Automated breast ultrasound lesions detection using convolutional neural networks

Breast lesion detection using ultrasound imaging is considered an important step of computer-aided diagnosis systems. Over the past decade, researchers have demonstrated the possibilities to automate the initial lesion detection. However, the lack of a common dataset impedes research when comparing...

Descripción completa

Detalles Bibliográficos
Autores: Yap, Moi Hoon, Pons Rodríguez, Gerard, Martí Bonmatí, Joan, Ganau Macías, Sergi, Sentís Crivellé, Melcior, Zwiggelaar, Reyer, Davison, Adrian K., Martí Marly, Robert
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2018
País:España
Institución:Universitat Oberta de Catalunya (UOC)
Repositorio:O2, repositorio institucional de la UOC
OAI Identifier:oai:openaccess.uoc.edu:10609/93200
Acceso en línea:https://hdl.handle.net/10609/93200
Access Level:acceso embargado
Palabra clave:breast cancer
convolutional neural networks
lesion detection
transfer learning
ultrasound imaging
cáncer de mama
redes neuronales convolucionales
detección de lesiones
transferencia de aprendizaje
imagen de ultrasonido
càncer de mama
xarxes neuronals convolucionals
detecció de lesions
transferir l'aprenentatge
imatges per ultrasò
Breast -- Cancer
Mama -- Càncer
Mama -- Cáncer
id ES_61a329fd4086c14c2f08ff6a2b308321
oai_identifier_str oai:openaccess.uoc.edu:10609/93200
network_acronym_str ES
network_name_str España
repository_id_str
spelling Automated breast ultrasound lesions detection using convolutional neural networksYap, Moi HoonPons Rodríguez, GerardMartí Bonmatí, JoanGanau Macías, SergiSentís Crivellé, MelciorZwiggelaar, ReyerDavison, Adrian K.Martí Marly, Robertbreast cancerconvolutional neural networkslesion detectiontransfer learningultrasound imagingcáncer de mamaredes neuronales convolucionalesdetección de lesionestransferencia de aprendizajeimagen de ultrasonidocàncer de mamaxarxes neuronals convolucionalsdetecció de lesionstransferir l'aprenentatgeimatges per ultrasòBreast -- CancerMama -- CàncerMama -- CáncerBreast lesion detection using ultrasound imaging is considered an important step of computer-aided diagnosis systems. Over the past decade, researchers have demonstrated the possibilities to automate the initial lesion detection. However, the lack of a common dataset impedes research when comparing the performance of such algorithms. This paper proposes the use of deep learning approaches for breast ultrasound lesion detection and investigates three different methods: a Patch-based LeNet, a U-Net, and a transfer learning approach with a pretrained FCN-AlexNet. Their performance is compared against four state-of-the-art lesion detection algorithms (i.e., Radial Gradient Index, Multifractal Filtering, Rule-based Region Ranking, and Deformable Part Models). In addition, this paper compares and contrasts two conventional ultrasound image datasets acquired from two different ultrasound systems. Dataset A comprises 306 (60 malignant and 246 benign) images and Dataset B comprises 163 (53 malignant and 110 benign) images. To overcome the lack of public datasets in this domain, Dataset B will be made available for research purposes. The results demonstrate an overall improvement by the deep learning approaches when assessed on both datasets in terms of True Positive Fraction, False Positives per image, and F-measure.IEEE Journal of Biomedical and Health InformaticsManchester Metropolitan UniversityUniversitat de GironaAberystwyth UniversityUniversity of ManchesterUniversitat Oberta de Catalunya (UOC)201920192018info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://hdl.handle.net/10609/93200reponame:O2, repositorio institucional de la UOCinstname:Universitat Oberta de Catalunya (UOC)InglésIEEE Journal of Biomedical and Health Informatics, 2018, 22(4)https://doi.org/10.1109/jbhi.2017.2731873implied-oainfo:eu-repo/semantics/embargoedAccessoai:openaccess.uoc.edu:10609/932002026-05-28T12:42:01Z
dc.title.none.fl_str_mv Automated breast ultrasound lesions detection using convolutional neural networks
title Automated breast ultrasound lesions detection using convolutional neural networks
spellingShingle Automated breast ultrasound lesions detection using convolutional neural networks
Yap, Moi Hoon
breast cancer
convolutional neural networks
lesion detection
transfer learning
ultrasound imaging
cáncer de mama
redes neuronales convolucionales
detección de lesiones
transferencia de aprendizaje
imagen de ultrasonido
càncer de mama
xarxes neuronals convolucionals
detecció de lesions
transferir l'aprenentatge
imatges per ultrasò
Breast -- Cancer
Mama -- Càncer
Mama -- Cáncer
title_short Automated breast ultrasound lesions detection using convolutional neural networks
title_full Automated breast ultrasound lesions detection using convolutional neural networks
title_fullStr Automated breast ultrasound lesions detection using convolutional neural networks
title_full_unstemmed Automated breast ultrasound lesions detection using convolutional neural networks
title_sort Automated breast ultrasound lesions detection using convolutional neural networks
dc.creator.none.fl_str_mv Yap, Moi Hoon
Pons Rodríguez, Gerard
Martí Bonmatí, Joan
Ganau Macías, Sergi
Sentís Crivellé, Melcior
Zwiggelaar, Reyer
Davison, Adrian K.
Martí Marly, Robert
author Yap, Moi Hoon
author_facet Yap, Moi Hoon
Pons Rodríguez, Gerard
Martí Bonmatí, Joan
Ganau Macías, Sergi
Sentís Crivellé, Melcior
Zwiggelaar, Reyer
Davison, Adrian K.
Martí Marly, Robert
author_role author
author2 Pons Rodríguez, Gerard
Martí Bonmatí, Joan
Ganau Macías, Sergi
Sentís Crivellé, Melcior
Zwiggelaar, Reyer
Davison, Adrian K.
Martí Marly, Robert
author2_role author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv Manchester Metropolitan University
Universitat de Girona
Aberystwyth University
University of Manchester
Universitat Oberta de Catalunya (UOC)
dc.subject.none.fl_str_mv breast cancer
convolutional neural networks
lesion detection
transfer learning
ultrasound imaging
cáncer de mama
redes neuronales convolucionales
detección de lesiones
transferencia de aprendizaje
imagen de ultrasonido
càncer de mama
xarxes neuronals convolucionals
detecció de lesions
transferir l'aprenentatge
imatges per ultrasò
Breast -- Cancer
Mama -- Càncer
Mama -- Cáncer
topic breast cancer
convolutional neural networks
lesion detection
transfer learning
ultrasound imaging
cáncer de mama
redes neuronales convolucionales
detección de lesiones
transferencia de aprendizaje
imagen de ultrasonido
càncer de mama
xarxes neuronals convolucionals
detecció de lesions
transferir l'aprenentatge
imatges per ultrasò
Breast -- Cancer
Mama -- Càncer
Mama -- Cáncer
description Breast lesion detection using ultrasound imaging is considered an important step of computer-aided diagnosis systems. Over the past decade, researchers have demonstrated the possibilities to automate the initial lesion detection. However, the lack of a common dataset impedes research when comparing the performance of such algorithms. This paper proposes the use of deep learning approaches for breast ultrasound lesion detection and investigates three different methods: a Patch-based LeNet, a U-Net, and a transfer learning approach with a pretrained FCN-AlexNet. Their performance is compared against four state-of-the-art lesion detection algorithms (i.e., Radial Gradient Index, Multifractal Filtering, Rule-based Region Ranking, and Deformable Part Models). In addition, this paper compares and contrasts two conventional ultrasound image datasets acquired from two different ultrasound systems. Dataset A comprises 306 (60 malignant and 246 benign) images and Dataset B comprises 163 (53 malignant and 110 benign) images. To overcome the lack of public datasets in this domain, Dataset B will be made available for research purposes. The results demonstrate an overall improvement by the deep learning approaches when assessed on both datasets in terms of True Positive Fraction, False Positives per image, and F-measure.
publishDate 2018
dc.date.none.fl_str_mv 2018
2019
2019
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/10609/93200
url https://hdl.handle.net/10609/93200
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv IEEE Journal of Biomedical and Health Informatics, 2018, 22(4)
https://doi.org/10.1109/jbhi.2017.2731873
dc.rights.none.fl_str_mv implied-oa
info:eu-repo/semantics/embargoedAccess
rights_invalid_str_mv implied-oa
eu_rights_str_mv embargoedAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv IEEE Journal of Biomedical and Health Informatics
publisher.none.fl_str_mv IEEE Journal of Biomedical and Health Informatics
dc.source.none.fl_str_mv reponame:O2, repositorio institucional de la UOC
instname:Universitat Oberta de Catalunya (UOC)
instname_str Universitat Oberta de Catalunya (UOC)
reponame_str O2, repositorio institucional de la UOC
collection O2, repositorio institucional de la UOC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869409431961206784
score 15.301603