Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson's disease identification
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Outros Autores: | , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.artmed.2018.04.001 http://hdl.handle.net/11449/179778 |
Resumo: | Background and objective: Parkinson's disease (PD) is considered a degenerative disorder that affects the motor system, which may cause tremors, micrography, and the freezing of gait. Although PD is related to the lack of dopamine, the triggering process of its development is not fully understood yet. Methods: In this work, we introduce convolutional neural networks to learn features from images produced by handwritten dynamics, which capture different information during the individual's assessment. Additionally, we make available a dataset composed of images and signal-based data to foster the research related to computer-aided PD diagnosis. Results: The proposed approach was compared against raw data and texture-based descriptors, showing suitable results, mainly in the context of early stage detection, with results nearly to 95%. Conclusions: The analysis of handwritten dynamics using deep learning techniques showed to be useful for automatic Parkinson's disease identification, as well as it can outperform handcrafted features. |
id |
UNSP_dd26d51c010e9c6be8f37f4a212cc39c |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/179778 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson's disease identificationConvolutional neural networksHandwritten dynamicsParkinson's diseaseBackground and objective: Parkinson's disease (PD) is considered a degenerative disorder that affects the motor system, which may cause tremors, micrography, and the freezing of gait. Although PD is related to the lack of dopamine, the triggering process of its development is not fully understood yet. Methods: In this work, we introduce convolutional neural networks to learn features from images produced by handwritten dynamics, which capture different information during the individual's assessment. Additionally, we make available a dataset composed of images and signal-based data to foster the research related to computer-aided PD diagnosis. Results: The proposed approach was compared against raw data and texture-based descriptors, showing suitable results, mainly in the context of early stage detection, with results nearly to 95%. Conclusions: The analysis of handwritten dynamics using deep learning techniques showed to be useful for automatic Parkinson's disease identification, as well as it can outperform handcrafted features.UFSCAR – Federal University of São Carlos Department of ComputingUNOESTE – University of Western São PauloUNESP – São Paulo State University School of SciencesUNIFOR – Graduate Program in Applied InformaticsUNESP – São Paulo State University Botucatu Medical SchoolOTH – Ostbayerische Technische HochschuleUNESP – São Paulo State University School of SciencesUNESP – São Paulo State University Botucatu Medical SchoolUniversidade Federal de São Carlos (UFSCar)UNOESTE – University of Western São PauloUniversidade Estadual Paulista (Unesp)UNIFOR – Graduate Program in Applied InformaticsOTH – Ostbayerische Technische HochschulePereira, Clayton R.Pereira, Danilo R.Rosa, Gustavo H. [UNESP]Albuquerque, Victor H.C.Weber, Silke A.T. [UNESP]Hook, ChristianPapa, João P. [UNESP]2018-12-11T17:36:43Z2018-12-11T17:36:43Z2018-05-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article67-77application/pdfhttp://dx.doi.org/10.1016/j.artmed.2018.04.001Artificial Intelligence in Medicine, v. 87, p. 67-77.1873-28600933-3657http://hdl.handle.net/11449/17977810.1016/j.artmed.2018.04.0012-s2.0-850454690542-s2.0-85045469054.pdfScopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengArtificial Intelligence in Medicine0,766info:eu-repo/semantics/openAccess2024-01-22T06:21:41Zoai:repositorio.unesp.br:11449/179778Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-01-22T06:21:41Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson's disease identification |
title |
Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson's disease identification |
spellingShingle |
Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson's disease identification Pereira, Clayton R. Convolutional neural networks Handwritten dynamics Parkinson's disease |
title_short |
Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson's disease identification |
title_full |
Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson's disease identification |
title_fullStr |
Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson's disease identification |
title_full_unstemmed |
Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson's disease identification |
title_sort |
Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson's disease identification |
author |
Pereira, Clayton R. |
author_facet |
Pereira, Clayton R. Pereira, Danilo R. Rosa, Gustavo H. [UNESP] Albuquerque, Victor H.C. Weber, Silke A.T. [UNESP] Hook, Christian Papa, João P. [UNESP] |
author_role |
author |
author2 |
Pereira, Danilo R. Rosa, Gustavo H. [UNESP] Albuquerque, Victor H.C. Weber, Silke A.T. [UNESP] Hook, Christian Papa, João P. [UNESP] |
author2_role |
author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Federal de São Carlos (UFSCar) UNOESTE – University of Western São Paulo Universidade Estadual Paulista (Unesp) UNIFOR – Graduate Program in Applied Informatics OTH – Ostbayerische Technische Hochschule |
dc.contributor.author.fl_str_mv |
Pereira, Clayton R. Pereira, Danilo R. Rosa, Gustavo H. [UNESP] Albuquerque, Victor H.C. Weber, Silke A.T. [UNESP] Hook, Christian Papa, João P. [UNESP] |
dc.subject.por.fl_str_mv |
Convolutional neural networks Handwritten dynamics Parkinson's disease |
topic |
Convolutional neural networks Handwritten dynamics Parkinson's disease |
description |
Background and objective: Parkinson's disease (PD) is considered a degenerative disorder that affects the motor system, which may cause tremors, micrography, and the freezing of gait. Although PD is related to the lack of dopamine, the triggering process of its development is not fully understood yet. Methods: In this work, we introduce convolutional neural networks to learn features from images produced by handwritten dynamics, which capture different information during the individual's assessment. Additionally, we make available a dataset composed of images and signal-based data to foster the research related to computer-aided PD diagnosis. Results: The proposed approach was compared against raw data and texture-based descriptors, showing suitable results, mainly in the context of early stage detection, with results nearly to 95%. Conclusions: The analysis of handwritten dynamics using deep learning techniques showed to be useful for automatic Parkinson's disease identification, as well as it can outperform handcrafted features. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-12-11T17:36:43Z 2018-12-11T17:36:43Z 2018-05-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1016/j.artmed.2018.04.001 Artificial Intelligence in Medicine, v. 87, p. 67-77. 1873-2860 0933-3657 http://hdl.handle.net/11449/179778 10.1016/j.artmed.2018.04.001 2-s2.0-85045469054 2-s2.0-85045469054.pdf |
url |
http://dx.doi.org/10.1016/j.artmed.2018.04.001 http://hdl.handle.net/11449/179778 |
identifier_str_mv |
Artificial Intelligence in Medicine, v. 87, p. 67-77. 1873-2860 0933-3657 10.1016/j.artmed.2018.04.001 2-s2.0-85045469054 2-s2.0-85045469054.pdf |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Artificial Intelligence in Medicine 0,766 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
67-77 application/pdf |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1792962401369325568 |