Automatic detection of intraoperative neurological injury
TL;DR: An automatic injury detection algorithm is proposed in which the EP signal is modeled as a pole-zero filter and then the model parameters are applied as inputs to a classifier type neural network.
Abstract: Neurological injuries occurring during high-risk surgical procedures can be detected by monitoring intraoperative evoked potential signals. In this communication, an automatic injury detection algorithm is proposed in which the EP signal is modeled as a pole-zero filter and then the model parameters are applied as inputs to a classifier type neural network. A recognition rate of 96% is achieved using an experimental model of brain injury.
Citations
More filters
Book•
01 Oct 2010TL;DR: Intraoperative neurophysiologic monitoring of vascular disorders and postoperative studies and outcomes: clinical indications and usefulness of a postoperative study Index.
Abstract: Preface 1. Introduction, history, and staffing for intraoperative monitoring 2. The preoperative assessment 3. Magnetic stimulation 4. The operating room environment and team approach: pitfalls and technical factors 5. Basic pharmacology of anesthetic agents and their effects on neurophysiological monitoring 6. Somatosensory evoked potential monitoring with scalp and cervical recording 7. Transcranial electric motor stimulation: technique and exclusionary criteria 8. Electrocorticography and intraoperative electroencephalography 9. Brainstem auditory evoked potential monitoring 10. Pedicle screw application and electromyographic recording 11. Cranial nerve monitoring 12. Peripheral nerve monitoring: basics and indications 13. Special consideration in pediatric surgical monitoring 14. Intraoperative neurophysiologic monitoring of vascular disorders 15. Selective dorsal rhizotomies: technique and protocol for monitoring 16. Interpreting and reporting the neurophysiological data to the surgical team: how to do it and when is it indicated? 17. Intraoperative wake-up test 18. Postoperative studies and outcomes: clinical indications and usefulness of a postoperative study Index.
9 citations
References
More filters
Book•
[...]
01 Jan 1994
607 citations
"Automatic detection of intraoperati..." refers methods in this paper
...A sigmoidal nonlinearity is used at the output of each neuron and the weights are updated using the backpropagation algorithm with a self-adjusting learning rate [8]....
[...]
TL;DR: Electrophysiologic responses of the nervous system to sensory stimulation, can be used to assess the functional integrity of specific sensory pathways in anesthetized patients and can be partially assessed when clinical examination is severely limited by the effects of anesthetic agents and adjuvant drugs.
Abstract: Sensory evoked potentials (EP), the electrophysiologic responses of the nervous system to sensory stimulation, can be used to assess the functional integrity of specific sensory pathways in anesthetized patients (1, 2). Thus, neurologic function can be partially assessed when clinical examination is severely limited by the effects of anesthetic agents and adjuvant drugs.
224 citations
"Automatic detection of intraoperati..." refers background in this paper
...The variation of EP signals with time is an important indication of the patient’s neurological condition [ 1 ], [2]....
[...]
TL;DR: In this estimation procedure the evoked response is modeled as a dynamic Fourier series and the Fourier coefficients are estimated adaptively by the least-mean-square algorithm.
Abstract: In this estimation procedure the evoked response is modeled as a dynamic Fourier series and the Fourier coefficients are estimated adaptively by the least-mean-square algorithm. Approximate expressions have been developed for the estimation error and time constant of adaptation. A procedure for optimizing the estimator performance is also presented. The effectiveness of the estimator with simulated as well as actual evoked responses is demonstrated. >
174 citations
TL;DR: In this paper, an iterative prefiltering method is proposed as an approach to estimate the poles and zeros of the vocal-tract transfer function simultaneously rather than sequentially as in Shanks' method.
Abstract: Kopec, Oppenheim, and Tribolet have described a homomorphic technique for producing, from a speech signal, a minimum-phase estimate of the vocal-tract impulse response. Once such an estimate has been obtained, the problem of modeling the vocal tract with a pole-zero model is a classical one in nonlinear estimation theory. It is shown in this paper that Shanks' method, Kalman's method, and the iterative prefiltering method are all different linearizations of the same nonlinear problem, and the iterative prefiltering method is proposed as an approach to estimating the poles and zeros of the vocal-tract transfer function simultaneously. A simulation is described which shows the advantage of estimating poles and zeros simultaneously rather than sequentially as in Shanks' method. A preliminary example of application to real speech is also given.
171 citations
TL;DR: A complete solution for the delineation of the ECG signal into its component waves is proposed from a system theoretic point of view.
Abstract: A complete solution for the delineation of the ECG signal into its component waves is proposed from a system theoretic point of view. The discrete cosine transform (DCT) of a bell-shaped biphasic function is approximated mathematically by a system function with two poles and two zeros, i.e., of order
85 citations
"Automatic detection of intraoperati..." refers methods in this paper
...In order to overcome this difficulty, an indirect approach is adopted by modeling the discrete cosine transform (DCT) of the time-averaged EP [7]....
[...]