scholarly journals Clinical outcome prediction from analysis of microelectrode recordings using deep learning in subthalamic deep brain stimulation for Parkinson`s disease

PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0244133
Author(s):  
Kwang Hyon Park ◽  
Sukkyu Sun ◽  
Yong Hoon Lim ◽  
Hye Ran Park ◽  
Jae Meen Lee ◽  
...  
Keyword(s):  
Deep Learning ◽  
Deep Brain Stimulation ◽  
Clinical Outcome ◽  
General Anesthesia ◽  
Brain Stimulation ◽  
Learning Algorithm ◽  
Multitask Learning ◽  
Stn Dbs ◽  
Updrs Part ◽  
Deep Brain

Background Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is an effective treatment for improving the motor symptoms of advanced Parkinson’s disease (PD). Accurate positioning of the stimulation electrodes is necessary for better clinical outcomes. Objective We applied deep learning techniques to microelectrode recording (MER) signals to better predict motor function improvement, represented by the UPDRS part III scores, after bilateral STN DBS in patients with advanced PD. If we find the optimal stimulation point with MER by deep learning, we can improve the clinical outcome of STN DBS even under restrictions such as general anesthesia or non-cooperation of the patients. Methods In total, 696 4-second left-side MER segments from 34 patients with advanced PD who underwent bilateral STN DBS surgery under general anesthesia were included. We transformed the original signal into three wavelets of 1–50 Hz, 50–500 Hz, and 500–5,000 Hz. The wavelet-transformed MER was used for input data of the deep learning. The patients were divided into two groups, good response and moderate response groups, according to DBS on to off ratio of UPDRS part III score for the off-medication state, 6 months postoperatively. The ratio were used for output data in deep learning. The Visual Geometry Group (VGG)-16 model with a multitask learning algorithm was used to estimate the bilateral effect of DBS. Different ratios of the loss function in the task-specific layer were applied considering that DBS affects both sides differently. Results When we divided the MER signals according to the frequency, the maximal accuracy was higher in the 50–500 Hz group than in the 1–50 Hz and 500–5,000 Hz groups. In addition, when the multitask learning method was applied, the stability of the model was improved in comparison with single task learning. The maximal accuracy (80.21%) occurred when the right-to-left loss ratio was 5:1 or 6:1. The area under the curve (AUC) was 0.88 in the receiver operating characteristic (ROC) curve. Conclusion Clinical improvements in PD patients who underwent bilateral STN DBS could be predicted based on a multitask deep learning-based MER analysis.

scholarly journals Bilateral Subthalamic Nucleus Deep Brain Stimulation under General Anesthesia: Literature Review and Single Center Experience

2020 ◽  
Vol 9 (9) ◽  
pp. 3044
Author(s):  
Hye Ran Park ◽  
Yong Hoon Lim ◽  
Eun Jin Song ◽  
Jae Meen Lee ◽  
Kawngwoo Park ◽  
...  
Keyword(s):  
Deep Brain Stimulation ◽  
Clinical Outcome ◽  
General Anesthesia ◽  
Subthalamic Nucleus ◽  
Brain Stimulation ◽  
Intraoperative Imaging ◽  
Single Center ◽  
Single Center Experience ◽  
Stn Dbs ◽  
Deep Brain

Bilateral subthalamic nucleus (STN) Deep brain stimulation (DBS) is a well-established treatment in patients with Parkinson’s disease (PD). Traditionally, STN DBS for PD is performed by using microelectrode recording (MER) and/or intraoperative macrostimulation under local anesthesia (LA). However, many patients cannot tolerate the long operation time under LA without medication. In addition, it cannot be even be performed on PD patients with poor physical and neurological condition. Recently, it has been reported that STN DBS under general anesthesia (GA) can be successfully performed due to the feasible MER under GA, as well as the technical advancement in direct targeting and intraoperative imaging. The authors reviewed the previously published literature on STN DBS under GA using intraoperative imaging and MER, focused on discussing the technique, clinical outcome, and the complication, as well as introducing our single-center experience. Based on the reports of previously published studies and ours, GA did not interfere with the MER signal from STN. STN DBS under GA without intraoperative stimulation shows similar or better clinical outcome without any additional complication compared to STN DBS under LA. Long-term follow-up with a large number of the patients would be necessary to validate the safety and efficacy of STN DBS under GA.

scholarly journals Deep brain stimulation outcomes in patients implanted under general anesthesia with frame-based stereotaxy and intraoperative MRI

2018 ◽  
Vol 129 (6) ◽  
pp. 1572-1578 ◽  
Author(s):  
Caio M. Matias ◽  
Leonardo A. Frizon ◽  
Sean J. Nagel ◽  
Darlene A. Lobel ◽  
André G. Machado
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Deep Brain Stimulation ◽  
General Anesthesia ◽  
Brain Stimulation ◽  
Intraoperative Mri ◽  
Significant Difference ◽  
Preoperative Plan ◽  
Updrs Part ◽  
Deep Brain

OBJECTIVEThe authors’ aim in this study was to evaluate placement accuracy and clinical outcomes in patients who underwent implantation of deep brain stimulation devices with the aid of frame-based stereotaxy and intraoperative MRI after induction of general anesthesia.METHODSThirty-three patients with movement disorders (27 with Parkinson’s disease) underwent implantation of unilateral or bilateral deep brain stimulation systems (64 leads total). All patients underwent the implantation procedure with standard frame-based techniques under general anesthesia and without microelectrode recording. MR images were acquired immediately after the procedure and fused to the preoperative plan to verify accuracy. To evaluate clinical outcome, different scales were used to assess quality of life (EQ-5D), activities of daily living (Unified Parkinson’s Disease Rating Scale [UPDRS] part II), and motor function (UPDRS part III during off- and on-medication and off- and on-stimulation states). Accuracy was assessed by comparing the coordinates (x, y, and z) from the preoperative plan and coordinates from the tip of the lead on intraoperative MRI and postoperative CT scans.RESULTSThe EQ-5D score improved or remained stable in 71% of the patients. When in the off-medication/on-stimulation state, all patients reported significant improvement in UPDRS III score at the last follow-up (p < 0.001), with a reduction of 25.2 points (46.3%) (SD 14.7 points and 23.5%, respectively). There was improvement or stability in the UPDRS II scores for 68% of the Parkinson’s patients. For 2 patients, the stereotactic error was deemed significant based on intraoperative MRI findings. In these patients, the lead was removed and replaced after correcting for the error during the same procedure. Postoperative lead revision was not necessary in any of the patients. Based on findings from the last intraoperative MRI study, the mean difference between the tip of the electrode and the planned target was 0.82 mm (SD 0.5 mm, p = 0.006) for the x-axis, 0.67 mm (SD 0.5 mm, p < 0.001) for the y-axis, and 0.78 mm (SD 0.7 mm, p = 0.008) for the z-axis. On average, the euclidian distance was 1.52 mm (SD 0.6 mm). In patients who underwent bilateral implantation, accuracy was further evaluated comparing the first implanted side and the second implanted side. There was a significant mediolateral (x-axis) difference (p = 0.02) in lead accuracy between the first (mean 1.02 mm, SD 0.57 mm) and the second (mean 0.66 mm, SD 0.50 mm) sides. However, no significant difference was found for the y- and z-axes (p = 0.10 and p = 0.89, respectively).CONCLUSIONSFrame-based DBS implantation under general anesthesia with intraoperative MRI verification of lead location is safe, accurate, precise, and effective compared with standard implantation performed using awake intraoperative physiology. More clinical trials are necessary to directly compare outcomes of each technique.

Unilateral deep brain stimulation of the subthalamic nucleus for Parkinson disease

2007 ◽  
Vol 106 (4) ◽  
pp. 626-632 ◽  
Author(s):  
Jerzy L. Slowinski ◽  
John D. Putzke ◽  
Ryan J. Uitti ◽  
John A. Lucas ◽  
Margaret F. Turk ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Deep Brain Stimulation ◽  
Parkinson Disease ◽  
Subthalamic Nucleus ◽  
Brain Stimulation ◽  
Mental Flexibility ◽  
Stn Dbs ◽  
Updrs Part ◽  
Deep Brain

Object The object of this study was to assess the results of unilateral deep brain stimulation (DBS) of the subthalamic nucleus (STN) for management of advanced Parkinson disease (PD). Methods A clinical series of 24 patients (mean age 71 years, range 56–80 years) with medically intractable PD, who were undergoing unilateral magnetic resonance imaging–targeted, electrophysiologically guided STN DBS, completed a battery of qualitative and quantitative outcome measures preoperatively (baseline) and postoperatively, using a modified Core Assessment Program for Intracerebral Transplantations protocol. The mean follow-up period was 9 months. Statistically significant improvement was observed in the Unified Parkinson's Disease Rating Scale (UPDRS) Part II score (18%), the total UPDRS PART III score (31%), the contralateral UPDRS Part III score (63%), and scores for axial motor features (19%), contralateral tremor (88%), rigidity (60%), bradykinesia (54%), and dyskinesia (69%), as well as the Parkinson's Disease Quality of Life questionnaire score (15%) in the on-stimulation state compared with baseline. Ipsilateral symptoms improved by approximately 15% or less. Performance on the Purdue pegboard test improved in the contralateral hand in the on-stimulation state compared with the off-stimulation state (38%, p < 0.05). The daily levodopa-equivalent dose was reduced by 21% (p = 0.018). Neuropsychological tests revealed an improvement in mental flexibility and a trend toward reduced letter fluency. There were no permanent surgical complications. Of the 16 participants with symmetrical disease, five required implantation of the DBS unit on the second side. Conclusions Unilateral STN DBS is an effective and safe treatment for selected patients with advanced PD. Unilateral STN DBS provides improvement of contralateral motor symptoms of PD as well as quality of life, reduces requirements for medication, and possibly enhances mental flexibility. This method of surgical treatment may be associated with a reduced risk and may provide an alternative to bilateral STN DBS for PD, especially in older patients or patients with asymmetry of parkinsonism.

Striatal dopamine transporter availability and individual clinical course within the 1-year follow-up of deep brain stimulation of the subthalamic nucleus in patients with Parkinson’s disease

2021 ◽  
pp. 1-7
Author(s):  
Julia Löser ◽  
Julia Luthardt ◽  
Michael Rullmann ◽  
David Weise ◽  
Osama Sabri ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Deep Brain Stimulation ◽  
Clinical Outcome ◽  
Dopamine Transporter ◽  
Subthalamic Nucleus ◽  
Brain Stimulation ◽  
Striatal Dopamine ◽  
Stn Dbs ◽  
Deep Brain

OBJECTIVEDegeneration of dopaminergic neurons in the substantia nigra projecting to the striatum is responsible for the motor symptoms in Parkinson’s disease (PD). Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is a well-established procedure to alleviate these symptoms in advanced PD. Yet the mechanism of action, especially the effects of STN-DBS on the availability of striatal dopamine transporter (DAT) as a marker of nigrostriatal nerve cell function, remains largely unknown. The aim of this study was therefore to evaluate whether 1) DAT availability changes within 1 year of STN-DBS and 2) the clinical outcome can be predicted based on preoperative DAT availability.METHODSTwenty-seven PD patients (mean age 62.7 ± 8.9 years; mean duration of illness 13.0 ± 4.9 years; PD subtypes: akinetic-rigid, n = 11; equivalence, n = 13; and tremor-dominant, n = 3) underwent [123I]FP-CIT SPECT preoperatively and after 1 year of STN-DBS. DAT availability as determined by the specific binding ratio (SBR) was assessed by volume of interest (VOI) analysis of the caudate nucleus and the putamen ipsilateral and contralateral to the clinically more affected side.RESULTSUnified Parkinson’s Disease Rating Scale (UPDRS) III scores improved significantly (mean preoperative on medication 25.6 ± 12.3, preoperative off medication 42.3 ± 15.2, postoperative on medication/off stimulation 41.4 ± 13.2, and postoperative on medication/on stimulation 16.1 ± 9.4; preoperative on medication vs postoperative on medication/on stimulation, p = 0.006), while the levodopa-equivalent daily dose was reduced (mean preoperative 957 ± 440 mg vs postoperative 313 ± 189 mg, p < 0.001). The SBR did not differ significantly before and 1 year after DBS, regardless of PD subtype. Preoperative DAT availability was not related to the change in UPDRS III score, but the change in DAT availability was significantly correlated with the change in UPDRS III score (contralateral head of the caudate VOI, p = 0.014; contralateral putamen VOI, p = 0.018).CONCLUSIONSOverall, DAT availability did not change significantly after 1 year of STN-DBS. However, on an individual basis, the improvement in UPDRS III score was associated with an increase in DAT availability, whereas DAT availability before STN-DBS surgery did not predict the clinical outcome. Whether a subtype-specific pattern of preoperative DAT availability can become a reliable predictor of successful STN-DBS must be evaluated in larger study cohorts.

Mapping efficacious deep brain stimulation for pediatric dystonia

2021 ◽  
pp. 1-11
Author(s):  
Ailish Coblentz ◽  
Gavin J. B. Elias ◽  
Alexandre Boutet ◽  
Jurgen Germann ◽  
Musleh Algarni ◽  
...  
Keyword(s):  
Deep Brain Stimulation ◽  
Clinical Outcome ◽  
Brain Stimulation ◽  
Pediatric Patients ◽  
Rating Scale ◽  
Structural Connectivity ◽  
Response To Treatment ◽  
Internal Globus Pallidus ◽  
Probabilistic Map ◽  
Deep Brain

OBJECTIVEThe objective of this study was to report the authors’ experience with deep brain stimulation (DBS) of the internal globus pallidus (GPi) as a treatment for pediatric dystonia, and to elucidate substrates underlying clinical outcome using state-of-the-art neuroimaging techniques.METHODSA retrospective analysis was conducted in 11 pediatric patients (6 girls and 5 boys, mean age 12 ± 4 years) with medically refractory dystonia who underwent GPi-DBS implantation between June 2009 and September 2017. Using pre- and postoperative MRI, volumes of tissue activated were modeled and weighted by clinical outcome to identify brain regions associated with clinical outcome. Functional and structural networks associated with clinical benefits were also determined using large-scale normative data sets.RESULTSA total of 21 implanted leads were analyzed in 11 patients. The average follow-up duration was 19 ± 20 months (median 5 months). Using a 7-point clinical rating scale, 10 patients showed response to treatment, as defined by scores < 3. The mean improvement in the Burke-Fahn-Marsden Dystonia Rating Scale motor score was 40% ± 23%. The probabilistic map of efficacy showed that the voxel cluster most associated with clinical improvement was located at the posterior aspect of the GPi, comparatively posterior and superior to the coordinates of the classic GPi target. Strong functional and structural connectivity was evident between the probabilistic map and areas such as the precentral and postcentral gyri, parietooccipital cortex, and brainstem.CONCLUSIONSThis study reported on a series of pediatric patients with dystonia in whom GPi-DBS resulted in variable clinical benefit and described a clinically favorable stimulation site for this cohort, as well as its structural and functional connectivity. This information could be valuable for improving surgical planning, simplifying programming, and further informing disease pathophysiology.

scholarly journals Fully Automated Targeting Using Nonrigid Image Registration Matches Accuracy and Exceeds Precision of Best Manual Approaches to Subthalamic Deep Brain Stimulation Targeting in Parkinson Disease

Neurosurgery ◽  
2015 ◽  
Vol 76 (6) ◽  
pp. 756-765 ◽  
Author(s):  
Srivatsan Pallavaram ◽  
Pierre-François D'Haese ◽  
Wendell Lake ◽  
Peter E. Konrad ◽  
Benoit M. Dawant ◽  
...  
Keyword(s):  
Deep Brain Stimulation ◽  
Image Registration ◽  
Parkinson Disease ◽  
Brain Stimulation ◽  
Red Nucleus ◽  
Nonrigid Image Registration ◽  
Direct Targeting ◽  
Fully Automatic ◽  
Stn Dbs ◽  
Deep Brain

Abstract BACKGROUND: Finding the optimal location for the implantation of the electrode in deep brain stimulation (DBS) surgery is crucial for maximizing the therapeutic benefit to the patient. Such targeting is challenging for several reasons, including anatomic variability between patients as well as the lack of consensus about the location of the optimal target. OBJECTIVE: To compare the performance of popular manual targeting methods against a fully automatic nonrigid image registration-based approach. METHODS: In 71 Parkinson disease subthalamic nucleus (STN)-DBS implantations, an experienced functional neurosurgeon selected the target manually using 3 different approaches: indirect targeting using standard stereotactic coordinates, direct targeting based on the patient magnetic resonance imaging, and indirect targeting relative to the red nucleus. Targets were also automatically predicted by using a leave-one-out approach to populate the CranialVault atlas with the use of nonrigid image registration. The different targeting methods were compared against the location of the final active contact, determined through iterative clinical programming in each individual patient. RESULTS: Targeting by using standard stereotactic coordinates corresponding to the center of the motor territory of the STN had the largest targeting error (3.69 mm), followed by direct targeting (3.44 mm), average stereotactic coordinates of active contacts from this study (3.02 mm), red nucleus-based targeting (2.75 mm), and nonrigid image registration-based automatic predictions using the CranialVault atlas (2.70 mm). The CranialVault atlas method had statistically smaller variance than all manual approaches. CONCLUSION: Fully automatic targeting based on nonrigid image registration with the use of the CranialVault atlas is as accurate and more precise than popular manual methods for STN-DBS.

Successful Deep Brain Stimulation Surgery With Intraoperative Magnetic Resonance Imaging on a Difficult Neuroacanthocytosis Case

Neurosurgery ◽  
2013 ◽  
Vol 73 (1) ◽  
pp. E184-E188 ◽  
Author(s):  
Thien Thien Lim ◽  
Hubert H. Fernandez ◽  
Scott Cooper ◽  
Kathryn Mary K. Wilson ◽  
Andre G. Machado
Keyword(s):  
Magnetic Resonance Imaging ◽  
Deep Brain Stimulation ◽  
Magnetic Resonance ◽  
General Anesthesia ◽  
Brain Stimulation ◽  
Resonance Imaging ◽  
Imaging Guidance ◽  
Intraoperative Magnetic Resonance Imaging ◽  
Magnetic Resonance Imaging Guidance ◽  
Deep Brain

Abstract BACKGROUND AND IMPORTANCE: Chorea acanthocytosis is a progressive hereditary neurodegenerative disorder characterized by hyperkinetic movements, seizures, and acanthocytosis in the absence of any lipid abnormality. Medical treatment is typically limited and disappointing. CLINICAL PRESENTATION: We report on a 32-year-old patient with chorea acanthocytosis with a failed attempt at awake deep brain stimulation (DBS) surgery due to intraoperative seizures and postoperative intracranial hematoma. He then underwent a second DBS operation, but under general anesthesia and with intraoperative magnetic resonance imaging guidance. Marked improvement in his dystonia, chorea, and overall quality of life was noted 2 and 8 months postoperatively. CONCLUSION: DBS surgery of the bilateral globus pallidus pars interna may be useful in controlling the hyperkinetic movements in neuroacanthocytosis. Because of the high propensity for seizures in this disorder, DBS performed under general anesthesia, with intraoperative magnetic resonance imaging guidance, may allow successful implantation while maintaining accurate target localization.

135 A Comparison of Outcomes Between Deep Brain Stimulation Under General Anesthesia Versus Conscious Sedation With Awake Evaluation

Neurosurgery ◽  
2016 ◽  
Vol 63 ◽  
pp. 155 ◽  
Author(s):  
François Alesch ◽  
Roshini Jain ◽  
Lilly Chen ◽  
Thomas Brucke ◽  
Fernando Seijo ◽  
...  
Keyword(s):  
Deep Brain Stimulation ◽  
General Anesthesia ◽  
Brain Stimulation ◽  
Conscious Sedation ◽  
Deep Brain

scholarly journals Dynamic Network Connectivity Reveals Markers of Response to Deep Brain Stimulation in Parkinson’s Disease

2021 ◽  
Vol 15 ◽  
Author(s):  
Chengyuan Wu ◽  
Caio Matias ◽  
Thomas Foltynie ◽  
Patricia Limousin ◽  
Ludvic Zrinzo ◽  
...  
Keyword(s):  
Graph Theory ◽  
Deep Brain Stimulation ◽  
Brain Stimulation ◽  
Theory Analysis ◽  
Whole Brain ◽  
Network Properties ◽  
Brain States ◽  
Graph Theory Analysis ◽  
Stn Dbs ◽  
Deep Brain

Background: Neuronal loss in Parkinson’s Disease (PD) leads to widespread neural network dysfunction. While graph theory allows for analysis of whole brain networks, patterns of functional connectivity (FC) associated with motor response to deep brain stimulation of the subthalamic nucleus (STN-DBS) have yet to be explored.Objective/Hypothesis: To investigate the distributed network properties associated with STN-DBS in patients with advanced PD.Methods: Eighteen patients underwent 3-Tesla resting state functional MRI (rs-fMRI) prior to STN-DBS. Improvement in UPDRS-III scores following STN-DBS were assessed 1 year after implantation. Independent component analysis (ICA) was applied to extract spatially independent components (ICs) from the rs-fMRI. FC between ICs was calculated across the entire time series and for dynamic brain states. Graph theory analysis was performed to investigate whole brain network topography in static and dynamic states.Results: Dynamic analysis identified two unique brain states: a relative hypoconnected state and a relative hyperconnected state. Time spent in a state, dwell time, and number of transitions were not correlated with DBS response. There were no significant FC findings, but graph theory analysis demonstrated significant relationships with STN-DBS response only during the hypoconnected state – STN-DBS was negatively correlated with network assortativity.Conclusion: Given the widespread effects of dopamine depletion in PD, analysis of whole brain networks is critical to our understanding of the pathophysiology of this disease. Only by leveraging graph theoretical analysis of dynamic FC were we able to isolate a hypoconnected brain state that contained distinct network properties associated with the clinical effects of STN-DBS.

Sign in / Sign up

Export Citation Format

Share Document