Cell dynamic morphology analysis by deep convolutional features

Heng Li; Zhiwen Liu; Fengqian Pang; Yonggang Shi

doi:10.1109/EMBC.2017.8037414

Cell dynamic morphology analysis by deep convolutional features

Heng Li, Zhiwen Liu, Fengqian Pang, Yonggang Shi

Beijing Institute of Technology

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

Abstract

Computational analysis of cell dynamic morphology in time-lapse image is a challenging task in biomedical research. Inspired by the recent success of deep learning, we investigate the possibility to apply a deep neural network to cell dynamic morphology analysis in this paper. Specifically, a contour spectrum is composed as the input of neural network to characterize cell spatiotemporal deformation, then a pre-trained convolutional neural network model is performed for automatic feature extraction. Finally, the extracted deep convolutional features are analyzed by SVM. Experimental results demonstrate that the proposed strategy outperforms existing methods on the live-cell database, and the features extracted by the last layer and classified by linear kernel SVM allows for the state-of-the-art performance.

Original language	English
Title of host publication	2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Subtitle of host publication	Smarter Technology for a Healthier World, EMBC 2017 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2700-2703
Number of pages	4
ISBN (Electronic)	9781509028092
DOIs	https://doi.org/10.1109/EMBC.2017.8037414
Publication status	Published - 13 Sept 2017
Event	39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017 - Jeju Island, Korea, Republic of Duration: 11 Jul 2017 → 15 Jul 2017

Publication series

Name	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)	1557-170X

Conference

Conference	39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017
Country/Territory	Korea, Republic of
City	Jeju Island
Period	11/07/17 → 15/07/17

Keywords

Cell dynamic morphology
Deep convolutional features
Deep learning
Spatiotemporal deformation

Access to Document

10.1109/EMBC.2017.8037414

Cite this

Li, H., Liu, Z., Pang, F., & Shi, Y. (2017). Cell dynamic morphology analysis by deep convolutional features. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings (pp. 2700-2703). Article 8037414 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2017.8037414

Li, Heng ; Liu, Zhiwen ; Pang, Fengqian et al. / Cell dynamic morphology analysis by deep convolutional features. 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 2700-2703 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

@inproceedings{03ca69799f5840908c9045d378d9418b,

title = "Cell dynamic morphology analysis by deep convolutional features",

abstract = "Computational analysis of cell dynamic morphology in time-lapse image is a challenging task in biomedical research. Inspired by the recent success of deep learning, we investigate the possibility to apply a deep neural network to cell dynamic morphology analysis in this paper. Specifically, a contour spectrum is composed as the input of neural network to characterize cell spatiotemporal deformation, then a pre-trained convolutional neural network model is performed for automatic feature extraction. Finally, the extracted deep convolutional features are analyzed by SVM. Experimental results demonstrate that the proposed strategy outperforms existing methods on the live-cell database, and the features extracted by the last layer and classified by linear kernel SVM allows for the state-of-the-art performance.",

keywords = "Cell dynamic morphology, Deep convolutional features, Deep learning, Spatiotemporal deformation",

author = "Heng Li and Zhiwen Liu and Fengqian Pang and Yonggang Shi",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017 ; Conference date: 11-07-2017 Through 15-07-2017",

year = "2017",

month = sep,

day = "13",

doi = "10.1109/EMBC.2017.8037414",

language = "English",

series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

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

pages = "2700--2703",

booktitle = "2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society",

address = "United States",

}

Li, H, Liu, Z, Pang, F & Shi, Y 2017, Cell dynamic morphology analysis by deep convolutional features. in 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings., 8037414, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, Institute of Electrical and Electronics Engineers Inc., pp. 2700-2703, 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017, Jeju Island, Korea, Republic of, 11/07/17. https://doi.org/10.1109/EMBC.2017.8037414

Cell dynamic morphology analysis by deep convolutional features. / Li, Heng; Liu, Zhiwen; Pang, Fengqian et al.
2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 2700-2703 8037414 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

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

TY - GEN

T1 - Cell dynamic morphology analysis by deep convolutional features

AU - Li, Heng

AU - Liu, Zhiwen

AU - Pang, Fengqian

AU - Shi, Yonggang

PY - 2017/9/13

Y1 - 2017/9/13

N2 - Computational analysis of cell dynamic morphology in time-lapse image is a challenging task in biomedical research. Inspired by the recent success of deep learning, we investigate the possibility to apply a deep neural network to cell dynamic morphology analysis in this paper. Specifically, a contour spectrum is composed as the input of neural network to characterize cell spatiotemporal deformation, then a pre-trained convolutional neural network model is performed for automatic feature extraction. Finally, the extracted deep convolutional features are analyzed by SVM. Experimental results demonstrate that the proposed strategy outperforms existing methods on the live-cell database, and the features extracted by the last layer and classified by linear kernel SVM allows for the state-of-the-art performance.

AB - Computational analysis of cell dynamic morphology in time-lapse image is a challenging task in biomedical research. Inspired by the recent success of deep learning, we investigate the possibility to apply a deep neural network to cell dynamic morphology analysis in this paper. Specifically, a contour spectrum is composed as the input of neural network to characterize cell spatiotemporal deformation, then a pre-trained convolutional neural network model is performed for automatic feature extraction. Finally, the extracted deep convolutional features are analyzed by SVM. Experimental results demonstrate that the proposed strategy outperforms existing methods on the live-cell database, and the features extracted by the last layer and classified by linear kernel SVM allows for the state-of-the-art performance.

KW - Cell dynamic morphology

KW - Deep convolutional features

KW - Deep learning

KW - Spatiotemporal deformation

UR - http://www.scopus.com/inward/record.url?scp=85032213176&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2017.8037414

DO - 10.1109/EMBC.2017.8037414

M3 - Conference contribution

C2 - 29060456

AN - SCOPUS:85032213176

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 2700

EP - 2703

BT - 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017

Y2 - 11 July 2017 through 15 July 2017

ER -

Li H, Liu Z, Pang F, Shi Y. Cell dynamic morphology analysis by deep convolutional features. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 2700-2703. 8037414. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). doi: 10.1109/EMBC.2017.8037414

Cell dynamic morphology analysis by deep convolutional features

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this