Spatial Shape Constrained Fuzzy C-Means (FCM) Clustering for Nucleus Segmentation in Pap Smear Images

Ratna Saha; Mariusz Bajger; Gobert Lee

doi:10.1109/DICTA.2016.7797086

Spatial Shape Constrained Fuzzy C-Means (FCM) Clustering for Nucleus Segmentation in Pap Smear Images

Ratna Saha
, Mariusz Bajger
, Gobert Lee

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

45 Citations (Scopus)

Abstract

Precise segmentation of Pap smear cell nucleus is crucial for early diagnosis of cervical cancer. This task is particularly challenging because of cell overlapping, inconsistent staining, poor contrast and other imaging artifacts. In this study, a novel method is proposed to segment cell nucleus from overlapping Pap smear cell images. The proposed technique introduces a circular shape function (CSF) to increase the robustness of Pap cell nucleus segmentation using fuzzy c-means clustering. CSF imposes a shape constrain over the formed clusters, while improves the boundary of the nucleus. The shape function helps to differentiate the pixels having similar intensity value but located in different spatial regions. The method is evaluated using Overlapping Cervical Cytology Image Segmentation Challenge - ISBI 2014 dataset and compared with the traditional FCM clustering and recently published state-of-the-art methods. Both qualitative and quantitative measures indicate that the new technique performs favorably with others.

Original language	English
Title of host publication	2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
Subtitle of host publication	Techniques and Applications, DICTA 2016
Editors	Alan Wee-Chung Liew, Jun Zhou, Yongsheng Gao, Zhiyong Wang, Clinton Fookes, Brian Lovell, Michael Blumenstein
Place of Publication	Piscataway, NJ
Publisher	Institute of Electrical and Electronics Engineers
ISBN (Electronic)	9781509028962
ISBN (Print)	978-1-5090-2896-2
DOIs	https://doi.org/10.1109/DICTA.2016.7797086
Publication status	Published - 22 Dec 2016
Event	2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA) - Duration: 30 Nov 2016 → …

Publication series

Name	2016 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2016

Conference

Conference	2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
Period	30/11/16 → …

UN SDGs

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

SDG 3 Good Health and Well-being

Access to Document

10.1109/DICTA.2016.7797086Licence: In Copyright

Cite this

Saha, R., Bajger, M., & Lee, G. (2016). Spatial Shape Constrained Fuzzy C-Means (FCM) Clustering for Nucleus Segmentation in Pap Smear Images. In A. W.-C. Liew, J. Zhou, Y. Gao, Z. Wang, C. Fookes, B. Lovell, & M. Blumenstein (Eds.), 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA): Techniques and Applications, DICTA 2016 Article 7797086 (2016 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2016). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/DICTA.2016.7797086

Saha, Ratna ; Bajger, Mariusz ; Lee, Gobert. / Spatial Shape Constrained Fuzzy C-Means (FCM) Clustering for Nucleus Segmentation in Pap Smear Images. 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA): Techniques and Applications, DICTA 2016. editor / Alan Wee-Chung Liew ; Jun Zhou ; Yongsheng Gao ; Zhiyong Wang ; Clinton Fookes ; Brian Lovell ; Michael Blumenstein. Piscataway, NJ : Institute of Electrical and Electronics Engineers, 2016. (2016 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2016).

@inproceedings{88b952aeb15646f296b94502b6ddafaf,

title = "Spatial Shape Constrained Fuzzy C-Means (FCM) Clustering for Nucleus Segmentation in Pap Smear Images",

abstract = "Precise segmentation of Pap smear cell nucleus is crucial for early diagnosis of cervical cancer. This task is particularly challenging because of cell overlapping, inconsistent staining, poor contrast and other imaging artifacts. In this study, a novel method is proposed to segment cell nucleus from overlapping Pap smear cell images. The proposed technique introduces a circular shape function (CSF) to increase the robustness of Pap cell nucleus segmentation using fuzzy c-means clustering. CSF imposes a shape constrain over the formed clusters, while improves the boundary of the nucleus. The shape function helps to differentiate the pixels having similar intensity value but located in different spatial regions. The method is evaluated using Overlapping Cervical Cytology Image Segmentation Challenge - ISBI 2014 dataset and compared with the traditional FCM clustering and recently published state-of-the-art methods. Both qualitative and quantitative measures indicate that the new technique performs favorably with others.",

author = "Ratna Saha and Mariusz Bajger and Gobert Lee",

year = "2016",

month = dec,

day = "22",

doi = "10.1109/DICTA.2016.7797086",

language = "English",

isbn = "978-1-5090-2896-2",

series = "2016 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2016",

publisher = "Institute of Electrical and Electronics Engineers",

editor = "Liew, \{Alan Wee-Chung\} and Jun Zhou and Yongsheng Gao and Zhiyong Wang and Clinton Fookes and Brian Lovell and Michael Blumenstein",

booktitle = "2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA)",

address = "United States",

note = "2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA) ; Conference date: 30-11-2016",

}

Saha, R, Bajger, M & Lee, G 2016, Spatial Shape Constrained Fuzzy C-Means (FCM) Clustering for Nucleus Segmentation in Pap Smear Images. in AW-C Liew, J Zhou, Y Gao, Z Wang, C Fookes, B Lovell & M Blumenstein (eds), 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA): Techniques and Applications, DICTA 2016., 7797086, 2016 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2016, Institute of Electrical and Electronics Engineers, Piscataway, NJ, 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 30/11/16. https://doi.org/10.1109/DICTA.2016.7797086

Spatial Shape Constrained Fuzzy C-Means (FCM) Clustering for Nucleus Segmentation in Pap Smear Images. / Saha, Ratna; Bajger, Mariusz ; Lee, Gobert.
2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA): Techniques and Applications, DICTA 2016. ed. / Alan Wee-Chung Liew; Jun Zhou; Yongsheng Gao; Zhiyong Wang; Clinton Fookes; Brian Lovell; Michael Blumenstein. Piscataway, NJ: Institute of Electrical and Electronics Engineers, 2016. 7797086 (2016 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2016).

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

TY - GEN

T1 - Spatial Shape Constrained Fuzzy C-Means (FCM) Clustering for Nucleus Segmentation in Pap Smear Images

AU - Saha, Ratna

AU - Bajger, Mariusz

AU - Lee, Gobert

PY - 2016/12/22

Y1 - 2016/12/22

N2 - Precise segmentation of Pap smear cell nucleus is crucial for early diagnosis of cervical cancer. This task is particularly challenging because of cell overlapping, inconsistent staining, poor contrast and other imaging artifacts. In this study, a novel method is proposed to segment cell nucleus from overlapping Pap smear cell images. The proposed technique introduces a circular shape function (CSF) to increase the robustness of Pap cell nucleus segmentation using fuzzy c-means clustering. CSF imposes a shape constrain over the formed clusters, while improves the boundary of the nucleus. The shape function helps to differentiate the pixels having similar intensity value but located in different spatial regions. The method is evaluated using Overlapping Cervical Cytology Image Segmentation Challenge - ISBI 2014 dataset and compared with the traditional FCM clustering and recently published state-of-the-art methods. Both qualitative and quantitative measures indicate that the new technique performs favorably with others.

AB - Precise segmentation of Pap smear cell nucleus is crucial for early diagnosis of cervical cancer. This task is particularly challenging because of cell overlapping, inconsistent staining, poor contrast and other imaging artifacts. In this study, a novel method is proposed to segment cell nucleus from overlapping Pap smear cell images. The proposed technique introduces a circular shape function (CSF) to increase the robustness of Pap cell nucleus segmentation using fuzzy c-means clustering. CSF imposes a shape constrain over the formed clusters, while improves the boundary of the nucleus. The shape function helps to differentiate the pixels having similar intensity value but located in different spatial regions. The method is evaluated using Overlapping Cervical Cytology Image Segmentation Challenge - ISBI 2014 dataset and compared with the traditional FCM clustering and recently published state-of-the-art methods. Both qualitative and quantitative measures indicate that the new technique performs favorably with others.

UR - http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7797086

UR - https://www.scopus.com/pages/publications/85011026179

U2 - 10.1109/DICTA.2016.7797086

DO - 10.1109/DICTA.2016.7797086

M3 - Conference contribution

SN - 978-1-5090-2896-2

T3 - 2016 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2016

BT - 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA)

A2 - Liew, Alan Wee-Chung

A2 - Zhou, Jun

A2 - Gao, Yongsheng

A2 - Wang, Zhiyong

A2 - Fookes, Clinton

A2 - Lovell, Brian

A2 - Blumenstein, Michael

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway, NJ

T2 - 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA)

Y2 - 30 November 2016

ER -

Saha R, Bajger M , Lee G. Spatial Shape Constrained Fuzzy C-Means (FCM) Clustering for Nucleus Segmentation in Pap Smear Images. In Liew AWC, Zhou J, Gao Y, Wang Z, Fookes C, Lovell B, Blumenstein M, editors, 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA): Techniques and Applications, DICTA 2016. Piscataway, NJ: Institute of Electrical and Electronics Engineers. 2016. 7797086. (2016 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2016). doi: 10.1109/DICTA.2016.7797086

Spatial Shape Constrained Fuzzy C-Means (FCM) Clustering for Nucleus Segmentation in Pap Smear Images

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this