Quasi-automatic initialization for parametric active contours
Pattern Recognition Letters
| Hi-index | 0.00 |
One of the major issues of active contouring methods is their sensitivity to the initial contour that is provided by the user. Unless it is drawn close enough to the actual contour, it may lead to unsatisfactory results. Thus, most active contour algorithms require considerable user interaction to provide a good initial contour. In this paper we present an efficient and fast rule- based algorithm for generating a good carotid artery initial contour from ultrasound images. Our algorithm reduces user interaction, as a user is only required to place a seed point inside the region of interest. Sensitivity, precision rate, and overlap ratio have been used to assess the amount of correlation between manually segmented lumens by an experienced clinician and by our algorithm, where the obtained 95% confidence interval of the mean value of these measures over all test cases are: [78.32% plusmn 1.98], [91.77% plusmn 1.96], and [72.68% plusmn 1.90], respectively. Furthermore, the output of our proposed scheme can be used as an input to any active contour algorithm to produce even better results.