Current studentsExisting staffContact us
 

Lung nodule classification by jointly using visual descriptors and deep features

Simple item page
dc.contributor.authorXie, Y.
dc.contributor.authorZhang, J.
dc.contributor.authorLiu, S.
dc.contributor.authorCai, W.
dc.contributor.authorXia, Y.
dc.contributor.conferenceMedical Image Computing and Computer-Assisted Intervention (MICCAI) (21 Oct 2016 - 21 Oct 2016 : Athens, Greece)
dc.contributor.editorMuller, H.
dc.contributor.editorKelm, B.M.
dc.contributor.editorArbel, T.
dc.contributor.editorCai, W.
dc.contributor.editorCardoso, M.J.
dc.contributor.editorLangs, G.
dc.contributor.editorMenze, B.
dc.contributor.editorMetaxas, D.
dc.contributor.editorMontillo, A.
dc.contributor.editorWells, W.M.
dc.contributor.editorZhang, S.
dc.contributor.editorChung, A.C.S.
dc.contributor.editorJenkinson, M.
dc.contributor.editorRibbens, A.
dc.date.issued2017
dc.description.abstractClassifying benign and malignant lung nodules using the thoracic computed tomography (CT) screening is the primary method for early diagnosis of lung cancer. Despite of their widely recognized success in image classification, deep learning techniques may not achieve satisfying accuracy on this problem, due to the limited training samples resulted from the all-consuming nature of medical image acquisition and annotation. In this paper, we jointly use the texture and shape descriptors, which characterize the heterogeneity of nodules, and the features learned by a deep convolutional neural network, and thus proposed a combined-feature based classification (CFBC) algorithm to differentiate lung nodules. We have evaluated this algorithm against four state-of-the-art nodule classification approaches on the benchmark LIDC-IDRI dataset. Our results suggest that the proposed CFBC algorithm can distinguish malignant lung nodules from benign ones more accurately than other four methods.
dc.description.statementofresponsibilityYutong Xie, Jianpeng Zhang, Sidong Liu, Weidong Cai, and Yong Xia
dc.identifier.citationLecture Notes in Artificial Intelligence, 2017 / Muller, H., Kelm, B.M., Arbel, T., Cai, W., Cardoso, M.J., Langs, G., Menze, B., Metaxas, D., Montillo, A., Wells, W.M., Zhang, S., Chung, A.C.S., Jenkinson, M., Ribbens, A. (ed./s), vol.10081, pp.116-125
dc.identifier.doi10.1007/978-3-319-61188-4_11
dc.identifier.isbn9783319611877
dc.identifier.issn0302-9743
dc.identifier.issn1611-3349
dc.identifier.orcidXie, Y. [0000-0002-6644-1250]
dc.identifier.urihttps://hdl.handle.net/2440/135334
dc.language.isoen
dc.publisherSpringer International Publishing
dc.publisher.placeCham, Switzerland
dc.relation.ispartofseriesLecture Notes in Computer Science; 10081
dc.rights© Springer International Publishing AG 2017
dc.source.urihttps://link.springer.com/book/10.1007/978-3-319-61188-4
dc.subjectLung module classification
dc.subjectComputed tomography
dc.subjectDeep convolutional neural network
dc.subjectTexture descriptor
dc.subjectShape descriptor
dc.titleLung nodule classification by jointly using visual descriptors and deep features
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Computer Science publications