Abstract
Partial volume effects are present in nearly all medical imaging data. These artifacts blur the boundaries between different regions, making accurate delineation of anatomical structures difficult. In this paper, we propose a method for unsupervised estimation of partial volume effects in single-channel image data. Based on a statistical image model, an algorithm is derived for estimating both partial volumes and the means of the different tissue classes in the image. To compensate for the ill-posed nature of the estimation problem, we employ a Bayesian approach that places a prior probability model on the parameters. We demonstrate on simulated and real images that the new algorithm is superior in several respects to the fuzzy and Gaussian clustering algorithms that have previously been used for modeling partial volume effects.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis |
| Publisher | IEEE |
| Pages | 170-177 |
| Number of pages | 8 |
| State | Published - 2000 |
| Externally published | Yes |
| Event | MMBIA-2000: IEEE Workshop on Mathematical Methods in Biomedical Image Analysis - Hilton Head Island, SC, USA Duration: Jun 11 2000 → Jun 12 2000 |
Other
| Other | MMBIA-2000: IEEE Workshop on Mathematical Methods in Biomedical Image Analysis |
|---|---|
| City | Hilton Head Island, SC, USA |
| Period | 6/11/00 → 6/12/00 |
Fingerprint
ASJC Scopus subject areas
- Analysis
Cite this
Unsupervised partial volume estimation in single-channel image data. / Pham, Dzung L.; Prince, Jerry Ladd.
Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis. IEEE, 2000. p. 170-177.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Unsupervised partial volume estimation in single-channel image data
AU - Pham, Dzung L.
AU - Prince, Jerry Ladd
PY - 2000
Y1 - 2000
N2 - Partial volume effects are present in nearly all medical imaging data. These artifacts blur the boundaries between different regions, making accurate delineation of anatomical structures difficult. In this paper, we propose a method for unsupervised estimation of partial volume effects in single-channel image data. Based on a statistical image model, an algorithm is derived for estimating both partial volumes and the means of the different tissue classes in the image. To compensate for the ill-posed nature of the estimation problem, we employ a Bayesian approach that places a prior probability model on the parameters. We demonstrate on simulated and real images that the new algorithm is superior in several respects to the fuzzy and Gaussian clustering algorithms that have previously been used for modeling partial volume effects.
AB - Partial volume effects are present in nearly all medical imaging data. These artifacts blur the boundaries between different regions, making accurate delineation of anatomical structures difficult. In this paper, we propose a method for unsupervised estimation of partial volume effects in single-channel image data. Based on a statistical image model, an algorithm is derived for estimating both partial volumes and the means of the different tissue classes in the image. To compensate for the ill-posed nature of the estimation problem, we employ a Bayesian approach that places a prior probability model on the parameters. We demonstrate on simulated and real images that the new algorithm is superior in several respects to the fuzzy and Gaussian clustering algorithms that have previously been used for modeling partial volume effects.
UR - http://www.scopus.com/inward/record.url?scp=0033687088&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0033687088&partnerID=8YFLogxK
M3 - Conference contribution
SP - 170
EP - 177
BT - Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis
PB - IEEE
ER -