Adaptive expanding B-snake model for extracting ultrasound breast lump boundary

Abstract

In this paper we introduce a new adaptive expanding B-snake model (AEBS) to extract 2-D ultrasound breast lump boundaries, using B-spline to split the whole snake energy into smaller parts to achieve both global deformation and local variation. Due to the noisy property of ultrasound breast lump images, initial model is loaded inside lump area and an expanding force is used to reduce the 'noise' from the breast tissues. Which has been improved after a pre-processing before the AEBS. Local elements' gradient is used as a feedback of contour deformation to make the expanding force to act intelligently. The balance of all defined forces in t-n (tangent and normal) coordinates is used as a terminating criterion. A serial of parallel-scanned ultrasound breast lump images have been used in the testing and results show our method works correctly and consistently.