Towards Automated EEG-Based Alzheimer's Disease Diagnosis Using Relevance Vector Machines

Nenhuma Miniatura disponível
Citações na Scopus
Tipo de produção
conferenceObject
Data de publicação
2014
Web of Science
Título da Revista
ISSN da Revista
Título do Volume
Editora
IEEE
Autores
CASSANI, Raymundo
FALK, Tiago H.
FRAGA, Francisco J.
Citação
5TH ISSNIP-IEEE BIOSIGNALS AND BIOROBOTICS CONFERENCE (2014): BIOSIGNALS AND ROBOTICS FOR BETTER AND SAFER LIVING, p.112-117, 2014
Projetos de Pesquisa
Unidades Organizacionais
Fascículo
Resumo
Existing electroencephalography (EEG) based Alzheimer's disease (AD) diagnostic systems typically rely on experts to visually inspect and segment the collected signals into artefact-free epochs and on support vector machine (SVM) based classifiers. The manual selection process, however, introduces biases and errors into the diagnostic procedure, renders it ""semi-automated,"" and makes the procedure costly and labour-intensive. In this paper, we overcome these limitations by proposing the use of an automated artefact removal (AAR) algorithm to remove artefacts from the EEG signal without the need for human intervention. We investigate the effects of the so-called wavelet-enhanced independent component analysis (wICA) AAR on three classes of EEG features, namely spectral power, coherence, and amplitude modulation, and ultimately, on diagnostic accuracy, specificity and sensitivity. Furthermore, we propose to replace the binary SVM classifier with a soft-decision relevance vector machine (RVM) classifier. Experimental results show the proposed RVM-based system outperforming the SVM trained on features extracted from both manually-selected and wICA-processed epochs. Moreover, the class membership information output by the RVM is shown to provide clinicians with a richer pool of information to assist with AD assessment.
Palavras-chave
Alzheimer's disease, electroencephalography, support vector machine (SVM), relevance vector machine (RVM), wICA
URI
https://observatorio.fm.usp.br/handle/OPI/54501
Referências
  1. Adeli H, 2005, CLIN EEG NEUROSCI, V36, P131, DOI 10.1177/155005940503600303
  2. Babiloni C, 2010, J ALZHEIMERS DIS, V22, P1047, DOI 10.3233/JAD-2010-100798
  3. BEDROSIAN E, 1963, P IEEE, V51, P868, DOI 10.1109/PROC.1963.2308
  4. BESTHORN C, 1994, ELECTROEN CLIN NEURO, V90, P242, DOI 10.1016/0013-4694(94)90095-7
  5. BRENNER RP, 1986, ELECTROEN CLIN NEURO, V64, P483, DOI 10.1016/0013-4694(86)90184-7
  6. Brucki SMD, 2003, ARQ NEURO-PSIQUIAT, V61, P777, DOI 10.1590/S0004-282X2003000500014
  7. Cassani R., FRONTIERS A IN PRESS
  8. Castellanos NP, 2006, J NEUROSCI METH, V158, P300, DOI 10.1016/j.jneumeth.2006.05.033
  9. COBEN LA, 1983, ELECTROEN CLIN NEURO, V55, P372, DOI 10.1016/0013-4694(83)90124-4
  10. CORTES C, 1995, MACH LEARN, V20, P273, DOI 10.1023/A:1022627411411
  11. Daly I., 2013, CLIN EEG NEUROSCI, P1
  12. Dauwels J, 2010, NEUROIMAGE, V49, P668, DOI 10.1016/j.neuroimage.2009.06.056
  13. Dauwels J., 2011, INT J ALZHEIMERS DIS, V2011
  14. De Clercq W, 2006, IEEE T BIO-MED ENG, V53, P2583, DOI 10.1109/TBME.2006.879459
  15. Falk TH, 2012, EURASIP J ADV SIG PR, DOI 10.1186/1687-6180-2012-192
  16. Fraga FJ, 2013, INT CONF ACOUST SPEE, P1207, DOI 10.1109/ICASSP.2013.6637842
  17. Fraga FJ, 2013, PLOS ONE, V8, DOI 10.1371/journal.pone.0072240
  18. GIAQUINTO S, 1986, ELECTROEN CLIN NEURO, V63, P540, DOI 10.1016/0013-4694(86)90141-0
  19. Gomez-Herrero G, 2006, 2006 7TH NORDIC SIGNAL PROCESSING SYMPOSIUM, P130
  20. Hurd MD, 2013, NEW ENGL J MED, V368, P1326, DOI [10.1056/NEJMsa1204629, 10.1056/NEJMc1305541]
  21. Jeong JS, 2004, CLIN NEUROPHYSIOL, V115, P1490, DOI 10.1016/j.clinph.2004.01.001
  22. Kanda P., 2013, CLIN EEG NEUROSCIENC
  23. Krishnaveni V, 2006, J NEURAL ENG, V3, P338, DOI 10.1088/1741-2560/3/4/011
  24. Lehmann C, 2007, J NEUROSCI METH, V161, P342, DOI 10.1016/j.jneumeth.2006.10.023
  25. Locatelli T, 1998, ELECTROEN CLIN NEURO, V106, P229, DOI 10.1016/S0013-4694(97)00129-6
  26. Makarov V. A., 2012, WAVELET ENHANCED IND
  27. MCKHANN G, 1984, NEUROLOGY, V34, P939, DOI 10.1212/WNL.34.7.939
  28. Nunez P. L., 2006, ELECT FIELDS BRAIN N, DOI 10.1093/acprof:oso/9780195050387.001.0001
  29. Sarazin M, 2012, NEUROIMAG CLIN N AM, V22, P23, DOI 10.1016/j.nic.2011.11.004
  30. SLOAN EP, 1994, ELECTROEN CLIN NEURO, V91, P163, DOI 10.1016/0013-4694(94)90066-3
  31. Sornmo L., 2005, BIOELECTRICAL SIGNAL, P453
  32. Thies W, 2013, ALZHEIMERS DEMENT, V9, P208, DOI 10.1016/j.jalz.2013.02.003
  33. Tipping ME, 2001, J MACH LEARN RES, V1, P211, DOI 10.1162/15324430152748236
  34. Trambaiolli LR, 2011, IEEE ENG MED BIO, P3828, DOI 10.1109/IEMBS.2011.6090951
  35. Trambaiolli LR, 2011, CLIN EEG NEUROSCI, V42, P160, DOI 10.1177/155005941104200304
  36. WHO, 2012, GLOB STRAT DENG PREV

Coleções
Comunicações em Eventos - HC/Outros
Comunicações em Eventos - LIM/45