Show simple item record

FieldValueLanguage
dc.contributor.authorLi, Ang
dc.contributor.authorLi, Changyang
dc.contributor.authorWang, Xiuying
dc.contributor.authorEberl, Stefan
dc.contributor.authorFeng, Dagan
dc.contributor.authorFulham, Michael
dc.date.accessioned2020-02-10
dc.date.available2020-02-10
dc.date.issued2016-07-27
dc.identifier.citationAng Li et al 2016 Phys. Med. Biol. 61 6085en_AU
dc.identifier.urihttps://hdl.handle.net/2123/21808
dc.description.abstractBlurred boundaries and heterogeneous intensities make accurate prostate MR image segmentation problematic. To improve prostate MR image segmentation we suggest an approach that includes: (a) an image patch division method to partition the prostate into homogeneous segments for feature extraction; (b) an image feature formulation and classification method, using the relevance vector machine, to provide probabilistic prior knowledge for graph energy construction; (c) a graph energy formulation scheme with Bayesian priors and Dirichlet graph energy and (d) a non-iterative graph energy minimization scheme, based on matrix differentiation, to perform the probabilistic pixel membership optimization. The segmentation output was obtained by assigning pixels with foreground and background labels based on derived membership probabilities. We evaluated our approach on the PROMISE-12 dataset with 50 prostate MR image volumes. Our approach achieved a mean dice similarity coefficient (DSC) of 0.90  ±  0.02, which surpassed the five best prior-based methods in the PROMISE-12 segmentation challenge.en_AU
dc.description.sponsorshipARCen_AU
dc.language.isoen_AUen_AU
dc.publisherIOPen_AU
dc.relationARC LP140100686en_AU
dc.subjectimage segmentation, prostate imaging, Bayesian inferenceen_AU
dc.titleA Combinatorial Bayesian and Dirichlet Model for Prostate MR Image Segmentation Using Probabilistic Image Featuresen_AU
dc.typeArticleen_AU
dc.subject.asrc080106 - Image Processingen_AU
dc.subject.asrc080109 - Pattern Recognition and Data Miningen_AU
dc.identifier.doi10.1088/0031-9155/61/16/6085
dc.type.pubtypePost-printen_AU


Show simple item record

Associated file/s

Associated collections

Show simple item record

There are no previous versions of the item available.