Semi-supervised segmentation of ultrasound images based on patch representation and continuous min cut.
Fiche du document
2014
- doi: 10.1371/journal.pone.0100972
- issn: 1932-6203
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/doi/10.1371/journal.pone.0100972
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/pmid/25010530
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/eissn/1932-6203
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/urn/urn:nbn:ch:serval-BIB_1D06022B9DAB1
info:eu-repo/semantics/openAccess , Copying allowed only for non-profit organizations , https://serval.unil.ch/disclaimer
Sujets proches
Diseases--ImagingCiter ce document
A. Ciurte et al., « Semi-supervised segmentation of ultrasound images based on patch representation and continuous min cut. », Serveur académique Lausannois, ID : 10.1371/journal.pone.0100972
Métriques
Partage / Export
Résumé
Ultrasound segmentation is a challenging problem due to the inherent speckle and some artifacts like shadows, attenuation and signal dropout. Existing methods need to include strong priors like shape priors or analytical intensity models to succeed in the segmentation. However, such priors tend to limit these methods to a specific target or imaging settings, and they are not always applicable to pathological cases. This work introduces a semi-supervised segmentation framework for ultrasound imaging that alleviates the limitation of fully automatic segmentation, that is, it is applicable to any kind of target and imaging settings. Our methodology uses a graph of image patches to represent the ultrasound image and user-assisted initialization with labels, which acts as soft priors. The segmentation problem is formulated as a continuous minimum cut problem and solved with an efficient optimization algorithm. We validate our segmentation framework on clinical ultrasound imaging (prostate, fetus, and tumors of the liver and eye). We obtain high similarity agreement with the ground truth provided by medical expert delineations in all applications (94% DICE values in average) and the proposed algorithm performs favorably with the literature.