Fully automatic and segmentation-robust classification of breast tumors based on local texture analysis of ultrasound images

In this paper, a novel fully automatic classification method of breast tumors using ultrasound (US) image is proposed. The proposed method can be divided into two steps: “ROI generation step” and “ROI classification step”. In the ROI generation step, the proposed method focuses on finding a credible ROI instead of finding the precise location of the breast tumor. In the ROI classification step, local textures in the ROI are considered with a novel strategy. Both steps were implemented by utilizing supervised texture classification approach. The experiments demonstrate that the proposed method is effective and useful for classifying breast tumors.