Self-affine snake for medical image segmentation

•We establish a comprehensive theoretical basis for self-affine snake (SAS).•We expand the cost function of contractive self-affine maps to avoid uncertainties.•The computational burden of SAS is enhanced by dynamic-efficient implementation.•A number of outstanding properties of SAS are experimentally assessed.•The effectivity and efficiency of SAS are evaluated for medical image segmentation.

In this paper, a new parametric active contour called self-affine snake is proposed for medical image segmentation. It integrates the wavelet transform, parametric active contour (or snake), and self-affine mapping system to keep their strengths and avoid the weak points. In more detail, it inherits wide capture range from wavelet transform and topological consistency from snake. Furthermore, it takes advantage of self-affine mapping system in several aspects including (i) convergence to weak boundaries, especially, next to strong edges, (ii) reconstruction of boundary openings, and (iii) progress into boundary concavities. The experimental results were performed using a number of synthetic and medical images given in five sets of experiments. Self-affine snake provided comparable/superior results in terms of both solution quality and CPU time compared to a number of frequently-used active contours including balloon, gradient vector flow (GVF), generalized GVF, and active contour without edges. However, its most important properties were the significant robustness against noise and reconstruction of boundary openings. Because of the valuable advantages, the proposed algorithm is an appropriate approach, particularly, for segmentation of medical images which usually suffers from noise corruption and edge uncertainty.

Graphical abstractFigure optionsDownload full-size imageDownload high-quality image (665 K)Download as PowerPoint slide