Back to overview

Semi-supervised segmentation of ultrasound images based on patch representation and continuous min cut.

Type of publication Peer-reviewed
Publikationsform Original article (peer-reviewed)
Author Ciurte Anca, Bresson Xavier, Cuisenaire Olivier, Houhou Nawal, Nedevschi Sergiu, Thiran Jean-Philippe, Bach Cuadra Meritxell,
Project Novel Image Processing Methods for Fetal MR Imaging: 3D Reconstruction and Segmentation with Soft Priors
Show all

Original article (peer-reviewed)

Journal PloS one
Volume (Issue) 9(7)
Page(s) 100972 - 100972
Title of proceedings PloS one
DOI 10.1371/journal.pone.0100972

Open Access

Type of Open Access Publisher (Gold Open Access)


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.