Show simple item record

dc.contributor.authorGaldran, Adrian
dc.contributor.authorPicon, Artzai
dc.contributor.authorGarrote, Estibaliz
dc.contributor.authorPardo, David
dc.date.accessioned2016-04-19T10:58:36Z
dc.date.available2016-04-19T10:58:36Z
dc.date.issued2015
dc.identifier.citationPATTERN RECOGNITION AND IMAGE ANALYSIS (IBPRIA 2015), Book Series: Lecture Notes in Computer Science, Volume: 9117, pp. 587-594, 2015en
dc.identifier.isbn978-3-319-19390-8en
dc.identifier.urihttp://hdl.handle.net/11556/200
dc.description.abstractPectoral muscle segmentation on medio-lateral oblique views of mammograms represents an important preprocessing step in many mammographic image analysis tasks. Although its location can be per- ceptually obvious for a human observer, the variability in shape, size, and intensities of the pectoral muscle boundary turns its automatic segmen- tation into a challenging problem. In this work we propose to decompose the input mammogram into its textural and structural components at di erent scales prior to dynamically thresholding it into several levels. The resulting segmentations are re ned with an active contour model and merged together by means of a simple voting scheme to remove possible outliers. Our method performs well compared to several other state-of- the-art techniques. An average DICE similarity coe cient of 0:91 and mean Hausdor distance of 3:66 3:23 mm. validate our approach.en
dc.language.isoengen
dc.publisherSpringeren
dc.titlePectoral Muscle Segmentation in Mammograms Based on Cartoon-Texture Decompositionen
dc.typeconferenceObjecten
dc.isiYesen
dc.rights.accessRightsopenAccessen
dc.subject.keywordsPectoral Muscle Segmentationen
dc.subject.keywordsMammographic Image Analysisen
dc.subject.keywordsBreast Cancer Detectionen
dc.subject.keywordsComputer-Aided Diagnosisen


Files in this item

Thumbnail

    Show simple item record