Ischemic stroke enhancement using a variational model and the expectation maximization method
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/10.1007/s00330-018-5378-2 http://hdl.handle.net/11449/176133 |
Resumo: | Objectives: In order to enable less experienced physicians to reliably detect early signs of stroke, A novel approach was proposed to enhance the visual perception of ischemic stroke in non-enhanced CT. Methods: A set of 39 retrospective CT scans were used, divided into 23 cases of acute ischemic stroke and 16 normal patients. Stroke cases were obtained within 4.5 h of symptom onset and with a mean NIHSS of 12.9±7.4. After selection of adjunct slices from the CT exam, image averaging was performed to reduce the noise and redundant information. This was followed by a variational decomposition model to keep the relevant component of the image. The expectation maximization method was applied to generate enhanced images. Results: We determined a test to evaluate the performance of observers in a clinical environment with and without the aid of enhanced images. The overall sensitivity of the observer’s analysis was 64.5 % and increased to 89.6 % and specificity was 83.3 % and increased to 91.7 %. Conclusion: These results show the importance of a computational tool to assist neuroradiology decisions, especially in critical situations such as the diagnosis of ischemic stroke. Key Points: • Diagnosing patients with stroke requires high efficiency to avoid irreversible cerebral damage. • A computational algorithm was proposed to enhance the visual perception of stroke. • Observers’ performance was increased with the aid of enhanced images. |
id |
UNSP_5fd0444f977f1500c2e4c244323bd5e3 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/176133 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Ischemic stroke enhancement using a variational model and the expectation maximization methodAlgorithmsBrainEarly diagnosisStrokeTomographyObjectives: In order to enable less experienced physicians to reliably detect early signs of stroke, A novel approach was proposed to enhance the visual perception of ischemic stroke in non-enhanced CT. Methods: A set of 39 retrospective CT scans were used, divided into 23 cases of acute ischemic stroke and 16 normal patients. Stroke cases were obtained within 4.5 h of symptom onset and with a mean NIHSS of 12.9±7.4. After selection of adjunct slices from the CT exam, image averaging was performed to reduce the noise and redundant information. This was followed by a variational decomposition model to keep the relevant component of the image. The expectation maximization method was applied to generate enhanced images. Results: We determined a test to evaluate the performance of observers in a clinical environment with and without the aid of enhanced images. The overall sensitivity of the observer’s analysis was 64.5 % and increased to 89.6 % and specificity was 83.3 % and increased to 91.7 %. Conclusion: These results show the importance of a computational tool to assist neuroradiology decisions, especially in critical situations such as the diagnosis of ischemic stroke. Key Points: • Diagnosing patients with stroke requires high efficiency to avoid irreversible cerebral damage. • A computational algorithm was proposed to enhance the visual perception of stroke. • Observers’ performance was increased with the aid of enhanced images.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Instituto de Biociências de Botucatu Departamento de Física e Biofísica UNESP—Universidade Estadual Paulista, P.O. BOX 510, Distrito de Rubião Junior S/NLaboratory I3MTO – University of Orleans, 5 Rue de Chartres, BP 6744Departamento de Neurologia Psicologia e Psiquiatria Faculdade de Medicina de Botucatu UNESP—Universidade Estadual Paulista, Distrito de Rubião Junior S/NDepartamento de Diagnóstico por Imagem Escola Paulista de Medicina – UNIFESP, Rua Napoleão de Barros, 800Departamento de Doenças Tropicais e Diagnóstico por Imagem Faculdade de Medicina de Botucatu UNESP—Universidade Estadual Paulista, Distrito de Rubião Junior S/NInstituto de Biociências de Botucatu Departamento de Física e Biofísica UNESP—Universidade Estadual Paulista, P.O. BOX 510, Distrito de Rubião Junior S/NDepartamento de Neurologia Psicologia e Psiquiatria Faculdade de Medicina de Botucatu UNESP—Universidade Estadual Paulista, Distrito de Rubião Junior S/NDepartamento de Doenças Tropicais e Diagnóstico por Imagem Faculdade de Medicina de Botucatu UNESP—Universidade Estadual Paulista, Distrito de Rubião Junior S/NFAPESP: 2014/22296-1Universidade Estadual Paulista (Unesp)Laboratory I3MTO – University of OrleansUniversidade Federal de São Paulo (UNIFESP)Alves, Allan Felipe Fattori [UNESP]Jennane, Rachidde Miranda, José Ricardo Arruda [UNESP]de Freitas, Carlos Clayton Macedo [UNESP]Abdala, Nitamarde Pina, Diana Rodrigues [UNESP]2018-12-11T17:19:12Z2018-12-11T17:19:12Z2018-09-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article3936-3942application/pdfhttp://dx.doi.org/10.1007/s00330-018-5378-2European Radiology, v. 28, n. 9, p. 3936-3942, 2018.1432-10840938-7994http://hdl.handle.net/11449/17613310.1007/s00330-018-5378-22-s2.0-850449394062-s2.0-85044939406.pdfScopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengEuropean Radiology1,9431,943info:eu-repo/semantics/openAccess2023-10-04T06:04:34Zoai:repositorio.unesp.br:11449/176133Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462023-10-04T06:04:34Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Ischemic stroke enhancement using a variational model and the expectation maximization method |
title |
Ischemic stroke enhancement using a variational model and the expectation maximization method |
spellingShingle |
Ischemic stroke enhancement using a variational model and the expectation maximization method Alves, Allan Felipe Fattori [UNESP] Algorithms Brain Early diagnosis Stroke Tomography |
title_short |
Ischemic stroke enhancement using a variational model and the expectation maximization method |
title_full |
Ischemic stroke enhancement using a variational model and the expectation maximization method |
title_fullStr |
Ischemic stroke enhancement using a variational model and the expectation maximization method |
title_full_unstemmed |
Ischemic stroke enhancement using a variational model and the expectation maximization method |
title_sort |
Ischemic stroke enhancement using a variational model and the expectation maximization method |
author |
Alves, Allan Felipe Fattori [UNESP] |
author_facet |
Alves, Allan Felipe Fattori [UNESP] Jennane, Rachid de Miranda, José Ricardo Arruda [UNESP] de Freitas, Carlos Clayton Macedo [UNESP] Abdala, Nitamar de Pina, Diana Rodrigues [UNESP] |
author_role |
author |
author2 |
Jennane, Rachid de Miranda, José Ricardo Arruda [UNESP] de Freitas, Carlos Clayton Macedo [UNESP] Abdala, Nitamar de Pina, Diana Rodrigues [UNESP] |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) Laboratory I3MTO – University of Orleans Universidade Federal de São Paulo (UNIFESP) |
dc.contributor.author.fl_str_mv |
Alves, Allan Felipe Fattori [UNESP] Jennane, Rachid de Miranda, José Ricardo Arruda [UNESP] de Freitas, Carlos Clayton Macedo [UNESP] Abdala, Nitamar de Pina, Diana Rodrigues [UNESP] |
dc.subject.por.fl_str_mv |
Algorithms Brain Early diagnosis Stroke Tomography |
topic |
Algorithms Brain Early diagnosis Stroke Tomography |
description |
Objectives: In order to enable less experienced physicians to reliably detect early signs of stroke, A novel approach was proposed to enhance the visual perception of ischemic stroke in non-enhanced CT. Methods: A set of 39 retrospective CT scans were used, divided into 23 cases of acute ischemic stroke and 16 normal patients. Stroke cases were obtained within 4.5 h of symptom onset and with a mean NIHSS of 12.9±7.4. After selection of adjunct slices from the CT exam, image averaging was performed to reduce the noise and redundant information. This was followed by a variational decomposition model to keep the relevant component of the image. The expectation maximization method was applied to generate enhanced images. Results: We determined a test to evaluate the performance of observers in a clinical environment with and without the aid of enhanced images. The overall sensitivity of the observer’s analysis was 64.5 % and increased to 89.6 % and specificity was 83.3 % and increased to 91.7 %. Conclusion: These results show the importance of a computational tool to assist neuroradiology decisions, especially in critical situations such as the diagnosis of ischemic stroke. Key Points: • Diagnosing patients with stroke requires high efficiency to avoid irreversible cerebral damage. • A computational algorithm was proposed to enhance the visual perception of stroke. • Observers’ performance was increased with the aid of enhanced images. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-12-11T17:19:12Z 2018-12-11T17:19:12Z 2018-09-01 |
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/10.1007/s00330-018-5378-2 European Radiology, v. 28, n. 9, p. 3936-3942, 2018. 1432-1084 0938-7994 http://hdl.handle.net/11449/176133 10.1007/s00330-018-5378-2 2-s2.0-85044939406 2-s2.0-85044939406.pdf |
url |
http://dx.doi.org/10.1007/s00330-018-5378-2 http://hdl.handle.net/11449/176133 |
identifier_str_mv |
European Radiology, v. 28, n. 9, p. 3936-3942, 2018. 1432-1084 0938-7994 10.1007/s00330-018-5378-2 2-s2.0-85044939406 2-s2.0-85044939406.pdf |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
European Radiology 1,943 1,943 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
3936-3942 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_ |
1797789287226277888 |