Abstract:<\/h2>\n
Multi-atlas<\/span> segmentation provides a general purpose, fully-automated approach for transferring spatial information from an existing dataset (“atlases”) to a previously unseen context (“target”) through image registration. The method to resolve voxelwise label<\/span> conflicts between the registered atlases (“label<\/span> fusion<\/span>“) has a substantial impact on segmentation quality. Ideally, statistical<\/span> fusion<\/span> algorithms (e.g., STAPLE) would result in accurate segmentations as they provide a framework to elegantly integrate models of rater performance. The accuracy of statistical<\/span> fusion<\/span> hinges upon accurately modeling the underlying process of how raters err. Despite success on human raters, current approaches inaccurately model multi-atlas<\/span> behavior as they fail to seamlessly incorporate exogenous intensity information into the estimation process. As a result, locally weighted voting algorithms represent the de facto standard fusion<\/span> approach in clinical applications. Moreover, regardless of the approach, fusion<\/span> algorithms are generally dependent upon large atlas sets and highly accurate registration as they implicitly assume that the registered atlases form a collectively unbiased representation of the target. Herein, we propose a novel statistical<\/span> fusion<\/span> algorithm, Non-Local<\/span> STAPLE (NLS). NLS reformulates the STAPLE framework from a non-local<\/span> means perspective in order to learn what label<\/span> an atlas would have observed, given perfect correspondence. Through this reformulation, NLS (1) seamlessly integrates intensity into the estimation process, (2) provides a theoretically consistent model of multi-atlas<\/span> observation error, and (3) largely diminishes the need for large atlas sets and very high-quality registrations. We assess the sensitivity and optimality of the approach and demonstrate significant improvement in two empirical multi-atlas<\/span> experiments. Andrew J. Asman and Bennett A. Landman. \u201cNon-Local Statistical Label Fusion for Multi-Atlas Segmentation.\u201d Medical Image Analysis (MEDIA). 2013. 17(2):194-208. PMC23265798 \u2020 Full Text: https:\/\/www.ncbi.nlm.nih.gov\/pubmed\/23265798 Abstract: Multi-atlas segmentation provides a general purpose, fully-automated approach for transferring spatial information from an existing dataset (“atlases”) to a previously unseen context (“target”) through image registration. The method to…<\/p>\n","protected":false},"author":6299,"featured_media":333,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3,46],"tags":[12,47,48,21,42],"class_list":["post-308","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-image-segmentation","category-multi-atlas-segmentation","tag-multi-atlas","tag-nls","tag-non-local-staple","tag-segmentation","tag-staple"],"_links":{"self":[{"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/posts\/308","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/users\/6299"}],"replies":[{"embeddable":true,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/comments?post=308"}],"version-history":[{"count":1,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/posts\/308\/revisions"}],"predecessor-version":[{"id":335,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/posts\/308\/revisions\/335"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/media\/333"}],"wp:attachment":[{"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/media?parent=308"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/categories?post=308"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/tags?post=308"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}![\"nihms531393f4\"](\"https:\/\/my.vanderbilt.edu\/masi\/wp-content\/uploads\/sites\/2304\n2661\/2016\/10\/nihms531393f4-3.jpg\")
<\/p>\n","protected":false},"excerpt":{"rendered":"