Contour extraction from ultrasound images viewed as a tracking problem
Donka S. Angelova, Lyudmila S. Mihaylova · 2009
Abstract – This paper focuses on the problem of con-tour extraction in medical images and shows that this segmentation task can be viewed as a tracking problem. The influence of the speckle noise and of the high non-linearities is overcome by Monte Carlo methods. An efficient multiple model Monte Carlo algorithm for pro-gressive contour growing (tracking) is developed, ac-counting for convex, non-circular forms of delineated contour areas. The driving idea of the proposed filter consists in the incorporation of different image inten-sity inside and outside the contour into the filter like-lihood. A PDA procedure using the contour edge mag-nitude is applied to cope with the measurement origin uncertainty. The filter performance is studied by ex-tracting contours from a number of real and simulated ultrasound medical images and very good accuracy is achieved.