Deep Neural Networks for Context-Dependent Deep Brain Stimulation

2019 ◽  
Author(s):  
Andrew Haddock ◽  
Howard J. Chizeck ◽  
Andrew L. Ko
Keyword(s):  
Neural Networks ◽  
Deep Brain Stimulation ◽  
Brain Stimulation ◽  
Deep Neural Networks ◽  
Context Dependent ◽  
Deep Brain

scholarly journals Dropout in Neural Networks Simulates the Paradoxical Effects of Deep Brain Stimulation on Memory

2020 ◽  
Author(s):  
Shawn Zheng Kai Tan ◽  
Richard Du ◽  
Jose Angelo Udal Perucho ◽  
Shauhrat S. Chopra ◽  
Varut Vardhanabhuti ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Brain Stimulation ◽  
Transfer Learning ◽  
Brain Stimulation ◽  
Paradoxical Effects ◽  
Rate Of Learning ◽  
Promising Treatment ◽  
Brain Target ◽  
Accuracy Of Prediction ◽  
Deep Brain

AbstractNeuromodulation techniques such as Deep Brain Stimulation (DBS) are a promising treatment for memory-related disorders including anxiety, addiction, and dementia. However, the outcome of these treatments appears to be paradoxical, as the use of these techniques can both disrupt and enhance memory even when applied to the same brain target. In this paper, we hypothesize that disruption and enhancement of memory through neuromodulation can be explained by the dropout of engram nodes. We used a convolutional neural network to classify handwritten digits and letters, applying dropout at different stages to simulate DBS effects on engrams. We showed that dropout applied during training improves the accuracy of prediction, whereas dropout applied during testing dramatically decreases accuracy of prediction, which mimics enhancement and disruption of memory, respectively. We further showed that transfer learning of neural networks with dropout had increased accuracy and rate of learning. Dropout during training provided a more robust “skeleton” network where transfer learning can be applied, mimicking the effects of chronic DBS on memory. Overall, we show that dropout of nodes can be a potential mechanism by which neuromodulation techniques such as DBS can both disrupt and enhance memory and provides a unique perspective on this paradox.

scholarly journals Predicting in vivo MRI Gradient-Field Induced Voltage Levels on Implanted Deep Brain Stimulation Systems Using Neural Networks

2020 ◽  
Vol 14 ◽  
Author(s):  
M. Arcan Erturk ◽  
Eric Panken ◽  
Mark J. Conroy ◽  
Jonathan Edmonson ◽  
Jeff Kramer ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Brain Stimulation ◽  
Brain Stimulation ◽  
Gradient Field ◽  
Induced Voltage ◽  
Deep Brain

scholarly journals Dropout in Neural Networks Simulates the Paradoxical Effects of Deep Brain Stimulation on Memory

2020 ◽  
Vol 12 ◽  
Author(s):  
Shawn Zheng Kai Tan ◽  
Richard Du ◽  
Jose Angelo Udal Perucho ◽  
Shauhrat S. Chopra ◽  
Varut Vardhanabhuti ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Brain Stimulation ◽  
Brain Stimulation ◽  
Paradoxical Effects ◽  
Deep Brain

scholarly journals Deep Brain Stimulation for Essential Tremor and Other Tremor Syndromes: A Narrative Review of Current Targets and Clinical Outcomes

2020 ◽  
Author(s):  
Christian Iorio-Morin ◽  
Anton Fomenko ◽  
Suneil Kalia
Keyword(s):  
Multiple Sclerosis ◽  
Neural Networks ◽  
Deep Brain Stimulation ◽  
Essential Tremor ◽  
Surgical Management ◽  
Brain Stimulation ◽  
Future Directions ◽  
Prevalent Symptom ◽  
Multiple Conditions ◽  
Deep Brain

Tremor is a prevalent symptom associated with multiple conditions, including Essential Tremor (ET), Parkinson’s disease (PD), multiple sclerosis (MS), stroke, and trauma. The surgical management of tremor evolved from stereotactic lesions to deep-brain stimulation (DBS), which allowed safe and reversible interference with specific neural networks. This paper reviews the current literature on DBS for tremor, starting with a detailed discussion of current tremor targets (Vim, Raprl, caudal Zi, Vo and STN) and continuing with a discussion of results obtained when performing DBS in the various aforementioned tremor syndromes. Future directions for DBS research are then briefly discussed.

Nicht-medikamentöse Optionen zur Behandlung pharmakoresistenter Epilepsien

2018 ◽  
Vol 75 (7) ◽  
pp. 448-454
Author(s):  
Thomas Grunwald ◽  
Judith Kröll
Keyword(s):  
Deep Brain Stimulation ◽  
Brain Stimulation ◽  
Tiefe Hirnstimulation ◽  
Ketogene Diät ◽  
Deep Brain

Zusammenfassung. Wenn mit den ersten beiden anfallspräventiven Medikamenten keine Anfallsfreiheit erzielt werden konnte, so ist die Wahrscheinlichkeit, dies mit anderen Medikamenten zu erreichen, nur noch ca. 10 %. Es sollte dann geprüft werden, warum eine Pharmakoresistenz besteht und ob ein epilepsiechirurgischer Eingriff zur Anfallsfreiheit führen kann. Ist eine solche Operation nicht möglich, so können palliative Verfahren wie die Vagus-Nerv-Stimulation (VNS) und die tiefe Hirnstimulation (Deep Brain Stimulation) in eine bessere Anfallskontrolle ermöglichen. Insbesondere bei schweren kindlichen Epilepsien stellt auch die ketogene Diät eine zu erwägende Option dar.

Sign in / Sign up

Export Citation Format

Share Document