Item


Evaluating lesion segmentation on breast sonography as related to lesion type

Breast sonography currently provides a complementary diagnosis when other modalities are not conclusive. However, lesion segmentation on sonography is still a challenging problem due to the presence of artifacts. To solve these problems, Markov random fields and maximum a posteriori-based methods are used to estimate a distortion field while identifying regions of similar intensity inhomogeneity. In this study, different initialization approaches were exhaustively evaluated using a database of 212 B-mode breast sonograms and considering the lesion types. Finally, conclusions about the relationship between the segmentation results and lesions types are described

This work was partially supported by Spanish Science and Innovation grant TIN2011-23704 and by a predoctoral grant from the recruitment of new research personnel program of the Generalitat de Catalunya

American Institute of Ultrasound in Medicine

Manager: Ministerio de Ciencia e Innovación (Espanya)
Author: Pons Rodríguez, Gerard
Martí Bonmatí, Joan
Martí Marly, Robert
Ganau, Sergi
Vilanova, Joan Carles
Noble, J. Alison
Abstract: Breast sonography currently provides a complementary diagnosis when other modalities are not conclusive. However, lesion segmentation on sonography is still a challenging problem due to the presence of artifacts. To solve these problems, Markov random fields and maximum a posteriori-based methods are used to estimate a distortion field while identifying regions of similar intensity inhomogeneity. In this study, different initialization approaches were exhaustively evaluated using a database of 212 B-mode breast sonograms and considering the lesion types. Finally, conclusions about the relationship between the segmentation results and lesions types are described
This work was partially supported by Spanish Science and Innovation grant TIN2011-23704 and by a predoctoral grant from the recruitment of new research personnel program of the Generalitat de Catalunya
Format: application/pdf
Document access: http://hdl.handle.net/10256/11347
Language: eng
Publisher: American Institute of Ultrasound in Medicine
Collection: info:eu-repo/semantics/altIdentifier/doi/10.7863/ultra.32.9.1659
info:eu-repo/semantics/altIdentifier/issn/0278-4297
info:eu-repo/semantics/altIdentifier/eissn/1550-9613
info:eu-repo/grantAgreement/MICINN//TIN2011-23704/ES/M3CAD. MULTI-MODALITY AND MULTI-VIEW MAMMOGRAPHIC COMPUTER AIDED DIAGNOSIS SYSTEM/
Rights: Tots els drets reservats
Subject: Mama -- Càncer -- Diagnòstic
Breast -- Cancer -- Diagnosis
Ecografia
Ultrasonic imaging
Title: Evaluating lesion segmentation on breast sonography as related to lesion type
Type: info:eu-repo/semantics/article
Repository: DUGiDocs

Subjects

Authors