Detecting acromegaly: screening for disease with a morphable model.

2.50
Hdl Handle:
http://hdl.handle.net/10541/72587
Title:
Detecting acromegaly: screening for disease with a morphable model.
Authors:
Learned-Miller, Erik G; Lu, Qifeng; Paisley, Angela N; Trainer, Peter J; Blanz, Volker; Dedden, Katrin; Miller, Ralph
Abstract:
Acromegaly is a rare disorder which affects about 50 of every million people. The disease typically causes swelling of the hands, feet, and face, and eventually permanent changes to areas such as the jaw, brow ridge, and cheek bones. The disease is often missed by physicians and progresses beyond where it might if it were identified and treated earlier. We consider a semi-automated approach to detecting acromegaly, using a novel combination of support vector machines (SVMs) and a morphable model. Our training set consists of 24 frontal photographs of acromegalic patients and 25 of disease-free subjects. We modelled each subject's face in an analysis-by-synthesis loop using the three-dimensional morphable face model of Blanz and Vetter. The model parameters capture many features of the 3D shape of the subject's head from just a single photograph, and are used directly for classification. We report encouraging results of a classifier built from the training set of real human subjects.
Affiliation:
University of Massachusetts, Amherst, Massachusetts, USA. elm@cs.umass.edu
Citation:
Detecting acromegaly: screening for disease with a morphable model. 2006, 9 (Pt 2):495-503 Med Image Comput Comput Assist Interv Int Conf Med Image Comput Comput Assist Interv
Journal:
Medical Image Computing and Computer-Assisted Intervention
Issue Date:
2006
URI:
http://hdl.handle.net/10541/72587
PubMed ID:
17354809
Type:
Article
Language:
en
Appears in Collections:
All Christie Publications

Full metadata record

DC FieldValue Language
dc.contributor.authorLearned-Miller, Erik G-
dc.contributor.authorLu, Qifeng-
dc.contributor.authorPaisley, Angela N-
dc.contributor.authorTrainer, Peter J-
dc.contributor.authorBlanz, Volker-
dc.contributor.authorDedden, Katrin-
dc.contributor.authorMiller, Ralph-
dc.date.accessioned2009-07-06T14:06:45Z-
dc.date.available2009-07-06T14:06:45Z-
dc.date.issued2006-
dc.identifier.citationDetecting acromegaly: screening for disease with a morphable model. 2006, 9 (Pt 2):495-503 Med Image Comput Comput Assist Interv Int Conf Med Image Comput Comput Assist Interven
dc.identifier.pmid17354809-
dc.identifier.urihttp://hdl.handle.net/10541/72587-
dc.description.abstractAcromegaly is a rare disorder which affects about 50 of every million people. The disease typically causes swelling of the hands, feet, and face, and eventually permanent changes to areas such as the jaw, brow ridge, and cheek bones. The disease is often missed by physicians and progresses beyond where it might if it were identified and treated earlier. We consider a semi-automated approach to detecting acromegaly, using a novel combination of support vector machines (SVMs) and a morphable model. Our training set consists of 24 frontal photographs of acromegalic patients and 25 of disease-free subjects. We modelled each subject's face in an analysis-by-synthesis loop using the three-dimensional morphable face model of Blanz and Vetter. The model parameters capture many features of the 3D shape of the subject's head from just a single photograph, and are used directly for classification. We report encouraging results of a classifier built from the training set of real human subjects.en
dc.language.isoenen
dc.subject.meshAcromegaly-
dc.subject.meshAlgorithms-
dc.subject.meshArtificial Intelligence-
dc.subject.meshCephalometry-
dc.subject.meshComputer Simulation-
dc.subject.meshFace-
dc.subject.meshHumans-
dc.subject.meshImage Enhancement-
dc.subject.meshImage Interpretation, Computer-Assisted-
dc.subject.meshImaging, Three-Dimensional-
dc.subject.meshMass Screening-
dc.subject.meshModels, Biological-
dc.subject.meshPattern Recognition, Automated-
dc.subject.meshPhotography-
dc.subject.meshReproducibility of Results-
dc.subject.meshSensitivity and Specificity-
dc.titleDetecting acromegaly: screening for disease with a morphable model.en
dc.typeArticleen
dc.contributor.departmentUniversity of Massachusetts, Amherst, Massachusetts, USA. elm@cs.umass.eduen
dc.identifier.journalMedical Image Computing and Computer-Assisted Interventionen

Related articles on PubMed

All Items in Christie are protected by copyright, with all rights reserved, unless otherwise indicated.