Dynamic PET image segmentation using multiphase level set method

Jinxiu Liao, Jinyi Qi

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

1 Citation (Scopus)

Abstract

Image segmentation plays an important role in medical diagnosis. Most existing segmentation methods are focused on 2-D or 3-D images. Here we propose an image segmentation method for 4-D dynamic PET images. We consider that voxels inside each organ have similar time activity curves. The use of tracer dynamic information allows us to separate regions that have similar integrated activity in a static image but with different temporal responses. We develop a multi-phase level set method (MP-LSM) that utilizes both the spatial and temporal information in a dynamic PET data set. Different weighting factors are assigned to each image frame based on the noise level. We used a weighted absolute difference function in the data matching term to increase the robustness of the estimate and to avoid over-partition of regions with high contrast. The proposed method can be applied to both dynamic and static PET images, as well as coregistered images from dual modality imaging systems, such as PET/CT. We validated the proposed method using computer simulated dynamic PET data, as well as real mouse data from a microPET scanner, and compared the results to that of a dynamic clustering method. The results show that the proposed method results in cleaner and smoother segments and less misclassified voxels.

Original languageEnglish (US)
Title of host publicationIEEE Nuclear Science Symposium Conference Record
Pages2047-2052
Number of pages6
Volume4
DOIs
StatePublished - 2007
Event2006 IEEE Nuclear Science Symposium, Medical Imaging Conference and 15th International Workshop on Room-Temperature Semiconductor X- and Gamma-Ray Detectors, Special Focus Workshops, NSS/MIC/RTSD - San Diego, CA, United States
Duration: Oct 29 2006Nov 4 2006

Other

Other2006 IEEE Nuclear Science Symposium, Medical Imaging Conference and 15th International Workshop on Room-Temperature Semiconductor X- and Gamma-Ray Detectors, Special Focus Workshops, NSS/MIC/RTSD
CountryUnited States
CitySan Diego, CA
Period10/29/0611/4/06

Fingerprint

Image segmentation
Imaging systems

Keywords

  • Dynamic PET
  • Image segmentation
  • Level set method

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Industrial and Manufacturing Engineering

Cite this

Liao, J., & Qi, J. (2007). Dynamic PET image segmentation using multiphase level set method. In IEEE Nuclear Science Symposium Conference Record (Vol. 4, pp. 2047-2052). [4179430] https://doi.org/10.1109/NSSMIC.2006.354316

Dynamic PET image segmentation using multiphase level set method. / Liao, Jinxiu; Qi, Jinyi.

IEEE Nuclear Science Symposium Conference Record. Vol. 4 2007. p. 2047-2052 4179430.

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

Liao, J & Qi, J 2007, Dynamic PET image segmentation using multiphase level set method. in IEEE Nuclear Science Symposium Conference Record. vol. 4, 4179430, pp. 2047-2052, 2006 IEEE Nuclear Science Symposium, Medical Imaging Conference and 15th International Workshop on Room-Temperature Semiconductor X- and Gamma-Ray Detectors, Special Focus Workshops, NSS/MIC/RTSD, San Diego, CA, United States, 10/29/06. https://doi.org/10.1109/NSSMIC.2006.354316
Liao J, Qi J. Dynamic PET image segmentation using multiphase level set method. In IEEE Nuclear Science Symposium Conference Record. Vol. 4. 2007. p. 2047-2052. 4179430 https://doi.org/10.1109/NSSMIC.2006.354316
Liao, Jinxiu ; Qi, Jinyi. / Dynamic PET image segmentation using multiphase level set method. IEEE Nuclear Science Symposium Conference Record. Vol. 4 2007. pp. 2047-2052
@inproceedings{49c1d0c142fb4b39883820af9395d1dc,
title = "Dynamic PET image segmentation using multiphase level set method",
abstract = "Image segmentation plays an important role in medical diagnosis. Most existing segmentation methods are focused on 2-D or 3-D images. Here we propose an image segmentation method for 4-D dynamic PET images. We consider that voxels inside each organ have similar time activity curves. The use of tracer dynamic information allows us to separate regions that have similar integrated activity in a static image but with different temporal responses. We develop a multi-phase level set method (MP-LSM) that utilizes both the spatial and temporal information in a dynamic PET data set. Different weighting factors are assigned to each image frame based on the noise level. We used a weighted absolute difference function in the data matching term to increase the robustness of the estimate and to avoid over-partition of regions with high contrast. The proposed method can be applied to both dynamic and static PET images, as well as coregistered images from dual modality imaging systems, such as PET/CT. We validated the proposed method using computer simulated dynamic PET data, as well as real mouse data from a microPET scanner, and compared the results to that of a dynamic clustering method. The results show that the proposed method results in cleaner and smoother segments and less misclassified voxels.",
keywords = "Dynamic PET, Image segmentation, Level set method",
author = "Jinxiu Liao and Jinyi Qi",
year = "2007",
doi = "10.1109/NSSMIC.2006.354316",
language = "English (US)",
isbn = "1424405610",
volume = "4",
pages = "2047--2052",
booktitle = "IEEE Nuclear Science Symposium Conference Record",

}

TY - GEN

T1 - Dynamic PET image segmentation using multiphase level set method

AU - Liao, Jinxiu

AU - Qi, Jinyi

PY - 2007

Y1 - 2007

N2 - Image segmentation plays an important role in medical diagnosis. Most existing segmentation methods are focused on 2-D or 3-D images. Here we propose an image segmentation method for 4-D dynamic PET images. We consider that voxels inside each organ have similar time activity curves. The use of tracer dynamic information allows us to separate regions that have similar integrated activity in a static image but with different temporal responses. We develop a multi-phase level set method (MP-LSM) that utilizes both the spatial and temporal information in a dynamic PET data set. Different weighting factors are assigned to each image frame based on the noise level. We used a weighted absolute difference function in the data matching term to increase the robustness of the estimate and to avoid over-partition of regions with high contrast. The proposed method can be applied to both dynamic and static PET images, as well as coregistered images from dual modality imaging systems, such as PET/CT. We validated the proposed method using computer simulated dynamic PET data, as well as real mouse data from a microPET scanner, and compared the results to that of a dynamic clustering method. The results show that the proposed method results in cleaner and smoother segments and less misclassified voxels.

AB - Image segmentation plays an important role in medical diagnosis. Most existing segmentation methods are focused on 2-D or 3-D images. Here we propose an image segmentation method for 4-D dynamic PET images. We consider that voxels inside each organ have similar time activity curves. The use of tracer dynamic information allows us to separate regions that have similar integrated activity in a static image but with different temporal responses. We develop a multi-phase level set method (MP-LSM) that utilizes both the spatial and temporal information in a dynamic PET data set. Different weighting factors are assigned to each image frame based on the noise level. We used a weighted absolute difference function in the data matching term to increase the robustness of the estimate and to avoid over-partition of regions with high contrast. The proposed method can be applied to both dynamic and static PET images, as well as coregistered images from dual modality imaging systems, such as PET/CT. We validated the proposed method using computer simulated dynamic PET data, as well as real mouse data from a microPET scanner, and compared the results to that of a dynamic clustering method. The results show that the proposed method results in cleaner and smoother segments and less misclassified voxels.

KW - Dynamic PET

KW - Image segmentation

KW - Level set method

UR - http://www.scopus.com/inward/record.url?scp=38649123728&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38649123728&partnerID=8YFLogxK

U2 - 10.1109/NSSMIC.2006.354316

DO - 10.1109/NSSMIC.2006.354316

M3 - Conference contribution

AN - SCOPUS:38649123728

SN - 1424405610

SN - 9781424405619

VL - 4

SP - 2047

EP - 2052

BT - IEEE Nuclear Science Symposium Conference Record

ER -