Feature learning with component selective encoding for histopathology image classification

Yang Song; Hang Chang; Yang Gao; Sidong Liu; Donghao Zhang; Junen Yao; Wojciech Chrzanowski; Weidong Cai

doi:10.1109/ISBI.2018.8363568

Feature learning with component selective encoding for histopathology image classification

Yang Song, Hang Chang, Yang Gao, Sidong Liu, Donghao Zhang, Junen Yao, Wojciech Chrzanowski, Weidong Cai

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

18 Citations (Scopus)

Abstract

In this paper, we present a new feature representation method, called the Component Selective Encoding (CSE), for automated histopathology image classification. While the integration of Fisher Vector (FV) encoding with convolutional neural network (CNN) has demonstrated excellent performance in the classification of both general texture and histopathology images, the high dimensionality of FV descriptors could lead to suboptimal performance. Our proposed CSE method provides effective dimensionality reduction that is adaptive to the discriminativeness of individual Gaussian components in the FV descriptors. Evaluation on the publicly available BreaKHis dataset shows that our method outperforms the existing approaches based on deep learning and FV encoding.

Original language	English
Title of host publication	Proceedings of 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
Editors	Erik Meijering, Ron Summers
Place of Publication	USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	257-260
Number of pages	4
Edition	1st
ISBN (Electronic)	9781538636367
DOIs	https://doi.org/10.1109/ISBI.2018.8363568
Publication status	Published - 2018
Externally published	Yes
Event	IEEE International Symposium on Biomedical Imaging (ISBI) 2018 - Washington, United States of America Duration: 4 Apr 2018 → 7 Apr 2018 Conference number: 15th https://ieeexplore.ieee.org/xpl/conhome/9433749/proceeding

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2018-April
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	IEEE International Symposium on Biomedical Imaging (ISBI) 2018
Abbreviated title	ISBI 2018
Country/Territory	United States of America
City	Washington
Period	4/04/18 → 7/04/18
Internet address	https://ieeexplore.ieee.org/xpl/conhome/9433749/proceeding

Keywords

Dimensionality reduction
Fisher Vector
Histopathology images
Transfer learning

Access to Document

10.1109/ISBI.2018.8363568

Cite this

Song, Y., Chang, H., Gao, Y., Liu, S., Zhang, D., Yao, J., Chrzanowski, W., & Cai, W. (2018). Feature learning with component selective encoding for histopathology image classification. In E. Meijering, & R. Summers (Eds.), Proceedings of 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018 (1st ed., pp. 257-260). (Proceedings - International Symposium on Biomedical Imaging; Vol. 2018-April). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISBI.2018.8363568

Song, Yang ; Chang, Hang ; Gao, Yang et al. / Feature learning with component selective encoding for histopathology image classification. Proceedings of 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. editor / Erik Meijering ; Ron Summers. 1st. ed. USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. pp. 257-260 (Proceedings - International Symposium on Biomedical Imaging).

@inproceedings{752cb86483454e84990cc1afc6591a57,

title = "Feature learning with component selective encoding for histopathology image classification",

abstract = "In this paper, we present a new feature representation method, called the Component Selective Encoding (CSE), for automated histopathology image classification. While the integration of Fisher Vector (FV) encoding with convolutional neural network (CNN) has demonstrated excellent performance in the classification of both general texture and histopathology images, the high dimensionality of FV descriptors could lead to suboptimal performance. Our proposed CSE method provides effective dimensionality reduction that is adaptive to the discriminativeness of individual Gaussian components in the FV descriptors. Evaluation on the publicly available BreaKHis dataset shows that our method outperforms the existing approaches based on deep learning and FV encoding.",

keywords = "Dimensionality reduction, Fisher Vector, Histopathology images, Transfer learning",

author = "Yang Song and Hang Chang and Yang Gao and Sidong Liu and Donghao Zhang and Junen Yao and Wojciech Chrzanowski and Weidong Cai",

note = "Funding Information: This work was supported in part by ARC grants. Publisher Copyright: {\textcopyright} 2018 IEEE.; IEEE International Symposium on Biomedical Imaging (ISBI) 2018, ISBI 2018 ; Conference date: 04-04-2018 Through 07-04-2018",

year = "2018",

doi = "10.1109/ISBI.2018.8363568",

language = "English",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

pages = "257--260",

editor = "Erik Meijering and Ron Summers",

booktitle = "Proceedings of 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018",

address = "United States of America",

edition = "1st",

url = "https://ieeexplore.ieee.org/xpl/conhome/9433749/proceeding",

}

Song, Y, Chang, H, Gao, Y, Liu, S, Zhang, D, Yao, J, Chrzanowski, W & Cai, W 2018, Feature learning with component selective encoding for histopathology image classification. in E Meijering & R Summers (eds), Proceedings of 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. 1st edn, Proceedings - International Symposium on Biomedical Imaging, vol. 2018-April, IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 257-260, IEEE International Symposium on Biomedical Imaging (ISBI) 2018, Washington, District of Columbia, United States of America, 4/04/18. https://doi.org/10.1109/ISBI.2018.8363568

Feature learning with component selective encoding for histopathology image classification. / Song, Yang; Chang, Hang; Gao, Yang et al.
Proceedings of 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. ed. / Erik Meijering; Ron Summers. 1st. ed. USA: IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 257-260 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2018-April).

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

TY - GEN

T1 - Feature learning with component selective encoding for histopathology image classification

AU - Song, Yang

AU - Chang, Hang

AU - Gao, Yang

AU - Liu, Sidong

AU - Zhang, Donghao

AU - Yao, Junen

AU - Chrzanowski, Wojciech

AU - Cai, Weidong

N1 - Conference code: 15th

PY - 2018

Y1 - 2018

N2 - In this paper, we present a new feature representation method, called the Component Selective Encoding (CSE), for automated histopathology image classification. While the integration of Fisher Vector (FV) encoding with convolutional neural network (CNN) has demonstrated excellent performance in the classification of both general texture and histopathology images, the high dimensionality of FV descriptors could lead to suboptimal performance. Our proposed CSE method provides effective dimensionality reduction that is adaptive to the discriminativeness of individual Gaussian components in the FV descriptors. Evaluation on the publicly available BreaKHis dataset shows that our method outperforms the existing approaches based on deep learning and FV encoding.

AB - In this paper, we present a new feature representation method, called the Component Selective Encoding (CSE), for automated histopathology image classification. While the integration of Fisher Vector (FV) encoding with convolutional neural network (CNN) has demonstrated excellent performance in the classification of both general texture and histopathology images, the high dimensionality of FV descriptors could lead to suboptimal performance. Our proposed CSE method provides effective dimensionality reduction that is adaptive to the discriminativeness of individual Gaussian components in the FV descriptors. Evaluation on the publicly available BreaKHis dataset shows that our method outperforms the existing approaches based on deep learning and FV encoding.

KW - Dimensionality reduction

KW - Fisher Vector

KW - Histopathology images

KW - Transfer learning

UR - http://www.scopus.com/inward/record.url?scp=85048073208&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2018.8363568

DO - 10.1109/ISBI.2018.8363568

M3 - Conference Paper

AN - SCOPUS:85048073208

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 257

EP - 260

BT - Proceedings of 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018

A2 - Meijering, Erik

A2 - Summers, Ron

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - USA

T2 - IEEE International Symposium on Biomedical Imaging (ISBI) 2018

Y2 - 4 April 2018 through 7 April 2018

ER -

Song Y, Chang H, Gao Y, Liu S, Zhang D, Yao J et al. Feature learning with component selective encoding for histopathology image classification. In Meijering E, Summers R, editors, Proceedings of 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. 1st ed. USA: IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 257-260. (Proceedings - International Symposium on Biomedical Imaging). doi: 10.1109/ISBI.2018.8363568

Feature learning with component selective encoding for histopathology image classification

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this