IEICE TRANSACTIONS on Information
Sparse and Low-Rank Matrix Decomposition for Local Morphological Analysis to Diagnose Cirrhosis
Summary :
Chronic liver disease is a major worldwide health problem. Diagnosis and staging of chronic liver diseases is an important issue. In this paper, we propose a quantitative method of analyzing local morphological changes for accurate and practical computer-aided diagnosis of cirrhosis. Our method is based on sparse and low-rank matrix decomposition, since the matrix of the liver shapes can be decomposed into two parts: a low-rank matrix, which can be considered similar to that of a normal liver, and a sparse error term that represents the local deformation. Compared with the previous global morphological analysis strategy based on the statistical shape model (SSM), our proposed method improves the accuracy of both normal and abnormal classifications. We also propose using the norm of the sparse error term as a simple measure for classification as normal or abnormal. The experimental results of the proposed method are better than those of the state-of-the-art SSM-based methods.
- Publication
- IEICE TRANSACTIONS on Information Vol.E97-D No.12 pp.3210-3221
- Publication Date
- 2014/12/01
- Publicized
- 2014/08/26
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2014EDP7180
- Type of Manuscript
- PAPER
- Category
- Biological Engineering
Authors
Junping DENG
Ritsumeikan University
Xian-Hua HAN
Ritsumeikan University
Yen-Wei CHEN
Ritsumeikan University,Osaka University
Gang XU
Ritsumeikan University
Yoshinobu SATO
Nara Institute of Science and Technology (NAIST)
Masatoshi HORI
Osaka University
Noriyuki TOMIYAMA
Osaka University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Junping DENG, Xian-Hua HAN, Yen-Wei CHEN, Gang XU, Yoshinobu SATO, Masatoshi HORI, Noriyuki TOMIYAMA, "Sparse and Low-Rank Matrix Decomposition for Local Morphological Analysis to Diagnose Cirrhosis" in IEICE TRANSACTIONS on Information,
vol. E97-D, no. 12, pp. 3210-3221, December 2014, doi: 10.1587/transinf.2014EDP7180.
Abstract: Chronic liver disease is a major worldwide health problem. Diagnosis and staging of chronic liver diseases is an important issue. In this paper, we propose a quantitative method of analyzing local morphological changes for accurate and practical computer-aided diagnosis of cirrhosis. Our method is based on sparse and low-rank matrix decomposition, since the matrix of the liver shapes can be decomposed into two parts: a low-rank matrix, which can be considered similar to that of a normal liver, and a sparse error term that represents the local deformation. Compared with the previous global morphological analysis strategy based on the statistical shape model (SSM), our proposed method improves the accuracy of both normal and abnormal classifications. We also propose using the norm of the sparse error term as a simple measure for classification as normal or abnormal. The experimental results of the proposed method are better than those of the state-of-the-art SSM-based methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2014EDP7180/_p
Copy
@ARTICLE{e97-d_12_3210,
author={Junping DENG, Xian-Hua HAN, Yen-Wei CHEN, Gang XU, Yoshinobu SATO, Masatoshi HORI, Noriyuki TOMIYAMA, },
journal={IEICE TRANSACTIONS on Information},
title={Sparse and Low-Rank Matrix Decomposition for Local Morphological Analysis to Diagnose Cirrhosis},
year={2014},
volume={E97-D},
number={12},
pages={3210-3221},
abstract={Chronic liver disease is a major worldwide health problem. Diagnosis and staging of chronic liver diseases is an important issue. In this paper, we propose a quantitative method of analyzing local morphological changes for accurate and practical computer-aided diagnosis of cirrhosis. Our method is based on sparse and low-rank matrix decomposition, since the matrix of the liver shapes can be decomposed into two parts: a low-rank matrix, which can be considered similar to that of a normal liver, and a sparse error term that represents the local deformation. Compared with the previous global morphological analysis strategy based on the statistical shape model (SSM), our proposed method improves the accuracy of both normal and abnormal classifications. We also propose using the norm of the sparse error term as a simple measure for classification as normal or abnormal. The experimental results of the proposed method are better than those of the state-of-the-art SSM-based methods.},
keywords={},
doi={10.1587/transinf.2014EDP7180},
ISSN={1745-1361},
month={December},}
Copy
TY - JOUR
TI - Sparse and Low-Rank Matrix Decomposition for Local Morphological Analysis to Diagnose Cirrhosis
T2 - IEICE TRANSACTIONS on Information
SP - 3210
EP - 3221
AU - Junping DENG
AU - Xian-Hua HAN
AU - Yen-Wei CHEN
AU - Gang XU
AU - Yoshinobu SATO
AU - Masatoshi HORI
AU - Noriyuki TOMIYAMA
PY - 2014
DO - 10.1587/transinf.2014EDP7180
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2014
AB - Chronic liver disease is a major worldwide health problem. Diagnosis and staging of chronic liver diseases is an important issue. In this paper, we propose a quantitative method of analyzing local morphological changes for accurate and practical computer-aided diagnosis of cirrhosis. Our method is based on sparse and low-rank matrix decomposition, since the matrix of the liver shapes can be decomposed into two parts: a low-rank matrix, which can be considered similar to that of a normal liver, and a sparse error term that represents the local deformation. Compared with the previous global morphological analysis strategy based on the statistical shape model (SSM), our proposed method improves the accuracy of both normal and abnormal classifications. We also propose using the norm of the sparse error term as a simple measure for classification as normal or abnormal. The experimental results of the proposed method are better than those of the state-of-the-art SSM-based methods.
ER -
English
