MRI based attenuation correction for PET/MRI via MRF segmentation and sparse regression estimated CT

Yasheng Chen, Meher Juttukonda, Yue Z. Lee, Yi Su, Felipe Espinoza, Weili Lin, Dinggang Shen, David Lulash, Hongyu An

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

MR-based attenuation correction (AC) is a prerequisite to fully harnessing the power of the recently introduced hybrid PET/MRI scanner. Assigning attenuation coefficients based upon MR anatomical images alone remains challenging. In this study, we sought to develop a novel approach based upon hidden Markov random field segmentation (hMRFS) and sparse regression (SR) to estimate CT from T1w images for AC in PET reconstruction in the head. The performance of the proposed method was evaluated using patient-specific PET simulation. We compared the mean absolute (MARE) and full width tenth maximum (FWTM) of relative errors of the reconstructed PET images using attenuation maps from the proposed (μ<inf>prop</inf>), averaged atlas (μ<inf>atlas</inf>) and CT segmentation methods (a.k.a. silver standard) and found that our proposed approach produced significantly lower MARE and FWTM in the errors of the reconstructed PET images. Thus, even with T1w contrast alone, we are able to achieve the accuracy on a par with the previous reports using multispectral MRI data.

Original languageEnglish
Title of host publication2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1364-1367
Number of pages4
ISBN (Print)9781467319591
Publication statusPublished - 2014 Jul 29
Externally publishedYes
Event2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 - Beijing, China
Duration: 2014 Apr 292014 May 2

Other

Other2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
CountryChina
CityBeijing
Period14/4/2914/5/2

Fingerprint

Atlases
Magnetic resonance imaging
Head

Keywords

  • Attenuation correction
  • MRI/PET
  • PET/MRI
  • Sparse regression

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Chen, Y., Juttukonda, M., Lee, Y. Z., Su, Y., Espinoza, F., Lin, W., ... An, H. (2014). MRI based attenuation correction for PET/MRI via MRF segmentation and sparse regression estimated CT. In 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 (pp. 1364-1367). [6868131] Institute of Electrical and Electronics Engineers Inc..

MRI based attenuation correction for PET/MRI via MRF segmentation and sparse regression estimated CT. / Chen, Yasheng; Juttukonda, Meher; Lee, Yue Z.; Su, Yi; Espinoza, Felipe; Lin, Weili; Shen, Dinggang; Lulash, David; An, Hongyu.

2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1364-1367 6868131.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chen, Y, Juttukonda, M, Lee, YZ, Su, Y, Espinoza, F, Lin, W, Shen, D, Lulash, D & An, H 2014, MRI based attenuation correction for PET/MRI via MRF segmentation and sparse regression estimated CT. in 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014., 6868131, Institute of Electrical and Electronics Engineers Inc., pp. 1364-1367, 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014, Beijing, China, 14/4/29.
Chen Y, Juttukonda M, Lee YZ, Su Y, Espinoza F, Lin W et al. MRI based attenuation correction for PET/MRI via MRF segmentation and sparse regression estimated CT. In 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 1364-1367. 6868131
Chen, Yasheng ; Juttukonda, Meher ; Lee, Yue Z. ; Su, Yi ; Espinoza, Felipe ; Lin, Weili ; Shen, Dinggang ; Lulash, David ; An, Hongyu. / MRI based attenuation correction for PET/MRI via MRF segmentation and sparse regression estimated CT. 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 1364-1367
@inproceedings{b0cfa64659504c97a7dceb012ade0d9d,
title = "MRI based attenuation correction for PET/MRI via MRF segmentation and sparse regression estimated CT",
abstract = "MR-based attenuation correction (AC) is a prerequisite to fully harnessing the power of the recently introduced hybrid PET/MRI scanner. Assigning attenuation coefficients based upon MR anatomical images alone remains challenging. In this study, we sought to develop a novel approach based upon hidden Markov random field segmentation (hMRFS) and sparse regression (SR) to estimate CT from T1w images for AC in PET reconstruction in the head. The performance of the proposed method was evaluated using patient-specific PET simulation. We compared the mean absolute (MARE) and full width tenth maximum (FWTM) of relative errors of the reconstructed PET images using attenuation maps from the proposed (μprop), averaged atlas (μatlas) and CT segmentation methods (a.k.a. silver standard) and found that our proposed approach produced significantly lower MARE and FWTM in the errors of the reconstructed PET images. Thus, even with T1w contrast alone, we are able to achieve the accuracy on a par with the previous reports using multispectral MRI data.",
keywords = "Attenuation correction, MRI/PET, PET/MRI, Sparse regression",
author = "Yasheng Chen and Meher Juttukonda and Lee, {Yue Z.} and Yi Su and Felipe Espinoza and Weili Lin and Dinggang Shen and David Lulash and Hongyu An",
year = "2014",
month = "7",
day = "29",
language = "English",
isbn = "9781467319591",
pages = "1364--1367",
booktitle = "2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - MRI based attenuation correction for PET/MRI via MRF segmentation and sparse regression estimated CT

AU - Chen, Yasheng

AU - Juttukonda, Meher

AU - Lee, Yue Z.

AU - Su, Yi

AU - Espinoza, Felipe

AU - Lin, Weili

AU - Shen, Dinggang

AU - Lulash, David

AU - An, Hongyu

PY - 2014/7/29

Y1 - 2014/7/29

N2 - MR-based attenuation correction (AC) is a prerequisite to fully harnessing the power of the recently introduced hybrid PET/MRI scanner. Assigning attenuation coefficients based upon MR anatomical images alone remains challenging. In this study, we sought to develop a novel approach based upon hidden Markov random field segmentation (hMRFS) and sparse regression (SR) to estimate CT from T1w images for AC in PET reconstruction in the head. The performance of the proposed method was evaluated using patient-specific PET simulation. We compared the mean absolute (MARE) and full width tenth maximum (FWTM) of relative errors of the reconstructed PET images using attenuation maps from the proposed (μprop), averaged atlas (μatlas) and CT segmentation methods (a.k.a. silver standard) and found that our proposed approach produced significantly lower MARE and FWTM in the errors of the reconstructed PET images. Thus, even with T1w contrast alone, we are able to achieve the accuracy on a par with the previous reports using multispectral MRI data.

AB - MR-based attenuation correction (AC) is a prerequisite to fully harnessing the power of the recently introduced hybrid PET/MRI scanner. Assigning attenuation coefficients based upon MR anatomical images alone remains challenging. In this study, we sought to develop a novel approach based upon hidden Markov random field segmentation (hMRFS) and sparse regression (SR) to estimate CT from T1w images for AC in PET reconstruction in the head. The performance of the proposed method was evaluated using patient-specific PET simulation. We compared the mean absolute (MARE) and full width tenth maximum (FWTM) of relative errors of the reconstructed PET images using attenuation maps from the proposed (μprop), averaged atlas (μatlas) and CT segmentation methods (a.k.a. silver standard) and found that our proposed approach produced significantly lower MARE and FWTM in the errors of the reconstructed PET images. Thus, even with T1w contrast alone, we are able to achieve the accuracy on a par with the previous reports using multispectral MRI data.

KW - Attenuation correction

KW - MRI/PET

KW - PET/MRI

KW - Sparse regression

UR - http://www.scopus.com/inward/record.url?scp=84927920704&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84927920704&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84927920704

SN - 9781467319591

SP - 1364

EP - 1367

BT - 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -