A combination of parabolic and grid slope interpolation for 2D tissue displacement estimations
(2017) In Medical & Biological Engineering & Computing 55(8). p.1327-1338- Abstract
Parabolic sub-sample interpolation for 2D block-matching motion estimation is computationally efficient. However, it is well known that the parabolic interpolation gives a biased motion estimate for displacements greater than |y.2| samples (y = 0, 1, …). Grid slope sub-sample interpolation is less biased, but it shows large variability for displacements close to y.0. We therefore propose to combine these sub-sample methods into one method (GS15PI) using a threshold to determine when to use which method. The proposed method was evaluated on simulated, phantom, and in vivo ultrasound cine loops and was compared to three sub-sample interpolation methods. On average, GS15PI reduced the absolute sub-sample estimation errors in the simulated... (More)
Parabolic sub-sample interpolation for 2D block-matching motion estimation is computationally efficient. However, it is well known that the parabolic interpolation gives a biased motion estimate for displacements greater than |y.2| samples (y = 0, 1, …). Grid slope sub-sample interpolation is less biased, but it shows large variability for displacements close to y.0. We therefore propose to combine these sub-sample methods into one method (GS15PI) using a threshold to determine when to use which method. The proposed method was evaluated on simulated, phantom, and in vivo ultrasound cine loops and was compared to three sub-sample interpolation methods. On average, GS15PI reduced the absolute sub-sample estimation errors in the simulated and phantom cine loops by 14, 8, and 24% compared to sub-sample interpolation of the image, parabolic sub-sample interpolation, and grid slope sub-sample interpolation, respectively. The limited in vivo evaluation of estimations of the longitudinal movement of the common carotid artery using parabolic and grid slope sub-sample interpolation and GS15PI resulted in coefficient of variation (CV) values of 6.9, 7.5, and 6.8%, respectively. The proposed method is computationally efficient and has low bias and variance. The method is another step toward a fast and reliable method for clinical investigations of longitudinal movement of the arterial wall.
(Less)
- author
- Albinsson, John LU ; Ahlgren, Åsa Rydén LU ; Jansson, Tomas LU and Cinthio, Magnus LU
- organization
- publishing date
- 2017-08
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Block matching, In silico, In vivo, Speckle tracking, Sub-sample estimation, Ultrasound
- in
- Medical & Biological Engineering & Computing
- volume
- 55
- issue
- 8
- pages
- 1327 - 1338
- publisher
- Springer
- external identifiers
-
- pmid:27837312
- wos:000407310300016
- scopus:84994759890
- ISSN
- 0140-0118
- DOI
- 10.1007/s11517-016-1593-7
- language
- English
- LU publication?
- yes
- id
- 0b80ae87-73d9-4202-b392-36aa53230ebb
- date added to LUP
- 2016-11-28 13:53:32
- date last changed
- 2024-09-07 02:52:32
@article{0b80ae87-73d9-4202-b392-36aa53230ebb, abstract = {{<p>Parabolic sub-sample interpolation for 2D block-matching motion estimation is computationally efficient. However, it is well known that the parabolic interpolation gives a biased motion estimate for displacements greater than |y.2| samples (y = 0, 1, …). Grid slope sub-sample interpolation is less biased, but it shows large variability for displacements close to y.0. We therefore propose to combine these sub-sample methods into one method (GS15PI) using a threshold to determine when to use which method. The proposed method was evaluated on simulated, phantom, and in vivo ultrasound cine loops and was compared to three sub-sample interpolation methods. On average, GS15PI reduced the absolute sub-sample estimation errors in the simulated and phantom cine loops by 14, 8, and 24% compared to sub-sample interpolation of the image, parabolic sub-sample interpolation, and grid slope sub-sample interpolation, respectively. The limited in vivo evaluation of estimations of the longitudinal movement of the common carotid artery using parabolic and grid slope sub-sample interpolation and GS15PI resulted in coefficient of variation (CV) values of 6.9, 7.5, and 6.8%, respectively. The proposed method is computationally efficient and has low bias and variance. The method is another step toward a fast and reliable method for clinical investigations of longitudinal movement of the arterial wall.</p>}}, author = {{Albinsson, John and Ahlgren, Åsa Rydén and Jansson, Tomas and Cinthio, Magnus}}, issn = {{0140-0118}}, keywords = {{Block matching; In silico; In vivo; Speckle tracking; Sub-sample estimation; Ultrasound}}, language = {{eng}}, number = {{8}}, pages = {{1327--1338}}, publisher = {{Springer}}, series = {{Medical & Biological Engineering & Computing}}, title = {{A combination of parabolic and grid slope interpolation for 2D tissue displacement estimations}}, url = {{http://dx.doi.org/10.1007/s11517-016-1593-7}}, doi = {{10.1007/s11517-016-1593-7}}, volume = {{55}}, year = {{2017}}, }