Adaptation of Convolutional Neural Networks for Multi-Channel Artifact Detection in Chronically Recorded Local Field Potentials

Author(s):  
Marcos Fabietti ◽  
Mufti Mahmud ◽  
Ahmad Lotfi ◽  
Alberto Averna ◽  
David Guggenmos ◽  
...  
2014 ◽  
Vol 15 (S1) ◽  
Author(s):  
Richard J Tomsett ◽  
Matt Ainsworth ◽  
Alexander Thiele ◽  
Mehdi Sanayei ◽  
Xing Chen ◽  
...  

2017 ◽  
Vol 2017 ◽  
pp. 1-16 ◽  
Author(s):  
Mohammad S. Islam ◽  
Khondaker A. Mamun ◽  
Hai Deng

Decoding neural activities related to voluntary and involuntary movements is fundamental to understanding human brain motor circuits and neuromotor disorders and can lead to the development of neuromotor prosthetic devices for neurorehabilitation. This study explores using recorded deep brain local field potentials (LFPs) for robust movement decoding of Parkinson’s disease (PD) and Dystonia patients. The LFP data from voluntary movement activities such as left and right hand index finger clicking were recorded from patients who underwent surgeries for implantation of deep brain stimulation electrodes. Movement-related LFP signal features were extracted by computing instantaneous power related to motor response in different neural frequency bands. An innovative neural network ensemble classifier has been proposed and developed for accurate prediction of finger movement and its forthcoming laterality. The ensemble classifier contains three base neural network classifiers, namely, feedforward, radial basis, and probabilistic neural networks. The majority voting rule is used to fuse the decisions of the three base classifiers to generate the final decision of the ensemble classifier. The overall decoding performance reaches a level of agreement (kappa value) at about0.729±0.16for decoding movement from the resting state and about0.671±0.14for decoding left and right visually cued movements.


2021 ◽  
Vol 11 (7) ◽  
pp. 882
Author(s):  
Yeon Hee Yu ◽  
Seong-Wook Kim ◽  
Dae-Kyoon Park ◽  
Ho-Yeon Song ◽  
Duk-Soo Kim ◽  
...  

Increased prevalence of chronic kidney disease (CKD) and neurological disorders including cerebrovascular disease, cognitive impairment, peripheral neuropathy, and dysfunction of central nervous system have been reported during the natural history of CKD. Psychological distress and depression are serious concerns in patients with CKD. However, the relevance of CKD due to decline in renal function and the pathophysiology of emotional deterioration is not clear. Male Sprague Dawley rats were divided into three groups: sham control, 5/6 nephrectomy at 4 weeks, and 5/6 nephrectomy at 10 weeks. Behavior tests, local field potentials, and histology and laboratory tests were conducted and investigated. We provided direct evidence showing that CKD rat models exhibited anxiogenic behaviors and depression-like phenotypes, along with altered hippocampal neural oscillations at 1–12 Hz. We generated CKD rat models by performing 5/6 nephrectomy, and identified higher level of serum creatinine and blood urea nitrogen (BUN) in CKD rats than in wild-type, depending on time. In addition, the level of α-smooth muscle actin (α-SMA) and collagen I for renal tissue was markedly elevated, with worsening fibrosis due to renal failures. The level of anxiety and depression-like behaviors increased in the 10-week CKD rat models compared with the 4-week rat models. In the recording of local field potentials, the power of delta (1–4 Hz), theta (4–7 Hz), and alpha rhythm (7–12 Hz) was significantly increased in the hippocampus of CKD rats compared with wild-type rats. Together, our findings indicated that anxiogenic behaviors and depression can be induced by CKD, and these abnormal symptoms can be worsened as the onset of CKD was prolonged. In conclusion, our results show that the hippocampus is vulnerable to uremia.


Sign in / Sign up

Export Citation Format

Share Document