A Bayesian approach for edge detection in medical ultrasound images

Successful applications of digital image processing techniques to medical u ltrasound images have been limited in part because of the lack of an useful imaging model for clinical ultrasound B-scans. In this work, we derive a d iscrete linear imaging model appropriate for clinical ultrasound B-scans. B ased on the newly derived model, we developed a Bayesian restoration approa ch that is currently designed for the generation of correct edges of medica l ultrasound images. Our results demonstrate that successful edge detection can indeed be achieved by the proposed method. The proposed Bayesian appro ach is very flexible and has the potential of being extended to perform spe ckle reduction, edge detection, and region segmentation at the same time.