Real-time machine learning classification of pallidal borders during deep brain stimulation surgery

Machine learning for adaptive deep brain stimulation in Parkinson's disease: closing the loop

Parkinson's disease (PD) is the second most common neurodegenerative disease bearing a severe social and economic impact. So far, there is no known disease modifying therapy and the current available treatments are symptom oriented. Deep Brain Stimulation (DBS) is established as an effective treatment for PD, however current systems lag behind today's technological potential. Adaptive DBS, where stimulation parameters depend on the patient's physiological state, emerges as an important step towards "smart" DBS, a strategy that enables adaptive stimulation and personalized therapy. This new strategy is facilitated by currently available neurotechnologies allowing the simultaneous monitoring of multiple signals, providing relevant physiological information. Advanced computational models and analytical methods are an important tool to explore the richness of the available data and identify signal properties to close the loop in DBS. To tackle this challenge, machine learning (ML) methods applied to DBS have gained popularity due to their ability to make good predictions in the presence of multiple variables and subtle patterns. ML based approaches are being explored at different fronts such as the identification of electrophysiological biomarkers and the development of personalized control systems, leading to effective symptom relief. In this review, we explore how ML can help overcome the challenges in the development of closed-loop DBS, particularly its role in the search for effective electrophysiology biomarkers. Promising results demonstrate ML potential for supporting a new generation of adaptive DBS, with better management of stimulation delivery, resulting in more efficient and patient-tailored treatments.

The Genetic Etiology of Parkinson's Disease Does Not Robustly Affect Subthalamic Physiology

BACKGROUND

It is unknown whether Parkinson's disease (PD) genetic heterogeneity, leading to phenotypic and pathological variability, is also associated with variability in the unique PD electrophysiological signature. Such variability might have practical implications for adaptive deep brain stimulation (DBS).

OBJECTIVE

The aim of our work was to study the electrophysiological activity in the subthalamic nucleus (STN) of patients with PD with pathogenic variants in different disease-causing genes.

METHODS

Electrophysiological data from participants with negative genetic tests were compared with those from GBA, LRRK2, and PRKN-PD.

RESULTS

We analyzed data from 93 STN trajectories (GBA-PD: 28, LRRK2-PD: 22, PARK-PD: 10, idiopathic PD: 33) of 52 individuals who underwent DBS surgery. Characteristics of β oscillatory activity in the dorsolateral motor part of the STN were similar for patients with negative genetic tests and for patients with different forms of monogenic PD.

CONCLUSIONS

The genetic heterogeneity in PD is not associated with electrophysiological differences. Therefore, similar adaptive DBS algorithms would be applicable to genetically heterogeneous patient populations. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Localization of deep brain stimulation trajectories via automatic mapping of microelectrode recordings to MRI

Objective. Suboptimal electrode placement during subthalamic nucleus deep brain stimulation (STN DBS) surgery may arise from several sources, including frame-based targeting errors and intraoperative brain shift. We present a computer algorithm that can accurately localize intraoperative microelectrode recording (MER) tracks on preoperative magnetic resonance imaging (MRI) in real-time, thereby predicting deviation between the surgical plan and the MER trajectories.Approach. Random forest (RF) modeling was used to derive a statistical relationship between electrophysiological features on intraoperative MER and voxel intensity on preoperative T2-weighted MR imaging. This model was integrated into a larger algorithm that can automatically localize intraoperative MER recording tracks on preoperative MRI in real-time. To verify accuracy, targeting error of both the planned intraoperative trajectory ('planned') and the algorithm-derived trajectory ('calculated') was estimated by measuring deviation from the final DBS lead location on postoperative high-resolution computed tomography ('actual').Main results. MR imaging and MERs were obtained from 24 STN DBS implant trajectories. The cross-validated RF model could accurately distinguish between gray and white matter regions along MER trajectories (AUC 0.84). When applying this model within the localization algorithm, thecalculatedMER trajectory estimate was found to be significantly closer to theactualDBS lead when compared to theplannedtrajectory recorded during surgery (1.04 mm vs 1.52 mm deviation,p< 0.002), with improvement shown in 19/24 cases (79%). When applying the algorithm to simulated DBS trajectory plans with randomized targeting error, up to 4 mm of error could be resolved to <2 mm on average (p< 0.0001).Significance. This work presents an automated system for intraoperative localization of electrodes during STN DBS surgery. This neuroengineering solution may enhance the accuracy of electrode position estimation, particularly in cases where high-resolution intraoperative imaging is not available.

[Robotics and computer-assisted procedures in cranial neurosurgery]

BACKGROUND

The medical technical innovations over the last decade have made operations in the highly sensitive regions of the brain much safer.

OBJECTIVE

Presentation of how far computer assistance and robotics have become incorporated into clinical neurosurgery.

MATERIAL AND METHOD

Evaluation of the scientific literature and analysis of the certification status of the corresponding medical devices.

RESULTS

The rapid development of computer technology and the switch to digital imaging has led to the widespread introduction of neurosurgical planning software and intraoperative neuronavigation. In the field of robotics, the penetration into clinical neurosurgery is currently still largely limited to the automatic setting of trajectories.

CONCLUSION

The digitalization of imaging has fundamentally transformed neurosurgery. In the field of cranial neurosurgery, computer-assisted procedures can now be distinguished from noncomputer-assisted procedures only in a handful of cases. In the coming years important innovations for the clinical implementation can be expected in the field of robotics.

Clinical neuroscience and neurotechnology: An amazing symbiosis

In the last decades, clinical neuroscience found a novel ally in neurotechnologies, devices able to record and stimulate electrical activity in the nervous system. These technologies improved the ability to diagnose and treat neural disorders. Neurotechnologies are concurrently enabling a deeper understanding of healthy and pathological dynamics of the nervous system through stimulation and recordings during brain implants. On the other hand, clinical neurosciences are not only driving neuroengineering toward the most relevant clinical issues, but are also shaping the neurotechnologies thanks to clinical advancements. For instance, understanding the etiology of a disease informs the location of a therapeutic stimulation, but also the way stimulation patterns should be designed to be more effective/naturalistic. Here, we describe cases of fruitful integration such as Deep Brain Stimulation and cortical interfaces to highlight how this symbiosis between clinical neuroscience and neurotechnology is closer to a novel integrated framework than to a simple interdisciplinary interaction.

Machine learning in deep brain stimulation: A systematic review

Deep Brain Stimulation (DBS) is an increasingly common therapy for a large range of neurological disorders, such as abnormal movement disorders. The effectiveness of DBS in terms of controlling patient symptomatology has made this procedure increasingly used over the past few decades. Concurrently, the popularity of Machine Learning (ML), a subfield of artificial intelligence, has skyrocketed and its influence has more recently extended to medical domains such as neurosurgery. Despite its growing research interest, there has yet to be a literature review specifically on the use of ML in DBS. We have followed a fully systematic methodology to obtain a corpus of 73 papers. In each paper, we identified the clinical application, the type/amount of data used, the method employed, and the validation strategy, further decomposed into 12 different sub-categories. The papers overall illustrated some existing trends in how ML is used in the context of DBS, including the breath of the problem domain and evolving techniques, as well as common frameworks and limitations. This systematic review analyzes at a broad level how ML have been recently used to address clinical problems on DBS, giving insight into how these new computational methods are helping to push the state-of-the-art of functional neurosurgery. DBS clinical workflow is complex, involves many specialists, and raises several clinical issues which have partly been addressed with artificial intelligence. However, several areas remain and those that have been recently addressed with ML are by no means considered "solved" by the community nor are they closed to new and evolving methods.

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.

Toward asleep DBS: cortico-basal ganglia spectral and coherence activity during interleaved propofol/ketamine sedation mimics NREM/REM sleep activity

Deep brain stimulation (DBS) is currently a standard procedure for advanced Parkinson's disease. Many centers employ awake physiological navigation and stimulation assessment to optimize DBS localization and outcome. To enable DBS under sedation, asleep DBS, we characterized the cortico-basal ganglia neuronal network of two nonhuman primates under propofol, ketamine, and interleaved propofol-ketamine (IPK) sedation. Further, we compared these sedation states in the healthy and Parkinsonian condition to those of healthy sleep. Ketamine increases high-frequency power and synchronization while propofol increases low-frequency power and synchronization in polysomnography and neuronal activity recordings. Thus, ketamine does not mask the low-frequency oscillations used for physiological navigation toward the basal ganglia DBS targets. The brain spectral state under ketamine and propofol mimicked rapid eye movement (REM) and Non-REM (NREM) sleep activity, respectively, and the IPK protocol resembles the NREM-REM sleep cycle. These promising results are a meaningful step toward asleep DBS with nondistorted physiological navigation.

Deep Brain Stimulation Initiative: Toward Innovative Technology, New Disease Indications, and Approaches to Current and Future Clinical Challenges in Neuromodulation Therapy

Deep brain stimulation (DBS) is one of the most important clinical therapies for neurological disorders. DBS also has great potential to become a great tool for clinical neuroscience research. Recently, the National Engineering Laboratory for Neuromodulation at Tsinghua University held an international Deep Brain Stimulation Initiative workshop to discuss the cutting-edge technological achievements and clinical applications of DBS. We specifically addressed new clinical approaches and challenges in DBS for movement disorders (Parkinson's disease and dystonia), clinical application toward neurorehabilitation for stroke, and the progress and challenges toward DBS for neuropsychiatric disorders. This review highlighted key developments in (1) neuroimaging, with advancements in 3-Tesla magnetic resonance imaging DBS compatibility for exploration of brain network mechanisms; (2) novel DBS recording capabilities for uncovering disease pathophysiology; and (3) overcoming global healthcare burdens with online-based DBS programming technology for connecting patient communities. The successful event marks a milestone for global collaborative opportunities in clinical development of neuromodulation to treat major neurological disorders.

An intra-operative feature-based classification of microelectrode recordings to support the subthalamic nucleus functional identification during deep brain stimulation surgery

OBJECTIVE

The Subthalamic Nucleus (STN) is the most selected target for the placement of the Deep Brain Stimulation (DBS) electrode to treat Parkinson's disease. Its identification is a delicate and challenging task which is based on the interpretation of the STN functional activity acquired through microelectrode recordings (MER). Aim of this work is to explore the potentiality of a set of twenty-five features to build a classification model for the discrimination of MER signals belonging to the STN.

APPROACH

We explored the use of different sets of spike-dependent and spike-independent features in combination with an Ensemble Trees classification (ET) algorithm on a dataset composed of thirteen patients receiving bilateral DBS. We compared results from six subsets of features and two dataset conditions (with and without standardization) using performance metrics on a leave-one-patient-out validation schema.

MAIN RESULTS

We obtained statistically better results (i.e., higher accuracy p-value = 0.003) on the raw dataset than on the standardized one, where the selection of seven features using a minimum redundancy maximum relevance (MRMR) algorithm provided a mean accuracy of 94.1%, comparable with the use of the full set of features. In the same conditions, the spike-dependent features provided the lowest accuracy (86.8%), while a power density-based index was shown to be a good indicator of STN activity (92.3%).

SIGNIFICANCE

Results suggest that a small and simple set of features can be used for an efficient classification of microelectrode recordings to implement an intraoperative support for clinical decision during deep brain stimulation surgery.

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.

Intraoperative changes in the H-reflex pathway during deep brain stimulation surgery for Parkinson's disease: A potential biomarker for optimal electrode placement

BACKGROUND

Deep Brain Stimulation (DBS) targeting the subthalamic nucleus (STN) and globus pallidus interna (GPi) is an effective treatment for cardinal motor symptoms and motor complications in Parkinson's Disease (PD). However, malpositioned DBS electrodes can result in suboptimal therapeutic response.

OBJECTIVE

We explored whether recovery of the H-reflex-an easily measured electrophysiological analogue of the stretch reflex, known to be altered in PD-could serve as an adjunct biomarker of suboptimal versus optimal electrode position during STN- or GPi-DBS implantation.

METHODS

Changes in soleus H-reflex recovery were investigated intraoperatively throughout awake DBS target refinement across 26 nuclei (14 STN). H-reflex recovery was evaluated during microelectrode recording (MER) and macrostimulation at multiple locations within and outside target nuclei, at varying stimulus intensities.

RESULTS

Following MER, H-reflex recovery normalized (i.e., became less Parkinsonian) in 21/26 nuclei, and correlated with on-table motor improvement consistent with an insertional effect. During macrostimulation, H-reflex recovery was maximally normalized in 23/26 nuclei when current was applied at the location within the nucleus producing optimal motor benefit. At these optimal sites, H-reflex normalization was greatest at stimulation intensities generating maximum motor benefit free of stimulation-induced side effects, with subthreshold or suprathreshold intensities generating less dramatic normalization.

CONCLUSION

H-reflex recovery is modulated by stimulation of the STN or GPi in patients with PD and varies depending on the location and intensity of stimulation within the target nucleus. H-reflex recovery shows potential as an easily-measured, objective, patient-specific, adjunct biomarker of suboptimal versus optimal electrode position during DBS surgery for PD.

What is the true discharge rate and pattern of the striatal projection neurons in Parkinson's disease and Dystonia?

Dopamine and striatal dysfunctions play a key role in the pathophysiology of Parkinson's disease (PD) and Dystonia, but our understanding of the changes in the discharge rate and pattern of striatal projection neurons (SPNs) remains limited. Here, we recorded and examined multi-unit signals from the striatum of PD and dystonic patients undergoing deep brain stimulation surgeries. Contrary to earlier human findings, we found no drastic changes in the spontaneous discharge of the well-isolated and stationary SPNs of the PD patients compared to the dystonic patients or to the normal levels of striatal activity reported in healthy animals. Moreover, cluster analysis using SPN discharge properties did not characterize two well-separated SPN subpopulations, indicating no SPN subpopulation-specific (D1 or D2 SPNs) discharge alterations in the pathological state. Our results imply that small to moderate changes in spontaneous SPN discharge related to PD and Dystonia are likely amplified by basal ganglia downstream structures.