Classification of mammorgraphic microcalcification clusters using a combination of topological and location modelling

Oluwaseun Ashiru; Reyer Zwiggelaar

doi:10.1109/IPTA.2016.7820986

Classification of mammorgraphic microcalcification clusters using a combination of topological and location modelling

Oluwaseun Ashiru, Reyer Zwiggelaar

Department of Computer Science

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

3 Citations (SciVal)

Abstract

We have investigated the classification of micro-calcification clusters in mammograms by combining two existing approaches. One of the approaches involves extracting and using topological information (connectivity) about micro-calcification clusters as feature vectors to classify them as being benign or malignant. The other approach involves extracting and using location details of micro-calcification clusters (where they appear in a breast and/or mammogram) as feature vectors to classify them as being benign or malignant. We have investigated various aspects of both methods and their combination. Our initial results, based on MIAS and DDSM indicate no significant improvement over the topological approach on its own

Original language	English
Title of host publication	6th International Conference on Image Processing Theory
Subtitle of host publication	Tools and Applications
Editors	M. Pietikainen, A. Hadid, M. B. Lopez
Publisher	IEEE Press
ISBN (Print)	978-146738910-5
DOIs	https://doi.org/10.1109/IPTA.2016.7820986
Publication status	Published - 17 Jan 2017
Event	6th International Conference on Image Processing Theory : Tools and Applications - Oulu, Finland Duration: 12 Dec 2016 → 15 Dec 2016

Conference

Conference	6th International Conference on Image Processing Theory
Abbreviated title	IPTA 2016
Country/Territory	Finland
City	Oulu
Period	12 Dec 2016 → 15 Dec 2016

Keywords

topology
mammography
delta-sigma modulation
feature extraction
breast cancer

UN SDGs

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

Access to Document

10.1109/IPTA.2016.7820986

Permanent link

Persistent link

Cite this

@inproceedings{6b68dfb4e63548be9e8c1cf1621e2962,

title = "Classification of mammorgraphic microcalcification clusters using a combination of topological and location modelling",

abstract = "We have investigated the classification of micro-calcification clusters in mammograms by combining two existing approaches. One of the approaches involves extracting and using topological information (connectivity) about micro-calcification clusters as feature vectors to classify them as being benign or malignant. The other approach involves extracting and using location details of micro-calcification clusters (where they appear in a breast and/or mammogram) as feature vectors to classify them as being benign or malignant. We have investigated various aspects of both methods and their combination. Our initial results, based on MIAS and DDSM indicate no significant improvement over the topological approach on its own",

keywords = "topology, mammography, delta-sigma modulation, feature extraction, breast cancer",

author = "Oluwaseun Ashiru and Reyer Zwiggelaar",

year = "2017",

month = jan,

day = "17",

doi = "10.1109/IPTA.2016.7820986",

language = "English",

isbn = "978-146738910-5",

editor = "M. Pietikainen and A. Hadid and Lopez, {M. B.}",

booktitle = "6th International Conference on Image Processing Theory",

publisher = "IEEE Press",

address = "United States of America",

note = "6th International Conference on Image Processing Theory : Tools and Applications, IPTA 2016 ; Conference date: 12-12-2016 Through 15-12-2016",

}

Ashiru, O & Zwiggelaar, R 2017, Classification of mammorgraphic microcalcification clusters using a combination of topological and location modelling. in M Pietikainen, A Hadid & MB Lopez (eds), 6th International Conference on Image Processing Theory: Tools and Applications., 7820986, IEEE Press, 6th International Conference on Image Processing Theory , Oulu, Finland, 12 Dec 2016. https://doi.org/10.1109/IPTA.2016.7820986

Classification of mammorgraphic microcalcification clusters using a combination of topological and location modelling. / Ashiru, Oluwaseun; Zwiggelaar, Reyer.

6th International Conference on Image Processing Theory: Tools and Applications. ed. / M. Pietikainen; A. Hadid; M. B. Lopez. IEEE Press, 2017. 7820986.

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

TY - GEN

T1 - Classification of mammorgraphic microcalcification clusters using a combination of topological and location modelling

AU - Ashiru, Oluwaseun

AU - Zwiggelaar, Reyer

PY - 2017/1/17

Y1 - 2017/1/17

N2 - We have investigated the classification of micro-calcification clusters in mammograms by combining two existing approaches. One of the approaches involves extracting and using topological information (connectivity) about micro-calcification clusters as feature vectors to classify them as being benign or malignant. The other approach involves extracting and using location details of micro-calcification clusters (where they appear in a breast and/or mammogram) as feature vectors to classify them as being benign or malignant. We have investigated various aspects of both methods and their combination. Our initial results, based on MIAS and DDSM indicate no significant improvement over the topological approach on its own

AB - We have investigated the classification of micro-calcification clusters in mammograms by combining two existing approaches. One of the approaches involves extracting and using topological information (connectivity) about micro-calcification clusters as feature vectors to classify them as being benign or malignant. The other approach involves extracting and using location details of micro-calcification clusters (where they appear in a breast and/or mammogram) as feature vectors to classify them as being benign or malignant. We have investigated various aspects of both methods and their combination. Our initial results, based on MIAS and DDSM indicate no significant improvement over the topological approach on its own

KW - topology

KW - mammography

KW - delta-sigma modulation

KW - feature extraction

KW - breast cancer

UR - http://hdl.handle.net/2160/44699

U2 - 10.1109/IPTA.2016.7820986

DO - 10.1109/IPTA.2016.7820986

M3 - Conference Proceeding (Non-Journal item)

SN - 978-146738910-5

BT - 6th International Conference on Image Processing Theory

A2 - Pietikainen, M.

A2 - Hadid, A.

A2 - Lopez, M. B.

PB - IEEE Press

T2 - 6th International Conference on Image Processing Theory

Y2 - 12 December 2016 through 15 December 2016

ER -

Classification of mammorgraphic microcalcification clusters using a combination of topological and location modelling

Abstract

Conference

Keywords

UN SDGs

Access to Document

Permanent link

Other files and links

Fingerprint

Cite this