Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorYap, Moi Hoon-
dc.contributor.authorPons Rodríguez, Gerard-
dc.contributor.authorMartí Bonmatí, Joan-
dc.contributor.authorGanau Macías, Sergi-
dc.contributor.authorSentís Crivellé, Melcior-
dc.contributor.authorZwiggelaar, Reyer-
dc.contributor.authorDavison, Adrian K.-
dc.contributor.authorMartí Marly, Robert-
dc.contributor.otherManchester Metropolitan University-
dc.contributor.otherUniversitat de Girona-
dc.contributor.otherAberystwyth University-
dc.contributor.otherUniversity of Manchester-
dc.contributor.otherUniversitat Oberta de Catalunya (UOC)-
dc.identifier.citationYap, M.H., Pons, G., Martí, J., Ganau, S., Sentís, M., Zwiggelaar, R., Davison, A.K. & Martí, R. (2018). Automated breast ultrasound lesions detection using convolutional neural networks. IEEE Journal of Biomedical and Health Informatics, 22(4), 1218-1226. doi: 10.1109/JBHI.2017.2731873-
dc.description.abstractBreast 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.en
dc.publisherIEEE Journal of Biomedical and Health Informatics-
dc.relation.ispartofIEEE Journal of Biomedical and Health Informatics, 2018, 22(4)-
dc.subjectbreast canceren
dc.subjectconvolutional neural networksen
dc.subjectlesion detectionen
dc.subjecttransfer learningen
dc.subjectultrasound imagingen
dc.subjectcáncer de mamaes
dc.subjectredes neuronales convolucionaleses
dc.subjectdetección de lesioneses
dc.subjecttransferencia de aprendizajees
dc.subjectimagen de ultrasonidoes
dc.subjectcàncer de mamaca
dc.subjectxarxes neuronals convolucionalsca
dc.subjectdetecció de lesionsca
dc.subjecttransferir l'aprenentatgeca
dc.subjectimatges per ultrasòca
dc.subject.lcshBreast -- Canceren
dc.titleAutomated breast ultrasound lesions detection using convolutional neural networks-
dc.subject.lemacMama -- Càncerca
dc.subject.lcshesMama -- Cánceres
Appears in Collections:Articles cientÍfics
Articles cientÍfIcs

Files in This Item:
File Description SizeFormat 
  Restricted Access
896,61 kBAdobe PDFView/Open Request a copy
View statistics

Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.