Left endocardium segmentation using spatio-temporal Metamorphs

Xinyi Cui, Shaoting Zhang, Junzhou Huang, Sharon Xiaolei Huang, Dimitris N. Metaxas, Leon Axel

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

Abstract

The Metamorphs model is a robust segmentation method which integrates both shape and appearance in a unified space. The standard Metamorphs model does not encode temporal information. Thus it is not effective in segmenting time series data, such as a cardiac cycle from MRI. Furthermore, it needs manual interaction to initialize the model, which is time consuming for temporal data. In this paper, we proposed a model to seamlessly couple both spatial and temporal information together in the Metamorphs method. It is also able to automatically initialize the model instead of manual initialization. We model energy terms as probability maps, then different energy terms can be easily fused by multiplying them together. Temporal Spectral Residual (TSR) is employed to rapidly generate a probability map in temporal data. Compared to traditional Metamorphs, the computational overhead of our model is very light due to the efficiency of the TSR method and the ease of coupling different energy functions by using probability maps. We validate this algorithm in a task of segmenting the left ventricle endocardium from 2D MR sequences, and our method shows performance superior to the traditional Metamorphs.

Original languageEnglish (US)
Title of host publication2012 9th IEEE International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro, ISBI 2012 - Proceedings
Pages226-229
Number of pages4
DOIs
StatePublished - Aug 15 2012
Event2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Barcelona, Spain
Duration: May 2 2012May 5 2012

Publication series

NameProceedings - International Symposium on Biomedical Imaging
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012
CountrySpain
CityBarcelona
Period5/2/125/5/12

Fingerprint

Endocardium
Magnetic resonance imaging
Time series
Heart Ventricles
Light

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Cui, X., Zhang, S., Huang, J., Huang, S. X., Metaxas, D. N., & Axel, L. (2012). Left endocardium segmentation using spatio-temporal Metamorphs. In 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Proceedings (pp. 226-229). [6235525] (Proceedings - International Symposium on Biomedical Imaging). https://doi.org/10.1109/ISBI.2012.6235525
Cui, Xinyi ; Zhang, Shaoting ; Huang, Junzhou ; Huang, Sharon Xiaolei ; Metaxas, Dimitris N. ; Axel, Leon. / Left endocardium segmentation using spatio-temporal Metamorphs. 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Proceedings. 2012. pp. 226-229 (Proceedings - International Symposium on Biomedical Imaging).
@inproceedings{a2603458ce9c431cacf5ad424d572734,
title = "Left endocardium segmentation using spatio-temporal Metamorphs",
abstract = "The Metamorphs model is a robust segmentation method which integrates both shape and appearance in a unified space. The standard Metamorphs model does not encode temporal information. Thus it is not effective in segmenting time series data, such as a cardiac cycle from MRI. Furthermore, it needs manual interaction to initialize the model, which is time consuming for temporal data. In this paper, we proposed a model to seamlessly couple both spatial and temporal information together in the Metamorphs method. It is also able to automatically initialize the model instead of manual initialization. We model energy terms as probability maps, then different energy terms can be easily fused by multiplying them together. Temporal Spectral Residual (TSR) is employed to rapidly generate a probability map in temporal data. Compared to traditional Metamorphs, the computational overhead of our model is very light due to the efficiency of the TSR method and the ease of coupling different energy functions by using probability maps. We validate this algorithm in a task of segmenting the left ventricle endocardium from 2D MR sequences, and our method shows performance superior to the traditional Metamorphs.",
author = "Xinyi Cui and Shaoting Zhang and Junzhou Huang and Huang, {Sharon Xiaolei} and Metaxas, {Dimitris N.} and Leon Axel",
year = "2012",
month = "8",
day = "15",
doi = "10.1109/ISBI.2012.6235525",
language = "English (US)",
isbn = "9781457718588",
series = "Proceedings - International Symposium on Biomedical Imaging",
pages = "226--229",
booktitle = "2012 9th IEEE International Symposium on Biomedical Imaging",

}

Cui, X, Zhang, S, Huang, J, Huang, SX, Metaxas, DN & Axel, L 2012, Left endocardium segmentation using spatio-temporal Metamorphs. in 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Proceedings., 6235525, Proceedings - International Symposium on Biomedical Imaging, pp. 226-229, 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012, Barcelona, Spain, 5/2/12. https://doi.org/10.1109/ISBI.2012.6235525

Left endocardium segmentation using spatio-temporal Metamorphs. / Cui, Xinyi; Zhang, Shaoting; Huang, Junzhou; Huang, Sharon Xiaolei; Metaxas, Dimitris N.; Axel, Leon.

2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Proceedings. 2012. p. 226-229 6235525 (Proceedings - International Symposium on Biomedical Imaging).

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

TY - GEN

T1 - Left endocardium segmentation using spatio-temporal Metamorphs

AU - Cui, Xinyi

AU - Zhang, Shaoting

AU - Huang, Junzhou

AU - Huang, Sharon Xiaolei

AU - Metaxas, Dimitris N.

AU - Axel, Leon

PY - 2012/8/15

Y1 - 2012/8/15

N2 - The Metamorphs model is a robust segmentation method which integrates both shape and appearance in a unified space. The standard Metamorphs model does not encode temporal information. Thus it is not effective in segmenting time series data, such as a cardiac cycle from MRI. Furthermore, it needs manual interaction to initialize the model, which is time consuming for temporal data. In this paper, we proposed a model to seamlessly couple both spatial and temporal information together in the Metamorphs method. It is also able to automatically initialize the model instead of manual initialization. We model energy terms as probability maps, then different energy terms can be easily fused by multiplying them together. Temporal Spectral Residual (TSR) is employed to rapidly generate a probability map in temporal data. Compared to traditional Metamorphs, the computational overhead of our model is very light due to the efficiency of the TSR method and the ease of coupling different energy functions by using probability maps. We validate this algorithm in a task of segmenting the left ventricle endocardium from 2D MR sequences, and our method shows performance superior to the traditional Metamorphs.

AB - The Metamorphs model is a robust segmentation method which integrates both shape and appearance in a unified space. The standard Metamorphs model does not encode temporal information. Thus it is not effective in segmenting time series data, such as a cardiac cycle from MRI. Furthermore, it needs manual interaction to initialize the model, which is time consuming for temporal data. In this paper, we proposed a model to seamlessly couple both spatial and temporal information together in the Metamorphs method. It is also able to automatically initialize the model instead of manual initialization. We model energy terms as probability maps, then different energy terms can be easily fused by multiplying them together. Temporal Spectral Residual (TSR) is employed to rapidly generate a probability map in temporal data. Compared to traditional Metamorphs, the computational overhead of our model is very light due to the efficiency of the TSR method and the ease of coupling different energy functions by using probability maps. We validate this algorithm in a task of segmenting the left ventricle endocardium from 2D MR sequences, and our method shows performance superior to the traditional Metamorphs.

UR - http://www.scopus.com/inward/record.url?scp=84864854115&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864854115&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2012.6235525

DO - 10.1109/ISBI.2012.6235525

M3 - Conference contribution

SN - 9781457718588

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 226

EP - 229

BT - 2012 9th IEEE International Symposium on Biomedical Imaging

ER -

Cui X, Zhang S, Huang J, Huang SX, Metaxas DN, Axel L. Left endocardium segmentation using spatio-temporal Metamorphs. In 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Proceedings. 2012. p. 226-229. 6235525. (Proceedings - International Symposium on Biomedical Imaging). https://doi.org/10.1109/ISBI.2012.6235525