Automatic contouring for breast tumors in 2-d sonography.

Automatic contouring for breast tumors using medical ultrasound (US) imaging may assist physicians, without relevant experience, in making correct diagnoses. This study utilizes the watershed transform and active contour model (ACM) to overcome the natural properties of US images, speckle, noise and tissue-related textures, to segment the breast tumors precisely. The watershed transform is performed as the automatic initial contouring procedure to maintain a rough tumor shape and boundary. Next, ACM automatically determines the exquisite contours of the tumor. The results of computer simulations reveal that the proposed method always identified similar contours and regions-of-interest (ROI) as were obtained by manual contouring (by an experienced physician) of the breast tumor in US images. As ultrasound imaging becomes more widespread, a functional automatic contouring is essential to clinical application. In computer-aided diagnosis (CAD) applications, moreover, automatic contouring can save much of the time required to sketch a precise contour, with very high stability.