Malignant-lesion segmentation using 4D co-occurrence texture analysis applied to dynamic contrast-enhanced magnetic resonance breast image data

Simple item page
dc.citation.epage501en_US
dc.citation.issueNumber3en_US
dc.citation.spage495en_US
dc.citation.volumeNumber25en_US
dc.contributor.authorWoods, B.J.en_US
dc.contributor.authorClymer, B.D.en_US
dc.contributor.authorKurc, T.en_US
dc.contributor.authorHeverhagen J.T.en_US
dc.contributor.authorStevens, R.en_US
dc.contributor.authorOrsdemir, A.en_US
dc.contributor.authorBulan O.en_US
dc.contributor.authorKnopp, M.V.en_US
dc.date.accessioned2016-02-08T10:15:14Z
dc.date.available2016-02-08T10:15:14Z
dc.date.issued2007en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractPurpose: To investigate the use of four-dimensional (4D) co-occurrence-based texture analysis to distinguish between nonmalignant and malignant tissues in dynamic contrast-enhanced (DCE) MR images. Materials and Methods: 4D texture analysis was performedon DCE-MRI data sets of breast lesions. A model-free neural network-based classification system assigned each voxel a "nonmalignant" or "malignant" label based on the textural features. The classification results were compared via receiver operating characteristic (ROC) curve analysis with the manual lesion segmentation produced by two radiologists (observers 1 and 2). Results: The mean sensitivity and specificity of the classifier agreed with the mean observer 2 performance when compared with segmentations by observer 1 for a 95% confidence interval, using a two-sided t-test with α = 0.05. The results show that an area under the ROC curve (Az) of 0.99948, 0.99867, and 0.99957 can be achieved by comparing the classifier vs. observer 1, classifier vs. union of both observers, and classifier vs. intersection of both observers, respectively. Conclusion: This study shows that a neural network classifier based on 4D texture analysis inputs can achieve a performance comparable to that achieved by human observers, and that further research in this area is warranted. © 2007 Wiley-Liss, Inc.en_US
dc.identifier.doi10.1002/jmri.20837en_US
dc.identifier.issn10531807
dc.identifier.urihttp://hdl.handle.net/11693/23528
dc.language.isoEnglishen_US
dc.relation.isversionofhttp://dx.doi.org/10.1002/jmri.20837en_US
dc.source.titleJournal of Magnetic Resonance Imagingen_US
dc.subjectBreasten_US
dc.subjectCanceren_US
dc.subjectDCE-MRIen_US
dc.subjectNeural networken_US
dc.subjectTexture analysisen_US
dc.subjectadulten_US
dc.subjectarea under the curveen_US
dc.subjectarticleen_US
dc.subjectartificial neural networken_US
dc.subjectbenign tumoren_US
dc.subjectbreast canceren_US
dc.subjectbreast carcinomaen_US
dc.subjectclinical articleen_US
dc.subjectcontrast enhancementen_US
dc.subjectdiagnostic valueen_US
dc.subjectdifferential diagnosisen_US
dc.subjectfemaleen_US
dc.subjectfibrocystic breast diseaseen_US
dc.subjecthumanen_US
dc.subjectmalignant neoplastic diseaseen_US
dc.subjectnuclear magnetic resonance imagingen_US
dc.subjectpriority journalen_US
dc.subjectradiologisten_US
dc.subjectroc curveen_US
dc.subjectsensitivity and specificityen_US
dc.subjectBiopsyen_US
dc.subjectBreasten_US
dc.subjectBreast Neoplasmsen_US
dc.subjectCarcinoma, Ductal, Breasten_US
dc.subjectContrast Mediaen_US
dc.subjectDiagnosis, Differentialen_US
dc.subjectFemaleen_US
dc.subjectFibrocystic Breast Diseaseen_US
dc.subjectHumansen_US
dc.subjectImage Enhancementen_US
dc.subjectImage Interpretation, Computer-Assisteden_US
dc.subjectImage Processing, Computer-Assisteden_US
dc.subjectMagnetic Resonance Imagingen_US
dc.subjectMeglumineen_US
dc.subjectNeural Networks (Computer)en_US
dc.subjectObserver Variationen_US
dc.subjectOrganometallic Compoundsen_US
dc.subjectRetrospective Studiesen_US
dc.subjectROC Curveen_US
dc.subjectSensitivity and Specificityen_US
dc.titleMalignant-lesion segmentation using 4D co-occurrence texture analysis applied to dynamic contrast-enhanced magnetic resonance breast image dataen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Malignant-lesion segmentation using 4D co-occurrence texture analysis applied to dynamic contrast-enhanced magnetic resonance breast image data.pdf
Size:
949.65 KB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Department of Electrical and Electronics Engineering