| 1. |
- Holdfeldt, Peter, 1976-, et al.
(författare)
-
A Dynamic Programming Inspired Method for Boundary Detection in Ultrasound Image Sequences with Application to Brachial Artery Flow-Mediated Dilation (FMD) Studies
- 2009
-
Rapport (övrigt vetenskapligt)abstract
- 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.
|
|
| 2. |
- Holdfeldt, Peter, 1976-, et al.
(författare)
-
A New Method Based on Dynamic Programming for Boundary Detection in Ultrasound Image Sequences
- 2008
-
Ingår i: Engineering in Medicine and Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE. EMBC 2008, August 20-24, Vancouver, Canada. - 557-170X. - 978-1-4244-1814-5 ; s. 3072-3074
-
Konferensbidrag (refereegranskat)abstract
- Dynamic programming has previously been used when measuring Lumen Diameter (LD) and Intima-Media Thickness (IMT) in single frame ultrasound carotid artery images [1]. An extension to multiframe detection of that procedure is proposed in this paper. Our new method transforms a three dimensional problem into multiple two dimensional problems that can again be solved by dynamic programming. First, several “candidate boundaries” are detected in each image. Then, one boundary from each image in the sequence is selected in such a way that the sequence of boundaries is optimal among the considered possibilities. A model of the movements of the boundaries is used in the second step. Our proposed method shows promising performance on both synthetic and real ultrasound data.
|
|
| 3. |
|
|
