introduced platforms for DBS remote management via telemedicine, and tools for estimating the volume of tissue activated within and outside the DBS targets. Finally, the surgical accuracy has improved thanks to intraoperative magnetic resonance or computerized tomography guidance, network-based imaging for DBS planning and targeting, and robotic-assisted surgery for ultra-accurate, millimetric lead placement. These technological and imaging advances have collectively optimized DBS outcomes and allowed “asleep” DBS procedures. Still, the short- and long-term outcomes of different implantable devices, surgical techniques, and asleep vs. awake procedures remain to be clarified. This expert review summarizes and critically discusses these recent innovations and their potential impact on the DBS field.

Direct visualization of deep brain stimulation targets in patients with Parkinson's disease via 3-T quantitative susceptibility mapping

BACKGROUND

The direct visualization of brain nuclei on magnetic resonance (MR) images is important for target localization during deep brain stimulation (DBS) in patients with Parkinson's disease (PD). We demonstrated the superiority of 3-T high-resolution submillimeter voxel size quantitative susceptibility mapping (QSM) for delineating the subthalamic nucleus (STN) and the globus pallidus internus (GPi).

METHODS

Preoperative 3-T QSM and T2 weighted (T2w) images were obtained from ten patients with PD. Qualitative visualization scores were analyzed by two neurosurgeons on both images using a 4-point and 5-point scale, respectively. Images were also compared with regard to contrast-to-noise ratios (CNRs) and edge detection power for the STN and GPi. The Wilcoxon rank-sum test and the signed-rank test were used to compare measurements between the two images.

RESULTS

Visualization scores for the STN and GPi, the mean CNR of the STN relative to the zona incerta (ZI) and the substantia nigra, and the mean CNR of the GPi relative to the internal capsule (IC) and the globus pallidum externum, were significantly higher on QSM images than on T2w images (P < 0.01). The edge detection powers of the STN-ZI and GPi-IC on QSM were significantly larger (by 2.6- and 3.8-fold, respectively) than those on T2w images (P < 0.01). QSM detected asymmetry of the STN in two patients.

CONCLUSIONS

QSM images provided improved delineation ability for the STN and GPi when compared to T2w images. Our findings are important for patients with PD who undergo DBS surgery, particularly those with asymmetric bilateral nuclei.

Machine Learning's Application in Deep Brain Stimulation for Parkinson's Disease: A Review

Deep brain stimulation (DBS) is a surgical treatment for advanced Parkinson's disease (PD) that has undergone technological evolution that parallels an expansion in clinical phenotyping, neurophysiology, and neuroimaging of the disease state. Machine learning (ML) has been successfully used in a wide range of healthcare problems, including DBS. As computational power increases and more data become available, the application of ML in DBS is expected to grow. We review the literature of ML in DBS and discuss future opportunities for such applications. Specifically, we perform a comprehensive review of the literature from PubMed, the Institute for Scientific Information's Web of Science, Cochrane Database of Systematic Reviews, and Institute of Electrical and Electronics Engineers' (IEEE) Xplore Digital Library for ML applications in DBS. These studies are broadly placed in the following categories: (1) DBS candidate selection; (2) programming optimization; (3) surgical targeting; and (4) insights into DBS mechanisms. For each category, we provide and contextualize the current body of research and discuss potential future directions for the application of ML in DBS.

Artificial intelligence for brain diseases: A systematic review

Artificial intelligence (AI) is a major branch of computer science that is fruitfully used for analyzing complex medical data and extracting meaningful relationships in datasets, for several clinical aims. Specifically, in the brain care domain, several innovative approaches have achieved remarkable results and open new perspectives in terms of diagnosis, planning, and outcome prediction. In this work, we present an overview of different artificial intelligent techniques used in the brain care domain, along with a review of important clinical applications. A systematic and careful literature search in major databases such as Pubmed, Scopus, and Web of Science was carried out using "artificial intelligence" and "brain" as main keywords. Further references were integrated by cross-referencing from key articles. 155 studies out of 2696 were identified, which actually made use of AI algorithms for different purposes (diagnosis, surgical treatment, intra-operative assistance, and postoperative assessment). Artificial neural networks have risen to prominent positions among the most widely used analytical tools. Classic machine learning approaches such as support vector machine and random forest are still widely used. Task-specific algorithms are designed for solving specific problems. Brain images are one of the most used data types. AI has the possibility to improve clinicians' decision-making ability in neuroscience applications. However, major issues still need to be addressed for a better practical use of AI in the brain. To this aim, it is important to both gather comprehensive data and build explainable AI algorithms.

Explainable Artificial Intelligence for Neuroscience: Behavioral Neurostimulation

The use of Artificial Intelligence and machine learning in basic research and clinical neuroscience is increasing. AI methods enable the interpretation of large multimodal datasets that can provide unbiased insights into the fundamental principles of brain function, potentially paving the way for earlier and more accurate detection of brain disorders and better informed intervention protocols. Despite AI's ability to create accurate predictions and classifications, in most cases it lacks the ability to provide a mechanistic understanding of how inputs and outputs relate to each other. Explainable Artificial Intelligence (XAI) is a new set of techniques that attempts to provide such an understanding, here we report on some of these practical approaches. We discuss the potential value of XAI to the field of neurostimulation for both basic scientific inquiry and therapeutic purposes, as well as, outstanding questions and obstacles to the success of the XAI approach.

Deep Learning-Based Deep Brain Stimulation Targeting and Clinical Applications

Background

The purpose of the present study was to evaluate deep learning-based image-guided surgical planning for deep brain stimulation (DBS). We developed deep learning semantic segmentation-based DBS targeting and prospectively applied the method clinically.

Methods

T2^∗ fast gradient-echo images from 102 patients were used for training and validation. Manually drawn ground truth information was prepared for the subthalamic and red nuclei with an axial cut ∼4 mm below the anterior–posterior commissure line. A fully convolutional neural network (FCN-VGG-16) was used to ensure margin identification by semantic segmentation. Image contrast augmentation was performed nine times. Up to 102 original images and 918 augmented images were used for training and validation. The accuracy of semantic segmentation was measured in terms of mean accuracy and mean intersection over the union. Targets were calculated based on their relative distance from these segmented anatomical structures considering the Bejjani target.

Results

Mean accuracies and mean intersection over the union values were high: 0.904 and 0.813, respectively, for the 62 training images, and 0.911 and 0.821, respectively, for the 558 augmented training images when 360 augmented validation images were used. The Dice coefficient converted from the intersection over the union was 0.902 when 720 training and 198 validation images were used. Semantic segmentation was adaptive to high anatomical variations in size, shape, and asymmetry. For clinical application, two patients were assessed: one with essential tremor and another with bradykinesia and gait disturbance due to Parkinson’s disease. Both improved without complications after surgery, and microelectrode recordings showed subthalamic nuclei signals in the latter patient.

Conclusion

The accuracy of deep learning-based semantic segmentation may surpass that of previous methods. DBS targeting and its clinical application were made possible using accurate deep learning-based semantic segmentation, which is adaptive to anatomical variations.

Proceedings of the Sixth Deep Brain Stimulation Think Tank Modulation of Brain Networks and Application of Advanced Neuroimaging, Neurophysiology, and Optogenetics

The annual deep brain stimulation (DBS) Think Tank aims to create an opportunity for a multidisciplinary discussion in the field of neuromodulation to examine developments, opportunities and challenges in the field. The proceedings of the Sixth Annual Think Tank recapitulate progress in applications of neurotechnology, neurophysiology, and emerging techniques for the treatment of a range of psychiatric and neurological conditions including Parkinson’s disease, essential tremor, Tourette syndrome, epilepsy, cognitive disorders, and addiction. Each section of this overview provides insight about the understanding of neuromodulation for specific disease and discusses current challenges and future directions. This year’s report addresses key issues in implementing advanced neurophysiological techniques, evolving use of novel modulation techniques to deliver DBS, ans improved neuroimaging techniques. The proceedings also offer insights into the new era of brain network neuromodulation and connectomic DBS to define and target dysfunctional brain networks. The proceedings also focused on innovations in applications and understanding of adaptive DBS (closed-loop systems), the use and applications of optogenetics in the field of neurostimulation and the need to develop databases for DBS indications. Finally, updates on neuroethical, legal, social, and policy issues relevant to DBS research are discussed.

Automatic localization of the subthalamic nucleus on patient-specific clinical MRI by incorporating 7 T MRI and machine learning: Application in deep brain stimulation

Deep brain stimulation (DBS) of the subthalamic nucleus (STN) has shown clinical potential for relieving the motor symptoms of advanced Parkinson's disease. While accurate localization of the STN is critical for consistent across-patients effective DBS, clear visualization of the STN under standard clinical MR protocols is still challenging. Therefore, intraoperative microelectrode recordings (MER) are incorporated to accurately localize the STN. However, MER require significant neurosurgical expertise and lengthen the surgery time. Recent advances in 7 T MR technology facilitate the ability to clearly visualize the STN. The vast majority of centers, however, still do not have 7 T MRI systems, and fewer have the ability to collect and analyze the data. This work introduces an automatic STN localization framework based on standard clinical MRIs without additional cost in the current DBS planning protocol. Our approach benefits from a large database of 7 T MRI and its clinical MRI pairs. We first model in the 7 T database, using efficient machine learning algorithms, the spatial and geometric dependency between the STN and its adjacent structures (predictors). Given a standard clinical MRI, our method automatically computes the predictors and uses the learned information to predict the patient-specific STN. We validate our proposed method on clinical T2 W MRI of 80 subjects, comparing with experts-segmented STNs from the corresponding 7 T MRI pairs. The experimental results show that our framework provides more accurate and robust patient-specific STN localization than using state-of-the-art atlases. We also demonstrate the clinical feasibility of the proposed technique assessing the post-operative electrode active contact locations.