We present a semi-supervised segmentation framework for B-mode ultrasound imaging. 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 optimisation algorithm.
Works using fP-CMC should cite:
Anca Ciurte, Xavier Bresson, Olivier Cuisenaire, Nawal Houhou, Sergiu Nedevschi, Jean-Philippe Thiran, Meritxell Bach Cuadra, Semi-Supervised Segmentation of Ultrasound Images based on Patch Representation and Continuous Min Cut. Plos One, Volume 9, Number 7, July 2014 . DOI: 10.1371/journal.pone.0100972.
Ciurte, Anca, Cuisenaire, Olivier, Bresson, Xavier, & Bach Cuadra, Meritxell. (2020, March 24). Software fP-CMC: Fast Patch-based Continuous Min-Cut segmentation. Semi-supervised Segmentation of Ultrasound Images Based on Patch Representation and Continuous Min Cut. Zenodo. http://doi.org/10.5281/zenodo.3725998
The code can be downloaded here.