A clustering algorithm for liver lesion segmentation of diffusion-weighted MR images

Abhinav K. Jha; Jeffrey J. Rodríguez; Renu M. Stephen; Alison T. Stopeck

doi:10.1109/SSIAI.2010.5483911

A clustering algorithm for liver lesion segmentation of diffusion-weighted MR images

Abhinav K. Jha, Jeffrey J. Rodríguez, Renu M. Stephen, Alison T. Stopeck

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

20 Scopus citations

Abstract

In diffusion-weighted magnetic resonance imaging, accurate segmentation of liver lesions in the diffusion-weighted images is required for computation of the apparent diffusion coefficient (ADC) of the lesion, the parameter that serves as an indicator of lesion response to therapy. However, the segmentation problem is challenging due to low SNR, fuzzy boundaries and speckle and motion artifacts. We propose a clustering algorithm that incorporates spatial information and a geometric constraint to solve this issue. We show that our algorithm provides improved accuracy compared to existing segmentation algorithms.

Original language	English (US)
Title of host publication	2010 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2010 - Proceedings
Pages	93-96
Number of pages	4
DOIs	https://doi.org/10.1109/SSIAI.2010.5483911
State	Published - 2010
Event	2010 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2010 - Austin, TX, United States Duration: May 23 2010 → May 25 2010

Publication series

Name	Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation

Other

Other	2010 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2010
Country/Territory	United States
City	Austin, TX
Period	5/23/10 → 5/25/10

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Computer Science Applications

Access to Document

10.1109/SSIAI.2010.5483911

Cite this

Jha, A. K., Rodríguez, J. J., Stephen, R. M., & Stopeck, A. T. (2010). A clustering algorithm for liver lesion segmentation of diffusion-weighted MR images. In 2010 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2010 - Proceedings (pp. 93-96). Article 5483911 (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation). https://doi.org/10.1109/SSIAI.2010.5483911

A clustering algorithm for liver lesion segmentation of diffusion-weighted MR images. / Jha, Abhinav K.; Rodríguez, Jeffrey J.; Stephen, Renu M. et al.
2010 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2010 - Proceedings. 2010. p. 93-96 5483911 (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation).

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

Jha, AK, Rodríguez, JJ, Stephen, RM & Stopeck, AT 2010, A clustering algorithm for liver lesion segmentation of diffusion-weighted MR images. in 2010 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2010 - Proceedings., 5483911, Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation, pp. 93-96, 2010 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2010, Austin, TX, United States, 5/23/10. https://doi.org/10.1109/SSIAI.2010.5483911

Jha AK, Rodríguez JJ, Stephen RM, Stopeck AT. A clustering algorithm for liver lesion segmentation of diffusion-weighted MR images. In 2010 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2010 - Proceedings. 2010. p. 93-96. 5483911. (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation). doi: 10.1109/SSIAI.2010.5483911

@inproceedings{3049b3f683834f8e9ba5fe10d7336800,

title = "A clustering algorithm for liver lesion segmentation of diffusion-weighted MR images",

abstract = "In diffusion-weighted magnetic resonance imaging, accurate segmentation of liver lesions in the diffusion-weighted images is required for computation of the apparent diffusion coefficient (ADC) of the lesion, the parameter that serves as an indicator of lesion response to therapy. However, the segmentation problem is challenging due to low SNR, fuzzy boundaries and speckle and motion artifacts. We propose a clustering algorithm that incorporates spatial information and a geometric constraint to solve this issue. We show that our algorithm provides improved accuracy compared to existing segmentation algorithms.",

author = "Jha, {Abhinav K.} and Rodr{\'i}guez, {Jeffrey J.} and Stephen, {Renu M.} and Stopeck, {Alison T.}",

year = "2010",

doi = "10.1109/SSIAI.2010.5483911",

language = "English (US)",

isbn = "9781424478026",

series = "Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation",

pages = "93--96",

booktitle = "2010 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2010 - Proceedings",

note = "2010 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2010 ; Conference date: 23-05-2010 Through 25-05-2010",

}

TY - GEN

T1 - A clustering algorithm for liver lesion segmentation of diffusion-weighted MR images

AU - Jha, Abhinav K.

AU - Rodríguez, Jeffrey J.

AU - Stephen, Renu M.

AU - Stopeck, Alison T.

PY - 2010

Y1 - 2010

N2 - In diffusion-weighted magnetic resonance imaging, accurate segmentation of liver lesions in the diffusion-weighted images is required for computation of the apparent diffusion coefficient (ADC) of the lesion, the parameter that serves as an indicator of lesion response to therapy. However, the segmentation problem is challenging due to low SNR, fuzzy boundaries and speckle and motion artifacts. We propose a clustering algorithm that incorporates spatial information and a geometric constraint to solve this issue. We show that our algorithm provides improved accuracy compared to existing segmentation algorithms.

AB - In diffusion-weighted magnetic resonance imaging, accurate segmentation of liver lesions in the diffusion-weighted images is required for computation of the apparent diffusion coefficient (ADC) of the lesion, the parameter that serves as an indicator of lesion response to therapy. However, the segmentation problem is challenging due to low SNR, fuzzy boundaries and speckle and motion artifacts. We propose a clustering algorithm that incorporates spatial information and a geometric constraint to solve this issue. We show that our algorithm provides improved accuracy compared to existing segmentation algorithms.

UR - http://www.scopus.com/inward/record.url?scp=77954813276&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954813276&partnerID=8YFLogxK

U2 - 10.1109/SSIAI.2010.5483911

DO - 10.1109/SSIAI.2010.5483911

M3 - Conference contribution

AN - SCOPUS:77954813276

SN - 9781424478026

T3 - Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation

SP - 93

EP - 96

BT - 2010 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2010 - Proceedings

T2 - 2010 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2010

Y2 - 23 May 2010 through 25 May 2010

ER -

A clustering algorithm for liver lesion segmentation of diffusion-weighted MR images

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this