A Dynamic Programming Inspired Method for Boundary Detection in Ultrasound Image Sequences with Application to Brachial Artery Flow-Mediated Dilation (FMD) Studies

Report, 2009

This paper describes a new method for boundary detection in ultrasound image sequences with specific application to brachial artery flow-mediated dilation (FMD) studies. The method represents an extension to conventional two-dimensional dynamic programming to be applied in a three-dimensional (spatio-temporal) context. A total of 42 digital image sequences, each of which contained 240 frames, were analyzed. The majority (34) of these sequences were analyzed successfully, and a few (8) partly successful. Following automated boundary detection, vessel diameter extrema (minima and maxima) could easily be computed and used for FMD calculations. It was concluded that the new method, although optimality when moving from two to three dimensions cannot be guaranteed, outperforms conventional dynamic programming.