Multiple-organ segmentation based on spatially-divided neighboring data energy

Minato Morita, Asuka Okagawa, Yuji Oyamada, Yoshihiko Mochizuki, Hiroshi Ishikawa

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

Abstract

Medical image segmentation, e.g., Computed Tomography (CT) volume segmentation, is necessary for further medical image analysis and computer aided intervention. In the standard energy minimization scheme for medical image segmentation, three terms exist in the energy: the data term, the Potts smoothing term, and the probabilistic atlas term. In this paper, we propose a novel potential function that extends the data term. The discriminability of the existing data term, which fully depends on how distinctive the objects of interest appear on CT volume, has problem when some of the objects have similar or same CT values. We overcome this limitation by considering the CT values of a pair of neighboring voxels. Increasing the voxel of interest to be evaluated, the data term become more discriminable even if some objects of interest have similar CT values. We also propose to learn the probability of the neighboring data term for each sub-region, not for each voxel. The proposed neighboring data term can be regarded as to combine the standard data term and the probabilistic atlas.

Original languageEnglish
Title of host publicationProceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages158-161
Number of pages4
ISBN (Print)9784901122153
DOIs
Publication statusPublished - 2015 Jul 8
Event14th IAPR International Conference on Machine Vision Applications, MVA 2015 - Tokyo, Japan
Duration: 2015 May 182015 May 22

Other

Other14th IAPR International Conference on Machine Vision Applications, MVA 2015
CountryJapan
CityTokyo
Period15/5/1815/5/22

Fingerprint

Tomography
Image segmentation
Image analysis

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Morita, M., Okagawa, A., Oyamada, Y., Mochizuki, Y., & Ishikawa, H. (2015). Multiple-organ segmentation based on spatially-divided neighboring data energy. In Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015 (pp. 158-161). [7153157] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MVA.2015.7153157

Multiple-organ segmentation based on spatially-divided neighboring data energy. / Morita, Minato; Okagawa, Asuka; Oyamada, Yuji; Mochizuki, Yoshihiko; Ishikawa, Hiroshi.

Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 158-161 7153157.

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

Morita, M, Okagawa, A, Oyamada, Y, Mochizuki, Y & Ishikawa, H 2015, Multiple-organ segmentation based on spatially-divided neighboring data energy. in Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015., 7153157, Institute of Electrical and Electronics Engineers Inc., pp. 158-161, 14th IAPR International Conference on Machine Vision Applications, MVA 2015, Tokyo, Japan, 15/5/18. https://doi.org/10.1109/MVA.2015.7153157
Morita M, Okagawa A, Oyamada Y, Mochizuki Y, Ishikawa H. Multiple-organ segmentation based on spatially-divided neighboring data energy. In Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 158-161. 7153157 https://doi.org/10.1109/MVA.2015.7153157
Morita, Minato ; Okagawa, Asuka ; Oyamada, Yuji ; Mochizuki, Yoshihiko ; Ishikawa, Hiroshi. / Multiple-organ segmentation based on spatially-divided neighboring data energy. Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 158-161
@inproceedings{780e852f056448faba6720bd4fcc7da2,
title = "Multiple-organ segmentation based on spatially-divided neighboring data energy",
abstract = "Medical image segmentation, e.g., Computed Tomography (CT) volume segmentation, is necessary for further medical image analysis and computer aided intervention. In the standard energy minimization scheme for medical image segmentation, three terms exist in the energy: the data term, the Potts smoothing term, and the probabilistic atlas term. In this paper, we propose a novel potential function that extends the data term. The discriminability of the existing data term, which fully depends on how distinctive the objects of interest appear on CT volume, has problem when some of the objects have similar or same CT values. We overcome this limitation by considering the CT values of a pair of neighboring voxels. Increasing the voxel of interest to be evaluated, the data term become more discriminable even if some objects of interest have similar CT values. We also propose to learn the probability of the neighboring data term for each sub-region, not for each voxel. The proposed neighboring data term can be regarded as to combine the standard data term and the probabilistic atlas.",
author = "Minato Morita and Asuka Okagawa and Yuji Oyamada and Yoshihiko Mochizuki and Hiroshi Ishikawa",
year = "2015",
month = "7",
day = "8",
doi = "10.1109/MVA.2015.7153157",
language = "English",
isbn = "9784901122153",
pages = "158--161",
booktitle = "Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Multiple-organ segmentation based on spatially-divided neighboring data energy

AU - Morita, Minato

AU - Okagawa, Asuka

AU - Oyamada, Yuji

AU - Mochizuki, Yoshihiko

AU - Ishikawa, Hiroshi

PY - 2015/7/8

Y1 - 2015/7/8

N2 - Medical image segmentation, e.g., Computed Tomography (CT) volume segmentation, is necessary for further medical image analysis and computer aided intervention. In the standard energy minimization scheme for medical image segmentation, three terms exist in the energy: the data term, the Potts smoothing term, and the probabilistic atlas term. In this paper, we propose a novel potential function that extends the data term. The discriminability of the existing data term, which fully depends on how distinctive the objects of interest appear on CT volume, has problem when some of the objects have similar or same CT values. We overcome this limitation by considering the CT values of a pair of neighboring voxels. Increasing the voxel of interest to be evaluated, the data term become more discriminable even if some objects of interest have similar CT values. We also propose to learn the probability of the neighboring data term for each sub-region, not for each voxel. The proposed neighboring data term can be regarded as to combine the standard data term and the probabilistic atlas.

AB - Medical image segmentation, e.g., Computed Tomography (CT) volume segmentation, is necessary for further medical image analysis and computer aided intervention. In the standard energy minimization scheme for medical image segmentation, three terms exist in the energy: the data term, the Potts smoothing term, and the probabilistic atlas term. In this paper, we propose a novel potential function that extends the data term. The discriminability of the existing data term, which fully depends on how distinctive the objects of interest appear on CT volume, has problem when some of the objects have similar or same CT values. We overcome this limitation by considering the CT values of a pair of neighboring voxels. Increasing the voxel of interest to be evaluated, the data term become more discriminable even if some objects of interest have similar CT values. We also propose to learn the probability of the neighboring data term for each sub-region, not for each voxel. The proposed neighboring data term can be regarded as to combine the standard data term and the probabilistic atlas.

UR - http://www.scopus.com/inward/record.url?scp=84941208334&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84941208334&partnerID=8YFLogxK

U2 - 10.1109/MVA.2015.7153157

DO - 10.1109/MVA.2015.7153157

M3 - Conference contribution

AN - SCOPUS:84941208334

SN - 9784901122153

SP - 158

EP - 161

BT - Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -