Automatic Segmentation of Microcalcification Clusters

Nashid Alam; Arnau Oliver; Erika R. E. Denton; Reyer Zwiggelaar

doi:10.1007/978-3-319-95921-4_24

Automatic Segmentation of Microcalcification Clusters

Nashid Alam, Arnau Oliver, Erika R. E. Denton, Reyer Zwiggelaar

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (Non-Journal item)

19 Citations (Scopus)

Abstract

Early detection of microcalcification (MC) clusters plays a crucial role in enhancing breast cancer diagnosis. Two automated MC cluster segmentation techniques are proposed based on morphological operations that incorporate image decomposition and interpolation methods. For both approaches, initially the contrast between the background tissue and MC cluster was increased and subsequently morphological operations were used. Evaluation was based on the Dice similarity scores and the results of MC cluster classification. A total number of 248 (131 benign and 117 malignant) and 24 (12 benign and 12 malignant) biopsy-proven digitized mammograms were considered from the DDSM and MIAS databases, which showed a classification accuracy of 94.48 ± 1.11% and
100.00 ± 0.00% respectively.

Original language	English
Title of host publication	Proceedings 22nd Conference, Medical Image Understanding and Analysis 2018
Editors	Mark Nixon, Sasan Mahmoodi, Reyer Zwiggelaar
Publisher	Springer Nature
Pages	251-261
Number of pages	11
ISBN (Electronic)	978-3-319-95921-4
ISBN (Print)	978-3-319-95920-7
DOIs	https://doi.org/10.1007/978-3-319-95921-4_24
Publication status	Published - 21 Aug 2018
Event	Proceedings 22nd Conference Medical Image Understanding and Analysis - Southampton, United Kingdom of Great Britain and Northern Ireland Duration: 09 Jul 2018 → 11 Jul 2018

Publication series

Name	Communications in Computer and Information Science
Publisher	Springer Nature
Volume	894
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	Proceedings 22nd Conference Medical Image Understanding and Analysis
Abbreviated title	MIUA 2018
Country/Territory	United Kingdom of Great Britain and Northern Ireland
City	Southampton
Period	09 Jul 2018 → 11 Jul 2018

UN SDGs

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

Access to Document

10.1007/978-3-319-95921-4_24

Permanent link

Persistent link

Cite this

Alam, N., Oliver, A., Denton, E. R. E., & Zwiggelaar, R. (2018). Automatic Segmentation of Microcalcification Clusters. In M. Nixon, S. Mahmoodi, & R. Zwiggelaar (Eds.), Proceedings 22nd Conference, Medical Image Understanding and Analysis 2018 (pp. 251-261). (Communications in Computer and Information Science; Vol. 894). Springer Nature. https://doi.org/10.1007/978-3-319-95921-4_24

@inproceedings{6670c14699a84188966307121ffa7956,

title = "Automatic Segmentation of Microcalcification Clusters",

abstract = "Early detection of microcalcification (MC) clusters plays a crucial role in enhancing breast cancer diagnosis. Two automated MC cluster segmentation techniques are proposed based on morphological operations that incorporate image decomposition and interpolation methods. For both approaches, initially the contrast between the background tissue and MC cluster was increased and subsequently morphological operations were used. Evaluation was based on the Dice similarity scores and the results of MC cluster classification. A total number of 248 (131 benign and 117 malignant) and 24 (12 benign and 12 malignant) biopsy-proven digitized mammograms were considered from the DDSM and MIAS databases, which showed a classification accuracy of 94.48 ± 1.11% and 100.00 ± 0.00% respectively.",

author = "Nashid Alam and Arnau Oliver and Denton, {Erika R. E.} and Reyer Zwiggelaar",

year = "2018",

month = aug,

day = "21",

doi = "10.1007/978-3-319-95921-4_24",

language = "English",

isbn = "978-3-319-95920-7",

series = "Communications in Computer and Information Science",

publisher = "Springer Nature",

pages = "251--261",

editor = "Mark Nixon and Sasan Mahmoodi and Reyer Zwiggelaar",

booktitle = "Proceedings 22nd Conference, Medical Image Understanding and Analysis 2018",

address = "Switzerland",

note = "Proceedings 22nd Conference Medical Image Understanding and Analysis, MIUA 2018 ; Conference date: 09-07-2018 Through 11-07-2018",

}

Alam, N, Oliver, A, Denton, ERE & Zwiggelaar, R 2018, Automatic Segmentation of Microcalcification Clusters. in M Nixon, S Mahmoodi & R Zwiggelaar (eds), Proceedings 22nd Conference, Medical Image Understanding and Analysis 2018. Communications in Computer and Information Science, vol. 894, Springer Nature, pp. 251-261, Proceedings 22nd Conference Medical Image Understanding and Analysis, Southampton, United Kingdom of Great Britain and Northern Ireland, 09 Jul 2018. https://doi.org/10.1007/978-3-319-95921-4_24

Automatic Segmentation of Microcalcification Clusters. / Alam, Nashid; Oliver, Arnau; Denton, Erika R. E. et al.
Proceedings 22nd Conference, Medical Image Understanding and Analysis 2018. ed. / Mark Nixon; Sasan Mahmoodi; Reyer Zwiggelaar. Springer Nature, 2018. p. 251-261 (Communications in Computer and Information Science; Vol. 894).

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (Non-Journal item)

TY - GEN

T1 - Automatic Segmentation of Microcalcification Clusters

AU - Alam, Nashid

AU - Oliver, Arnau

AU - Denton, Erika R. E.

AU - Zwiggelaar, Reyer

PY - 2018/8/21

Y1 - 2018/8/21

N2 - Early detection of microcalcification (MC) clusters plays a crucial role in enhancing breast cancer diagnosis. Two automated MC cluster segmentation techniques are proposed based on morphological operations that incorporate image decomposition and interpolation methods. For both approaches, initially the contrast between the background tissue and MC cluster was increased and subsequently morphological operations were used. Evaluation was based on the Dice similarity scores and the results of MC cluster classification. A total number of 248 (131 benign and 117 malignant) and 24 (12 benign and 12 malignant) biopsy-proven digitized mammograms were considered from the DDSM and MIAS databases, which showed a classification accuracy of 94.48 ± 1.11% and 100.00 ± 0.00% respectively.

AB - Early detection of microcalcification (MC) clusters plays a crucial role in enhancing breast cancer diagnosis. Two automated MC cluster segmentation techniques are proposed based on morphological operations that incorporate image decomposition and interpolation methods. For both approaches, initially the contrast between the background tissue and MC cluster was increased and subsequently morphological operations were used. Evaluation was based on the Dice similarity scores and the results of MC cluster classification. A total number of 248 (131 benign and 117 malignant) and 24 (12 benign and 12 malignant) biopsy-proven digitized mammograms were considered from the DDSM and MIAS databases, which showed a classification accuracy of 94.48 ± 1.11% and 100.00 ± 0.00% respectively.

UR - http://www.scopus.com/inward/record.url?scp=85052887449&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-95921-4_24

DO - 10.1007/978-3-319-95921-4_24

M3 - Conference Proceeding (Non-Journal item)

SN - 978-3-319-95920-7

T3 - Communications in Computer and Information Science

SP - 251

EP - 261

BT - Proceedings 22nd Conference, Medical Image Understanding and Analysis 2018

A2 - Nixon, Mark

A2 - Mahmoodi, Sasan

A2 - Zwiggelaar, Reyer

PB - Springer Nature

T2 - Proceedings 22nd Conference Medical Image Understanding and Analysis

Y2 - 9 July 2018 through 11 July 2018

ER -

Automatic Segmentation of Microcalcification Clusters

Abstract

Publication series

Conference

UN SDGs

Access to Document

Permanent link

Other files and links

Fingerprint

Cite this