Show simple item record

dc.contributor.authorAl Arif, SMMR
dc.contributor.authorKnapp, K
dc.contributor.authorSlabaugh, G
dc.date.accessioned2019-11-26T12:24:16Z
dc.date.issued2018-09-26
dc.description.abstractShape has widely been used in medical image segmentation algorithms to constrain a segmented region to a class of learned shapes. Recent methods for object segmentation mostly use deep learning algorithms. The state-of-the-art deep segmentation networks are trained with loss functions defined in a pixel-wise manner, which is not suitable for learning topological shape information and constraining segmentation results. In this paper, we propose a novel shape predictor network for object segmentation. The proposed deep fully convolutional neural network learns to predict shapes instead of learning pixel-wise classification. We apply the novel shape predictor network to X-ray images of cervical vertebra where shape is of utmost importance. The proposed network is trained with a novel loss function that computes the error in the shape domain. Experimental results demonstrate the effectiveness of the proposed method to achieve state-of-the-art segmentation, with correct topology and accurate fitting that matches expert segmentation.en_GB
dc.description.sponsorshipEngineering and Physical Sciences Research Council (EPSRC)en_GB
dc.description.sponsorshipRoyal Devon and Exeter NHS Foundation Trusten_GB
dc.identifier.citationIn: Medical Image Computing and Computer Assisted Intervention – MICCAI 2018, edited by A. Frangi, J. Schnabel, C. Davatzikos, C. Alberola-López, and G. Fichtinger, pp. 430-439 . Lecture Notes in Computer Science, vol 11070en_GB
dc.identifier.doi10.1007/978-3-030-00928-1_49
dc.identifier.urihttp://hdl.handle.net/10871/39804
dc.language.isoenen_GB
dc.publisherSpringeren_GB
dc.rights© Springer Nature Switzerland AG 2018en_GB
dc.titleSPNet: Shape Prediction Using a Fully Convolutional Neural Networken_GB
dc.typeBook chapteren_GB
dc.date.available2019-11-26T12:24:16Z
dc.relation.isPartOfMedical Image Computing and Computer Assisted Intervention – MICCAI 2018en_GB
dc.descriptionThis is the author accepted manuscript. The final version is available from Springer via the DOI in this recorden_GB
dc.rights.urihttp://www.rioxx.net/licenses/all-rights-reserveden_GB
exeter.funder::Engineering and Physical Sciences Research Council (EPSRC)en_GB
exeter.funder::Royal Devon & Exeter NHS Foundation Trsten_GB
rioxxterms.versionAMen_GB
rioxxterms.licenseref.startdate2018-09-26
rioxxterms.typeBook chapteren_GB
refterms.dateFCD2019-11-26T12:22:56Z
refterms.versionFCDAM
refterms.dateFOA2019-11-26T12:24:20Z


Files in this item

This item appears in the following Collection(s)

Show simple item record