A sonography image processing system for tumour segmentation

ABSTRACT

A sonography image processing system for tumour segmentation is implemented by using the active contour model based on level set formulation. To achieve extraction of weak edges in speckle noisy images, the level set model called Edge Attraction Force on Chan and Vese model is developed. The cell competition algorithm is modified by adding the information of the cells’ edges. Calculus of variation is taken to derive the evolution equation of the active contour. Experiments demonstrate that the boundaries of tumours extracted by the proposed active contour are more accurate for conquering the drawbacks coming from weak edges. Experiments demonstrate that the boundaries of tumors extracted by the proposed active contour are accurate and the results avoid the drawbacks of the weak edges.