Show simple item record

dc.contributor.authorPatenaude, Brian
dc.contributor.authorSmith, Stephen M.
dc.contributor.authorKennedy, David N.
dc.contributor.authorJenkinson, Mark
dc.date2022-08-11T08:09:07.000
dc.date.accessioned2022-08-23T16:18:25Z
dc.date.available2022-08-23T16:18:25Z
dc.date.issued2011-06-01
dc.date.submitted2015-03-30
dc.identifier.citationPatenaude B, Smith SM, Kennedy DN, Jenkinson M. A Bayesian model of shape and appearance for subcortical brain segmentation. Neuroimage. 2011 Jun 1;56(3):907-22. doi: 10.1016/j.neuroimage.2011.02.046. Epub 2011 Feb 23. PubMed PMID: 21352927; PubMed Central PMCID: PMC3417233. <a href="http://dx.doi.org/10.1016/j.neuroimage.2011.02.046">Link to article on publisher's site</a>
dc.identifier.issn1053-8119 (Linking)
dc.identifier.doi10.1016/j.neuroimage.2011.02.046
dc.identifier.pmid21352927
dc.identifier.urihttp://hdl.handle.net/20.500.14038/34809
dc.description.abstractAutomatic segmentation of subcortical structures in human brain MR images is an important but difficult task due to poor and variable intensity contrast. Clear, well-defined intensity features are absent in many places along typical structure boundaries and so extra information is required to achieve successful segmentation. A method is proposed here that uses manually labelled image data to provide anatomical training information. It utilises the principles of the Active Shape and Appearance Models but places them within a Bayesian framework, allowing probabilistic relationships between shape and intensity to be fully exploited. The model is trained for 15 different subcortical structures using 336 manually-labelled T1-weighted MR images. Using the Bayesian approach, conditional probabilities can be calculated easily and efficiently, avoiding technical problems of ill-conditioned covariance matrices, even with weak priors, and eliminating the need for fitting extra empirical scaling parameters, as is required in standard Active Appearance Models. Furthermore, differences in boundary vertex locations provide a direct, purely local measure of geometric change in structure between groups that, unlike voxel-based morphometry, is not dependent on tissue classification methods or arbitrary smoothing. In this paper the fully-automated segmentation method is presented and assessed both quantitatively, using Leave-One-Out testing on the 336 training images, and qualitatively, using an independent clinical dataset involving Alzheimer's disease. Median Dice overlaps between 0.7 and 0.9 are obtained with this method, which is comparable or better than other automated methods. An implementation of this method, called FIRST, is currently distributed with the freely-available FSL package.
dc.language.isoen_US
dc.relation<a href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=pubmed&cmd=Retrieve&list_uids=21352927&dopt=Abstract">Link to Article in PubMed</a>
dc.relation.urlhttp://www.ncbi.nlm.nih.gov/pmc/articles/PMC3417233/
dc.subjectAdolescent
dc.subjectAdult
dc.subjectAged
dc.subjectAlgorithms
dc.subjectArtificial Intelligence
dc.subjectBayes Theorem
dc.subjectBrain
dc.subjectFemale
dc.subjectHumans
dc.subjectImage Processing, Computer-Assisted
dc.subjectLinear Models
dc.subjectMagnetic Resonance Imaging
dc.subjectMale
dc.subjectMiddle Aged
dc.subject*Models, Neurological
dc.subjectModels, Statistical
dc.subjectReproducibility of Results
dc.subjectThalamus
dc.subjectYoung Adult
dc.subjectNervous System
dc.subjectNeuroscience and Neurobiology
dc.subjectPsychiatry and Psychology
dc.subjectRadiology
dc.subjectStatistical Models
dc.titleA Bayesian model of shape and appearance for subcortical brain segmentation
dc.typeJournal Article
dc.source.journaltitleNeuroImage
dc.source.volume56
dc.source.issue3
dc.identifier.legacycoverpagehttps://escholarship.umassmed.edu/iddrc_pubs/30
dc.identifier.contextkey6919892
html.description.abstract<p>Automatic segmentation of subcortical structures in human brain MR images is an important but difficult task due to poor and variable intensity contrast. Clear, well-defined intensity features are absent in many places along typical structure boundaries and so extra information is required to achieve successful segmentation. A method is proposed here that uses manually labelled image data to provide anatomical training information. It utilises the principles of the Active Shape and Appearance Models but places them within a Bayesian framework, allowing probabilistic relationships between shape and intensity to be fully exploited. The model is trained for 15 different subcortical structures using 336 manually-labelled T1-weighted MR images. Using the Bayesian approach, conditional probabilities can be calculated easily and efficiently, avoiding technical problems of ill-conditioned covariance matrices, even with weak priors, and eliminating the need for fitting extra empirical scaling parameters, as is required in standard Active Appearance Models. Furthermore, differences in boundary vertex locations provide a direct, purely local measure of geometric change in structure between groups that, unlike voxel-based morphometry, is not dependent on tissue classification methods or arbitrary smoothing. In this paper the fully-automated segmentation method is presented and assessed both quantitatively, using Leave-One-Out testing on the 336 training images, and qualitatively, using an independent clinical dataset involving Alzheimer's disease. Median Dice overlaps between 0.7 and 0.9 are obtained with this method, which is comparable or better than other automated methods. An implementation of this method, called FIRST, is currently distributed with the freely-available FSL package.</p>
dc.identifier.submissionpathiddrc_pubs/30
dc.contributor.departmentIntellectual and Developmental Disabilities Research Center
dc.contributor.departmentDepartment of Psychiatry
dc.source.pages907-22


Files in this item

Thumbnail
Name:
Publisher version

This item appears in the following Collection(s)

Show simple item record