Pathology image retrieval by block LBP based pLSA model with low-rank and sparse matrix decomposition

Yushan Zheng; Zhiguo Jiang; Jun Shi; Yibing Ma

doi:10.1007/978-3-662-45498-5_36

Pathology image retrieval by block LBP based pLSA model with low-rank and sparse matrix decomposition

Yushan Zheng^*
, Zhiguo Jiang
, Jun Shi
, Yibing Ma

^*Corresponding author for this work

Beihang University

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

6 Scopus citations

Abstract

Content-based image retrieval (CBIR) is widely used in Computer Aided Diagnosis (CAD) systems which can aid pathologist to make reasonable decision by querying the slides with diagnostic information from the digital pathology slide database. In this paper, we propose a novel pathology image retrieval method for breast cancer. It firstly applies block Local Binary Pattern (LBP) features to describe the spatial texture property of pathology image, and then use them to construct the probabilistic latent semantic analysis (pLSA) model which generally takes advantage of visual words to mine the topic-level representation of image and thus reveals the high-level semantics. Different from conventional pLSA model, we employ low-rank and sparse matrix composition for describing the correlated and specific characteristics of visual words. Therefore, the more discriminative topic-level representation corresponding to each pathology image can be obtained. Experimental results on the digital pathology image database for breast cancer demonstrate the feasibility and effectiveness of our method.

Original language	English
Title of host publication	Advances in Image and Graphics Technologies - Chinese Conference, IGTA 2014, Proceedings
Editors	Tieniu Tan, Qiuqi Ruan, Shengjin Wang, Huimin Ma, Kaiqi Huang
Publisher	Springer Verlag
Pages	327-335
Number of pages	9
ISBN (Electronic)	9783662454978
DOIs	https://doi.org/10.1007/978-3-662-45498-5_36
State	Published - 2014
Event	8th Conference on Image and Graphics Technologies and Applications, IGTA 2014 - Beijing, China Duration: 19 Jun 2014 → 20 Jun 2014

Publication series

Name	Communications in Computer and Information Science
Volume	437
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	8th Conference on Image and Graphics Technologies and Applications, IGTA 2014
Country/Territory	China
City	Beijing
Period	19/06/14 → 20/06/14

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Breast cancer
Computer aided diagnosis
Image retrieval
Low-rank and sparse matrix composition
Probabilistic latent semantic analysis

Access to Document

10.1007/978-3-662-45498-5_36

Cite this

Zheng, Y., Jiang, Z., Shi, J., & Ma, Y. (2014). Pathology image retrieval by block LBP based pLSA model with low-rank and sparse matrix decomposition. In T. Tan, Q. Ruan, S. Wang, H. Ma, & K. Huang (Eds.), Advances in Image and Graphics Technologies - Chinese Conference, IGTA 2014, Proceedings (pp. 327-335). (Communications in Computer and Information Science; Vol. 437). Springer Verlag. https://doi.org/10.1007/978-3-662-45498-5_36

Zheng, Yushan ; Jiang, Zhiguo ; Shi, Jun et al. / Pathology image retrieval by block LBP based pLSA model with low-rank and sparse matrix decomposition. Advances in Image and Graphics Technologies - Chinese Conference, IGTA 2014, Proceedings. editor / Tieniu Tan ; Qiuqi Ruan ; Shengjin Wang ; Huimin Ma ; Kaiqi Huang. Springer Verlag, 2014. pp. 327-335 (Communications in Computer and Information Science).

@inproceedings{094547da0ab54d9991d25801b378f4e4,

title = "Pathology image retrieval by block LBP based pLSA model with low-rank and sparse matrix decomposition",

abstract = "Content-based image retrieval (CBIR) is widely used in Computer Aided Diagnosis (CAD) systems which can aid pathologist to make reasonable decision by querying the slides with diagnostic information from the digital pathology slide database. In this paper, we propose a novel pathology image retrieval method for breast cancer. It firstly applies block Local Binary Pattern (LBP) features to describe the spatial texture property of pathology image, and then use them to construct the probabilistic latent semantic analysis (pLSA) model which generally takes advantage of visual words to mine the topic-level representation of image and thus reveals the high-level semantics. Different from conventional pLSA model, we employ low-rank and sparse matrix composition for describing the correlated and specific characteristics of visual words. Therefore, the more discriminative topic-level representation corresponding to each pathology image can be obtained. Experimental results on the digital pathology image database for breast cancer demonstrate the feasibility and effectiveness of our method.",

keywords = "Breast cancer, Computer aided diagnosis, Image retrieval, Low-rank and sparse matrix composition, Probabilistic latent semantic analysis",

author = "Yushan Zheng and Zhiguo Jiang and Jun Shi and Yibing Ma",

note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2014.; 8th Conference on Image and Graphics Technologies and Applications, IGTA 2014 ; Conference date: 19-06-2014 Through 20-06-2014",

year = "2014",

doi = "10.1007/978-3-662-45498-5\_36",

language = "英语",

series = "Communications in Computer and Information Science",

publisher = "Springer Verlag",

pages = "327--335",

editor = "Tieniu Tan and Qiuqi Ruan and Shengjin Wang and Huimin Ma and Kaiqi Huang",

booktitle = "Advances in Image and Graphics Technologies - Chinese Conference, IGTA 2014, Proceedings",

address = "德国",

}

Zheng, Y , Jiang, Z, Shi, J & Ma, Y 2014, Pathology image retrieval by block LBP based pLSA model with low-rank and sparse matrix decomposition. in T Tan, Q Ruan, S Wang, H Ma & K Huang (eds), Advances in Image and Graphics Technologies - Chinese Conference, IGTA 2014, Proceedings. Communications in Computer and Information Science, vol. 437, Springer Verlag, pp. 327-335, 8th Conference on Image and Graphics Technologies and Applications, IGTA 2014, Beijing, China, 19/06/14. https://doi.org/10.1007/978-3-662-45498-5_36

Pathology image retrieval by block LBP based pLSA model with low-rank and sparse matrix decomposition. / Zheng, Yushan ; Jiang, Zhiguo; Shi, Jun et al.
Advances in Image and Graphics Technologies - Chinese Conference, IGTA 2014, Proceedings. ed. / Tieniu Tan; Qiuqi Ruan; Shengjin Wang; Huimin Ma; Kaiqi Huang. Springer Verlag, 2014. p. 327-335 (Communications in Computer and Information Science; Vol. 437).

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

TY - GEN

T1 - Pathology image retrieval by block LBP based pLSA model with low-rank and sparse matrix decomposition

AU - Zheng, Yushan

AU - Jiang, Zhiguo

AU - Shi, Jun

AU - Ma, Yibing

N1 - Publisher Copyright: © Springer-Verlag Berlin Heidelberg 2014.

PY - 2014

Y1 - 2014

N2 - Content-based image retrieval (CBIR) is widely used in Computer Aided Diagnosis (CAD) systems which can aid pathologist to make reasonable decision by querying the slides with diagnostic information from the digital pathology slide database. In this paper, we propose a novel pathology image retrieval method for breast cancer. It firstly applies block Local Binary Pattern (LBP) features to describe the spatial texture property of pathology image, and then use them to construct the probabilistic latent semantic analysis (pLSA) model which generally takes advantage of visual words to mine the topic-level representation of image and thus reveals the high-level semantics. Different from conventional pLSA model, we employ low-rank and sparse matrix composition for describing the correlated and specific characteristics of visual words. Therefore, the more discriminative topic-level representation corresponding to each pathology image can be obtained. Experimental results on the digital pathology image database for breast cancer demonstrate the feasibility and effectiveness of our method.

AB - Content-based image retrieval (CBIR) is widely used in Computer Aided Diagnosis (CAD) systems which can aid pathologist to make reasonable decision by querying the slides with diagnostic information from the digital pathology slide database. In this paper, we propose a novel pathology image retrieval method for breast cancer. It firstly applies block Local Binary Pattern (LBP) features to describe the spatial texture property of pathology image, and then use them to construct the probabilistic latent semantic analysis (pLSA) model which generally takes advantage of visual words to mine the topic-level representation of image and thus reveals the high-level semantics. Different from conventional pLSA model, we employ low-rank and sparse matrix composition for describing the correlated and specific characteristics of visual words. Therefore, the more discriminative topic-level representation corresponding to each pathology image can be obtained. Experimental results on the digital pathology image database for breast cancer demonstrate the feasibility and effectiveness of our method.

KW - Breast cancer

KW - Computer aided diagnosis

KW - Image retrieval

KW - Low-rank and sparse matrix composition

KW - Probabilistic latent semantic analysis

UR - https://www.scopus.com/pages/publications/84908642309

U2 - 10.1007/978-3-662-45498-5_36

DO - 10.1007/978-3-662-45498-5_36

M3 - 会议稿件

AN - SCOPUS:84908642309

T3 - Communications in Computer and Information Science

SP - 327

EP - 335

BT - Advances in Image and Graphics Technologies - Chinese Conference, IGTA 2014, Proceedings

A2 - Tan, Tieniu

A2 - Ruan, Qiuqi

A2 - Wang, Shengjin

A2 - Ma, Huimin

A2 - Huang, Kaiqi

PB - Springer Verlag

T2 - 8th Conference on Image and Graphics Technologies and Applications, IGTA 2014

Y2 - 19 June 2014 through 20 June 2014

ER -

Zheng Y , Jiang Z, Shi J, Ma Y. Pathology image retrieval by block LBP based pLSA model with low-rank and sparse matrix decomposition. In Tan T, Ruan Q, Wang S, Ma H, Huang K, editors, Advances in Image and Graphics Technologies - Chinese Conference, IGTA 2014, Proceedings. Springer Verlag. 2014. p. 327-335. (Communications in Computer and Information Science). doi: 10.1007/978-3-662-45498-5_36

Pathology image retrieval by block LBP based pLSA model with low-rank and sparse matrix decomposition

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this