Hybrid classifiers ensemble with an undersampling scheme for liver tumor segmentation

Wanzheng Zhu; Beom Seok Oh; Weimin Huang; Zhiping Lin; Yuehao Pan; Jiayin Zhou

doi:10.1109/ICICS.2015.7459850

Hybrid classifiers ensemble with an undersampling scheme for liver tumor segmentation

Wanzheng Zhu, Beom Seok Oh, Weimin Huang, Zhiping Lin, Yuehao Pan, Jiayin Zhou

Dept. of Applied Artificial Intelligence

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

4 Scopus citations

Abstract

In this paper, we propose a new framework, namely hybrid classifiers ensemble with random undersampling for liver tumor segmentation. Essentially, the proposed framework is working on computed tomography images in which each pixel is represented by a rich feature vector. To handle the class imbalance problem, those pixels which correspond to non-tumor region are randomly subsampled. Outcomes of three types of classifiers are then combined in a decision level for performance enhancement. Our empirical results on 19 tumor images from 11 patients show promising segmentation performance.

Original language	English
Title of host publication	2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781467372183
DOIs	https://doi.org/10.1109/ICICS.2015.7459850
State	Published - 26 Apr 2016
Event	10th International Conference on Information, Communications and Signal Processing, ICICS 2015 - Singapore, Singapore Duration: 2 Dec 2015 → 4 Dec 2015

Publication series

Name	2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015

Conference

Conference	10th International Conference on Information, Communications and Signal Processing, ICICS 2015
Country/Territory	Singapore
City	Singapore
Period	2/12/15 → 4/12/15

Access to Document

10.1109/ICICS.2015.7459850

Cite this

Zhu, W., Oh, B. S., Huang, W., Lin, Z., Pan, Y., & Zhou, J. (2016). Hybrid classifiers ensemble with an undersampling scheme for liver tumor segmentation. In 2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015 Article 7459850 (2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICICS.2015.7459850

Zhu, Wanzheng ; Oh, Beom Seok ; Huang, Weimin et al. / Hybrid classifiers ensemble with an undersampling scheme for liver tumor segmentation. 2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015. Institute of Electrical and Electronics Engineers Inc., 2016. (2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015).

@inproceedings{7346118f52c54bf4acb090adab063be8,

title = "Hybrid classifiers ensemble with an undersampling scheme for liver tumor segmentation",

abstract = "In this paper, we propose a new framework, namely hybrid classifiers ensemble with random undersampling for liver tumor segmentation. Essentially, the proposed framework is working on computed tomography images in which each pixel is represented by a rich feature vector. To handle the class imbalance problem, those pixels which correspond to non-tumor region are randomly subsampled. Outcomes of three types of classifiers are then combined in a decision level for performance enhancement. Our empirical results on 19 tumor images from 11 patients show promising segmentation performance.",

author = "Wanzheng Zhu and Oh, \{Beom Seok\} and Weimin Huang and Zhiping Lin and Yuehao Pan and Jiayin Zhou",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 10th International Conference on Information, Communications and Signal Processing, ICICS 2015 ; Conference date: 02-12-2015 Through 04-12-2015",

year = "2016",

month = apr,

day = "26",

doi = "10.1109/ICICS.2015.7459850",

language = "English",

series = "2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015",

}

Zhu, W, Oh, BS, Huang, W, Lin, Z, Pan, Y & Zhou, J 2016, Hybrid classifiers ensemble with an undersampling scheme for liver tumor segmentation. in 2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015., 7459850, 2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015, Institute of Electrical and Electronics Engineers Inc., 10th International Conference on Information, Communications and Signal Processing, ICICS 2015, Singapore, Singapore, 2/12/15. https://doi.org/10.1109/ICICS.2015.7459850

Hybrid classifiers ensemble with an undersampling scheme for liver tumor segmentation. / Zhu, Wanzheng; Oh, Beom Seok; Huang, Weimin et al.
2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015. Institute of Electrical and Electronics Engineers Inc., 2016. 7459850 (2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015).

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

TY - GEN

T1 - Hybrid classifiers ensemble with an undersampling scheme for liver tumor segmentation

AU - Zhu, Wanzheng

AU - Oh, Beom Seok

AU - Huang, Weimin

AU - Lin, Zhiping

AU - Pan, Yuehao

AU - Zhou, Jiayin

PY - 2016/4/26

Y1 - 2016/4/26

N2 - In this paper, we propose a new framework, namely hybrid classifiers ensemble with random undersampling for liver tumor segmentation. Essentially, the proposed framework is working on computed tomography images in which each pixel is represented by a rich feature vector. To handle the class imbalance problem, those pixels which correspond to non-tumor region are randomly subsampled. Outcomes of three types of classifiers are then combined in a decision level for performance enhancement. Our empirical results on 19 tumor images from 11 patients show promising segmentation performance.

AB - In this paper, we propose a new framework, namely hybrid classifiers ensemble with random undersampling for liver tumor segmentation. Essentially, the proposed framework is working on computed tomography images in which each pixel is represented by a rich feature vector. To handle the class imbalance problem, those pixels which correspond to non-tumor region are randomly subsampled. Outcomes of three types of classifiers are then combined in a decision level for performance enhancement. Our empirical results on 19 tumor images from 11 patients show promising segmentation performance.

UR - https://www.scopus.com/pages/publications/84973650046

U2 - 10.1109/ICICS.2015.7459850

DO - 10.1109/ICICS.2015.7459850

M3 - Conference contribution

AN - SCOPUS:84973650046

T3 - 2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015

BT - 2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 10th International Conference on Information, Communications and Signal Processing, ICICS 2015

Y2 - 2 December 2015 through 4 December 2015

ER -

Zhu W, Oh BS, Huang W, Lin Z, Pan Y, Zhou J. Hybrid classifiers ensemble with an undersampling scheme for liver tumor segmentation. In 2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015. Institute of Electrical and Electronics Engineers Inc. 2016. 7459850. (2015 10th International Conference on Information, Communications and Signal Processing, ICICS 2015). doi: 10.1109/ICICS.2015.7459850

Hybrid classifiers ensemble with an undersampling scheme for liver tumor segmentation

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this