BUS Segmentation

Segmentation code for breast lesions in ultrasound images

The proposed approach comprises three steps as follows. Firstly, the image is preprocessed to remove speckle noise while preserving important features of the image. Three methods are investigated, i.e., Frost Filter, Detail Preserving Anisotropic Diffusion, and Probabilistic Patch-Based Filter. Secondly, Normalized Cut or Quick Shift is used to provide an initial segmentation map for breast lesions. Thirdly, a postprocessing step is proposed to select the correct region from a set of candidate regions.
Authors: Mohamed Elawady, Ibrahim Sadek, Abd El Rahman Shabayek, Gerard Pons, and Sergi Ganau
Paper: http://link.springer.com/chapter/10.1007/978-3-319-41501-7_24
Dataset: UDIAT [163 Images with GT] {Private} (Diagnostic Center of Sabadell, Spain)
Users of this software are encouraged to cite the following article: Elawady, Mohamed, Ibrahim Sadek, Abd El Rahman Shabayek, Gerard Pons, and Sergi Ganau. "Automatic Nonlinear Filtering and Segmentation for Breast Ultrasound Images." In International Conference Image Analysis and Recognition, pp. 206-213. Springer International Publishing, 2016.
github: https://github.com/mawady/bus-segmentation