Suseendrakumar Duraivel1,2, Akshay T Rao3, Charles W Lu2,3, J Nicole Bentley4, William C Stacey2,5, Cynthia A Chestek3, Parag G Patil2,3,5. 1. Department of Biomedical Engineering, Duke University, Durham, NC 27708, United States of America. 2. Department of Neurosurgery, University of Michigan, Ann Arbor, MI 48109, United States of America. 3. Department of Biomedical Engineering, University of Michigan, Ann Arbor, MI 48109, United States of America. 4. Department of Neurosurgery, University of Alabama at Birmingham, Birmingham, AL 35294-3410, United States of America. 5. Department of Neurology, University of Michigan, Ann Arbor, MI 48109, United States of America.
Abstract
OBJECTIVE: Conventional neural signal analysis methods assume that features of interest are linear, time-invariant signals confined to well-delineated spectral bands. However, new evidence suggests that neural signals exhibit important non-stationary characteristics with ill-defined spectral distributions. These features pose a need for signal processing algorithms that can characterize temporal and spectral features of non-linear time series. This study compares the effectiveness of four algorithms in extracting neural information for use in decoding cortical signals: Fast Fourier Transform bandpass filtering (FFT), principal spectral component analysis (PSCA), wavelet analysis (WA), and empirical mode decomposition (EMD). APPROACH: Electrocorticographic signals were recorded from the motor and sensory cortex of two epileptic patients performing finger movements. Each signal processing algorithm was used to extract beta (10-30 Hz) and gamma (66-114 Hz) band power to detect thumb movement and decode finger flexions, respectively. Naïve-Bayes (NB), support vector machine (SVM), and linear discriminant analysis (LDA) classifiers using each signal were validated using leave-one-out cross-validation. MAIN RESULTS: Decoders using all four signal decompositions achieved above 90% average accuracy in finger movement detection using beta power. When decoding individual finger flexion using gamma, the PSCA NB classifiers achieved 78 ± 4% accuracy while FFT, WA, and EMD analysis achieved accuracies of 73 ± 8%, 68 ± 7%, and 62 ± 3% respectively, with similar results using SVM and LDA. SIGNIFICANCE: These results illustrate the relative levels of useful information contributed by each decomposition method in the case of finger movement decoding, which can inform the development of effective neural decoding pipelines. Further analyses could compare performance using more specific non-sinusoidal features, such as transients and phase-amplitude coupling.
OBJECTIVE: Conventional neural signal analysis methods assume that features of interest are linear, time-invariant signals confined to well-delineated spectral bands. However, new evidence suggests that neural signals exhibit important non-stationary characteristics with ill-defined spectral distributions. These features pose a need for signal processing algorithms that can characterize temporal and spectral features of non-linear time series. This study compares the effectiveness of four algorithms in extracting neural information for use in decoding cortical signals: Fast Fourier Transform bandpass filtering (FFT), principal spectral component analysis (PSCA), wavelet analysis (WA), and empirical mode decomposition (EMD). APPROACH: Electrocorticographic signals were recorded from the motor and sensory cortex of two epileptic patients performing finger movements. Each signal processing algorithm was used to extract beta (10-30 Hz) and gamma (66-114 Hz) band power to detect thumb movement and decode finger flexions, respectively. Naïve-Bayes (NB), support vector machine (SVM), and linear discriminant analysis (LDA) classifiers using each signal were validated using leave-one-out cross-validation. MAIN RESULTS: Decoders using all four signal decompositions achieved above 90% average accuracy in finger movement detection using beta power. When decoding individual finger flexion using gamma, the PSCA NB classifiers achieved 78 ± 4% accuracy while FFT, WA, and EMD analysis achieved accuracies of 73 ± 8%, 68 ± 7%, and 62 ± 3% respectively, with similar results using SVM and LDA. SIGNIFICANCE: These results illustrate the relative levels of useful information contributed by each decomposition method in the case of finger movement decoding, which can inform the development of effective neural decoding pipelines. Further analyses could compare performance using more specific non-sinusoidal features, such as transients and phase-amplitude coupling.
Authors: Zachary T Irwin; David E Thompson; Karen E Schroeder; Derek M Tat; Ali Hassani; Autumn J Bullard; Shoshana L Woo; Melanie G Urbanchek; Adam J Sachs; Paul S Cederna; William C Stacey; Parag G Patil; Cynthia A Chestek Journal: IEEE Trans Neural Syst Rehabil Eng Date: 2015-11-20 Impact factor: 3.802
Authors: Cynthia A Chestek; Vikash Gilja; Christine H Blabe; Brett L Foster; Krishna V Shenoy; Josef Parvizi; Jaimie M Henderson Journal: J Neural Eng Date: 2013-01-31 Impact factor: 5.379
Authors: Chia-Han Chiang; Charles Wang; Katrina Barth; Shervin Rahimpour; Michael Trumpis; Suseendrakumar Duraivel; Iakov Rachinskiy; Agrita Dubey; Katie E Wingel; Megan Wong; Nicholas S Witham; Thomas Odell; Virginia Woods; Brinnae Bent; Werner Doyle; Daniel Friedman; Eckardt Bihler; Christopher F Reiche; Derek G Southwell; Michael M Haglund; Allan H Friedman; Shivanand P Lad; Sasha Devore; Orrin Devinsky; Florian Solzbacher; Bijan Pesaran; Gregory Cogan; Jonathan Viventi Journal: J Neural Eng Date: 2021-06-17 Impact factor: 5.043