Classification of cervical-cancer using pap-smear images: A convolutional neural network approach

Bilal Taha; Jorge Dias; Naoufel Werghi

doi:10.1007/978-3-319-60964-5_23

Classification of cervical-cancer using pap-smear images: A convolutional neural network approach

Bilal Taha
, Jorge Dias
, Naoufel Werghi

Electrical Engineering

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

84 Scopus citations

Abstract

Cervical cancer is the second most common and the fifth deadliest cancer in women. In this paper, we propose a deep learning approach for detecting cervix cancer from pap-smear images. Rather than designing and training a convolutional neural network (CNN) from the scratch, we show that we can employ a pre-trained CNN architecture as a feature extractor and use the output features as input to train a Support Vector Machine Classifier. We demonstrate the efficacy of such a new employment on the Herlev public database for single cell papsmear, whereby the experimental results show that our proposed system neatly outperforms other state of the art methods.

Original language	British English
Title of host publication	Medical Image Understanding and Analysis - 21st Annual Conference, MIUA 2017, Proceedings
Editors	Victor Gonzalez-Castro, Maria Valdes Hernandez
Publisher	Springer Verlag
Pages	261-272
Number of pages	12
ISBN (Print)	9783319609638
DOIs	https://doi.org/10.1007/978-3-319-60964-5_23
State	Published - 2017
Event	21st Annual Conference on Medical Image Understanding and Analysis, MIUA 2017 - Edinburgh, United Kingdom Duration: 11 Jul 2017 → 13 Jul 2017

Publication series

Name	Communications in Computer and Information Science
Volume	723
ISSN (Print)	1865-0929

Conference

Conference	21st Annual Conference on Medical Image Understanding and Analysis, MIUA 2017
Country/Territory	United Kingdom
City	Edinburgh
Period	11/07/17 → 13/07/17

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Convolutional neural network
Deep learning
Pap-smear classification

Access to Document

10.1007/978-3-319-60964-5_23

OpenUrl availability

Full text

Cite this

Taha, B., Dias, J., & Werghi, N. (2017). Classification of cervical-cancer using pap-smear images: A convolutional neural network approach. In V. Gonzalez-Castro, & M. Valdes Hernandez (Eds.), Medical Image Understanding and Analysis - 21st Annual Conference, MIUA 2017, Proceedings (pp. 261-272). (Communications in Computer and Information Science; Vol. 723). Springer Verlag. https://doi.org/10.1007/978-3-319-60964-5_23

Taha, Bilal ; Dias, Jorge ; Werghi, Naoufel. / Classification of cervical-cancer using pap-smear images : A convolutional neural network approach. Medical Image Understanding and Analysis - 21st Annual Conference, MIUA 2017, Proceedings. editor / Victor Gonzalez-Castro ; Maria Valdes Hernandez. Springer Verlag, 2017. pp. 261-272 (Communications in Computer and Information Science).

@inproceedings{0154e2fbf9b64f788324282c11df9e31,

title = "Classification of cervical-cancer using pap-smear images: A convolutional neural network approach",

abstract = "Cervical cancer is the second most common and the fifth deadliest cancer in women. In this paper, we propose a deep learning approach for detecting cervix cancer from pap-smear images. Rather than designing and training a convolutional neural network (CNN) from the scratch, we show that we can employ a pre-trained CNN architecture as a feature extractor and use the output features as input to train a Support Vector Machine Classifier. We demonstrate the efficacy of such a new employment on the Herlev public database for single cell papsmear, whereby the experimental results show that our proposed system neatly outperforms other state of the art methods.",

keywords = "Convolutional neural network, Deep learning, Pap-smear classification",

author = "Bilal Taha and Jorge Dias and Naoufel Werghi",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG 2017.; 21st Annual Conference on Medical Image Understanding and Analysis, MIUA 2017 ; Conference date: 11-07-2017 Through 13-07-2017",

year = "2017",

doi = "10.1007/978-3-319-60964-5\_23",

language = "British English",

isbn = "9783319609638",

series = "Communications in Computer and Information Science",

publisher = "Springer Verlag",

pages = "261--272",

editor = "Victor Gonzalez-Castro and \{Valdes Hernandez\}, Maria",

booktitle = "Medical Image Understanding and Analysis - 21st Annual Conference, MIUA 2017, Proceedings",

address = "Germany",

}

Taha, B, Dias, J & Werghi, N 2017, Classification of cervical-cancer using pap-smear images: A convolutional neural network approach. in V Gonzalez-Castro & M Valdes Hernandez (eds), Medical Image Understanding and Analysis - 21st Annual Conference, MIUA 2017, Proceedings. Communications in Computer and Information Science, vol. 723, Springer Verlag, pp. 261-272, 21st Annual Conference on Medical Image Understanding and Analysis, MIUA 2017, Edinburgh, United Kingdom, 11/07/17. https://doi.org/10.1007/978-3-319-60964-5_23

Classification of cervical-cancer using pap-smear images: A convolutional neural network approach. / Taha, Bilal; Dias, Jorge ; Werghi, Naoufel.
Medical Image Understanding and Analysis - 21st Annual Conference, MIUA 2017, Proceedings. ed. / Victor Gonzalez-Castro; Maria Valdes Hernandez. Springer Verlag, 2017. p. 261-272 (Communications in Computer and Information Science; Vol. 723).

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

TY - GEN

T1 - Classification of cervical-cancer using pap-smear images

T2 - 21st Annual Conference on Medical Image Understanding and Analysis, MIUA 2017

AU - Taha, Bilal

AU - Dias, Jorge

AU - Werghi, Naoufel

PY - 2017

Y1 - 2017

N2 - Cervical cancer is the second most common and the fifth deadliest cancer in women. In this paper, we propose a deep learning approach for detecting cervix cancer from pap-smear images. Rather than designing and training a convolutional neural network (CNN) from the scratch, we show that we can employ a pre-trained CNN architecture as a feature extractor and use the output features as input to train a Support Vector Machine Classifier. We demonstrate the efficacy of such a new employment on the Herlev public database for single cell papsmear, whereby the experimental results show that our proposed system neatly outperforms other state of the art methods.

AB - Cervical cancer is the second most common and the fifth deadliest cancer in women. In this paper, we propose a deep learning approach for detecting cervix cancer from pap-smear images. Rather than designing and training a convolutional neural network (CNN) from the scratch, we show that we can employ a pre-trained CNN architecture as a feature extractor and use the output features as input to train a Support Vector Machine Classifier. We demonstrate the efficacy of such a new employment on the Herlev public database for single cell papsmear, whereby the experimental results show that our proposed system neatly outperforms other state of the art methods.

KW - Convolutional neural network

KW - Deep learning

KW - Pap-smear classification

UR - https://www.scopus.com/pages/publications/85022201753

U2 - 10.1007/978-3-319-60964-5_23

DO - 10.1007/978-3-319-60964-5_23

M3 - Conference contribution

AN - SCOPUS:85022201753

SN - 9783319609638

T3 - Communications in Computer and Information Science

SP - 261

EP - 272

BT - Medical Image Understanding and Analysis - 21st Annual Conference, MIUA 2017, Proceedings

A2 - Gonzalez-Castro, Victor

A2 - Valdes Hernandez, Maria

PB - Springer Verlag

Y2 - 11 July 2017 through 13 July 2017

ER -

Taha B, Dias J , Werghi N. Classification of cervical-cancer using pap-smear images: A convolutional neural network approach. In Gonzalez-Castro V, Valdes Hernandez M, editors, Medical Image Understanding and Analysis - 21st Annual Conference, MIUA 2017, Proceedings. Springer Verlag. 2017. p. 261-272. (Communications in Computer and Information Science). doi: 10.1007/978-3-319-60964-5_23

Classification of cervical-cancer using pap-smear images: A convolutional neural network approach

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

OpenUrl availability

Other files and links

Fingerprint

Cite this