Integrating anatomical priors in ECT reconstruction via joint mixtures and mutual information

A. Rangarajan; I. T. Hsiao; G. Gindi

Integrating anatomical priors in ECT reconstruction via joint mixtures and mutual information

A. Rangarajan^*
, I. T. Hsiao
, G. Gindi

^*Corresponding author for this work

Yale University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

We present a joint mixture model for integrating anatomical information in ECT reconstruction. The mixture model acts as a Bayesian prior with the added benefit of the anatomical segmentation pixel-region labels guiding the reconstruction process. An additional hyper-prior on the mixture occupation probability is introduced. This has the novel interpretation of maximizing the mutual information between the anatomical image and the evolving ECT reconstruction. Results are presented on a phantom with the bias/variance tradeoff being the indicator of performance.

Original language	English
Title of host publication	IEEE Nuclear Science Symposium and Medical Imaging Conference
Publisher	IEEE
Pages	1584-1588
Number of pages	5
ISBN (Print)	0780350227
State	Published - 1999
Externally published	Yes
Event	Proceedings of the 1998 IEEE Nuclear Science Symposium Conference Record - Toronto, Que, Can Duration: 08 11 1998 → 14 11 1998

Publication series

Name	IEEE Nuclear Science Symposium and Medical Imaging Conference
Volume	3

Conference

Conference	Proceedings of the 1998 IEEE Nuclear Science Symposium Conference Record
City	Toronto, Que, Can
Period	08/11/98 → 14/11/98

Cite this

@inproceedings{137c71ae76a84a56925a0387d18ca492,

title = "Integrating anatomical priors in ECT reconstruction via joint mixtures and mutual information",

abstract = "We present a joint mixture model for integrating anatomical information in ECT reconstruction. The mixture model acts as a Bayesian prior with the added benefit of the anatomical segmentation pixel-region labels guiding the reconstruction process. An additional hyper-prior on the mixture occupation probability is introduced. This has the novel interpretation of maximizing the mutual information between the anatomical image and the evolving ECT reconstruction. Results are presented on a phantom with the bias/variance tradeoff being the indicator of performance.",

author = "A. Rangarajan and Hsiao, \{I. T.\} and G. Gindi",

year = "1999",

language = "英语",

isbn = "0780350227",

series = "IEEE Nuclear Science Symposium and Medical Imaging Conference",

publisher = "IEEE",

pages = "1584--1588",

booktitle = "IEEE Nuclear Science Symposium and Medical Imaging Conference",

note = "Proceedings of the 1998 IEEE Nuclear Science Symposium Conference Record ; Conference date: 08-11-1998 Through 14-11-1998",

}

Rangarajan, A, Hsiao, IT & Gindi, G 1999, Integrating anatomical priors in ECT reconstruction via joint mixtures and mutual information. in IEEE Nuclear Science Symposium and Medical Imaging Conference. IEEE Nuclear Science Symposium and Medical Imaging Conference, vol. 3, IEEE, pp. 1584-1588, Proceedings of the 1998 IEEE Nuclear Science Symposium Conference Record, Toronto, Que, Can, 08/11/98.

Integrating anatomical priors in ECT reconstruction via joint mixtures and mutual information. / Rangarajan, A.; Hsiao, I. T.; Gindi, G.
IEEE Nuclear Science Symposium and Medical Imaging Conference. IEEE, 1999. p. 1584-1588 (IEEE Nuclear Science Symposium and Medical Imaging Conference; Vol. 3).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Integrating anatomical priors in ECT reconstruction via joint mixtures and mutual information

AU - Rangarajan, A.

AU - Hsiao, I. T.

AU - Gindi, G.

PY - 1999

Y1 - 1999

N2 - We present a joint mixture model for integrating anatomical information in ECT reconstruction. The mixture model acts as a Bayesian prior with the added benefit of the anatomical segmentation pixel-region labels guiding the reconstruction process. An additional hyper-prior on the mixture occupation probability is introduced. This has the novel interpretation of maximizing the mutual information between the anatomical image and the evolving ECT reconstruction. Results are presented on a phantom with the bias/variance tradeoff being the indicator of performance.

AB - We present a joint mixture model for integrating anatomical information in ECT reconstruction. The mixture model acts as a Bayesian prior with the added benefit of the anatomical segmentation pixel-region labels guiding the reconstruction process. An additional hyper-prior on the mixture occupation probability is introduced. This has the novel interpretation of maximizing the mutual information between the anatomical image and the evolving ECT reconstruction. Results are presented on a phantom with the bias/variance tradeoff being the indicator of performance.

UR - https://www.scopus.com/pages/publications/0032596971

M3 - 会议稿件

AN - SCOPUS:0032596971

SN - 0780350227

T3 - IEEE Nuclear Science Symposium and Medical Imaging Conference

SP - 1584

EP - 1588

BT - IEEE Nuclear Science Symposium and Medical Imaging Conference

PB - IEEE

T2 - Proceedings of the 1998 IEEE Nuclear Science Symposium Conference Record

Y2 - 8 November 1998 through 14 November 1998

ER -

Integrating anatomical priors in ECT reconstruction via joint mixtures and mutual information

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this