A robust graph-based segmentation method for breast tumors in ultrasound images

ObjectivesThis paper introduces a new graph-based method for segmenting breast tumors in US images.Background and motivationSegmentation for breast tumors in ultrasound (US) images is crucial for computer-aided diagnosis system, but it has always been a difficult task due to the defects inherent in the US images, such as speckles and low contrast.MethodsThe proposed segmentation algorithm constructed a graph using improved neighborhood models. In addition, taking advantages of local statistics, a new pair-wise region comparison predicate that was insensitive to noises was proposed to determine the mergence of any two of adjacent subregions.Results and conclusionExperimental results have shown that the proposed method could improve the segmentation accuracy by 1.5–5.6% in comparison with three often used segmentation methods, and should be capable of segmenting breast tumors in US images.

► A new graph-based method was proposed for segmentation of ultrasound images.
► The characteristics of ultrasound images were incorporated into the method.
► The local statistics were used in the proposed method, and improved the robustness.
► The proposed method could more accurately extract regions of breast tumors.