3D breast registration for PET-CT and MR based on surface matching

Hakjae Lee, Kisung Lee, Mincheol Ko, Jungwon Kang, Ilyang Joo, Hyeonjoon Moon, Kyeong Min Kim

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

2 Citations (Scopus)

Abstract

The objective of this study is to develop a 3D breast image registration algorithm for PET-CT and MR system. Proposed algorithm consists of three stages: breast segmentation, surface matching, and image transformation. Contrast-enhanced MR image volume was used as a reference and CT volume was transformed with varying parameters to calculate similarity between two image modalities. At first, the breast regions were cropped separately by the pre-determined regional masks. For the CT image case, region growing based breast segmentation was explored to eliminate the breast dedicated jig which has been developed to hold the shape of breast during PET-CT scan. After the segmentation, each of the points set of breast surface has been extracted. The extracted point sets were used as a feature vector for the surface matching. For the surface matching, we developed modified version of elastic-convolved iterative closest point (ECICP) algorithm to obtain the optimal transformation parameters. Then PET image was transformed with those parameters and overlaid it onto MR image. The results of this study show that the difference between MR and CT image has been considerably reduced and the suspicious lesions on MR and PET images were matched as well.

Original languageEnglish
Title of host publicationIEEE Nuclear Science Symposium Conference Record
Pages3121-3124
Number of pages4
DOIs
Publication statusPublished - 2012 Mar 26
Event2011 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2011 - Valencia, Spain
Duration: 2011 Oct 232011 Oct 29

Other

Other2011 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2011
CountrySpain
CityValencia
Period11/10/2311/10/29

Fingerprint

breast
Breast
Cone-Beam Computed Tomography
jigs
Masks
Positron Emission Tomography Computed Tomography
lesions
masks

ASJC Scopus subject areas

  • Radiation
  • Nuclear and High Energy Physics
  • Radiology Nuclear Medicine and imaging

Cite this

Lee, H., Lee, K., Ko, M., Kang, J., Joo, I., Moon, H., & Kim, K. M. (2012). 3D breast registration for PET-CT and MR based on surface matching. In IEEE Nuclear Science Symposium Conference Record (pp. 3121-3124). [6152567] https://doi.org/10.1109/NSSMIC.2011.6152567

3D breast registration for PET-CT and MR based on surface matching. / Lee, Hakjae; Lee, Kisung; Ko, Mincheol; Kang, Jungwon; Joo, Ilyang; Moon, Hyeonjoon; Kim, Kyeong Min.

IEEE Nuclear Science Symposium Conference Record. 2012. p. 3121-3124 6152567.

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

Lee, H, Lee, K, Ko, M, Kang, J, Joo, I, Moon, H & Kim, KM 2012, 3D breast registration for PET-CT and MR based on surface matching. in IEEE Nuclear Science Symposium Conference Record., 6152567, pp. 3121-3124, 2011 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2011, Valencia, Spain, 11/10/23. https://doi.org/10.1109/NSSMIC.2011.6152567
Lee H, Lee K, Ko M, Kang J, Joo I, Moon H et al. 3D breast registration for PET-CT and MR based on surface matching. In IEEE Nuclear Science Symposium Conference Record. 2012. p. 3121-3124. 6152567 https://doi.org/10.1109/NSSMIC.2011.6152567
Lee, Hakjae ; Lee, Kisung ; Ko, Mincheol ; Kang, Jungwon ; Joo, Ilyang ; Moon, Hyeonjoon ; Kim, Kyeong Min. / 3D breast registration for PET-CT and MR based on surface matching. IEEE Nuclear Science Symposium Conference Record. 2012. pp. 3121-3124
@inproceedings{1d57eb17bdf8495ca15048d487f4cb75,
title = "3D breast registration for PET-CT and MR based on surface matching",
abstract = "The objective of this study is to develop a 3D breast image registration algorithm for PET-CT and MR system. Proposed algorithm consists of three stages: breast segmentation, surface matching, and image transformation. Contrast-enhanced MR image volume was used as a reference and CT volume was transformed with varying parameters to calculate similarity between two image modalities. At first, the breast regions were cropped separately by the pre-determined regional masks. For the CT image case, region growing based breast segmentation was explored to eliminate the breast dedicated jig which has been developed to hold the shape of breast during PET-CT scan. After the segmentation, each of the points set of breast surface has been extracted. The extracted point sets were used as a feature vector for the surface matching. For the surface matching, we developed modified version of elastic-convolved iterative closest point (ECICP) algorithm to obtain the optimal transformation parameters. Then PET image was transformed with those parameters and overlaid it onto MR image. The results of this study show that the difference between MR and CT image has been considerably reduced and the suspicious lesions on MR and PET images were matched as well.",
author = "Hakjae Lee and Kisung Lee and Mincheol Ko and Jungwon Kang and Ilyang Joo and Hyeonjoon Moon and Kim, {Kyeong Min}",
year = "2012",
month = "3",
day = "26",
doi = "10.1109/NSSMIC.2011.6152567",
language = "English",
isbn = "9781467301183",
pages = "3121--3124",
booktitle = "IEEE Nuclear Science Symposium Conference Record",

}

TY - GEN

T1 - 3D breast registration for PET-CT and MR based on surface matching

AU - Lee, Hakjae

AU - Lee, Kisung

AU - Ko, Mincheol

AU - Kang, Jungwon

AU - Joo, Ilyang

AU - Moon, Hyeonjoon

AU - Kim, Kyeong Min

PY - 2012/3/26

Y1 - 2012/3/26

N2 - The objective of this study is to develop a 3D breast image registration algorithm for PET-CT and MR system. Proposed algorithm consists of three stages: breast segmentation, surface matching, and image transformation. Contrast-enhanced MR image volume was used as a reference and CT volume was transformed with varying parameters to calculate similarity between two image modalities. At first, the breast regions were cropped separately by the pre-determined regional masks. For the CT image case, region growing based breast segmentation was explored to eliminate the breast dedicated jig which has been developed to hold the shape of breast during PET-CT scan. After the segmentation, each of the points set of breast surface has been extracted. The extracted point sets were used as a feature vector for the surface matching. For the surface matching, we developed modified version of elastic-convolved iterative closest point (ECICP) algorithm to obtain the optimal transformation parameters. Then PET image was transformed with those parameters and overlaid it onto MR image. The results of this study show that the difference between MR and CT image has been considerably reduced and the suspicious lesions on MR and PET images were matched as well.

AB - The objective of this study is to develop a 3D breast image registration algorithm for PET-CT and MR system. Proposed algorithm consists of three stages: breast segmentation, surface matching, and image transformation. Contrast-enhanced MR image volume was used as a reference and CT volume was transformed with varying parameters to calculate similarity between two image modalities. At first, the breast regions were cropped separately by the pre-determined regional masks. For the CT image case, region growing based breast segmentation was explored to eliminate the breast dedicated jig which has been developed to hold the shape of breast during PET-CT scan. After the segmentation, each of the points set of breast surface has been extracted. The extracted point sets were used as a feature vector for the surface matching. For the surface matching, we developed modified version of elastic-convolved iterative closest point (ECICP) algorithm to obtain the optimal transformation parameters. Then PET image was transformed with those parameters and overlaid it onto MR image. The results of this study show that the difference between MR and CT image has been considerably reduced and the suspicious lesions on MR and PET images were matched as well.

UR - http://www.scopus.com/inward/record.url?scp=84863353857&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863353857&partnerID=8YFLogxK

U2 - 10.1109/NSSMIC.2011.6152567

DO - 10.1109/NSSMIC.2011.6152567

M3 - Conference contribution

AN - SCOPUS:84863353857

SN - 9781467301183

SP - 3121

EP - 3124

BT - IEEE Nuclear Science Symposium Conference Record

ER -