A multi-view deep learning architecture for classification of breast microcalcifications

Alan Joseph Bekker; Hayit Greenspan; Jacob Goldberger

doi:10.1109/isbi.2016.7493369

A multi-view deep learning architecture for classification of breast microcalcifications

Alan Joseph Bekker, Hayit Greenspan, Jacob Goldberger

Tel Aviv University

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

47 Scopus citations

Abstract

In this paper we address the problem of differentiating between malignant and benign tumors based on their appearance in the CC and MLO mammography views. Classification of clustered breast microcalcifications into benign and malignant categories is an extremely challenging task for computerized algorithms and expert radiologists alike. We describe a deep-learning classification method that is based on two view-level decisions, implemented by two neural networks, followed by a single-neuron layer that combines the viewlevel decisions into a global decision that mimics the biopsy results. Our method is evaluated on a large multi-view dataset extracted from the standardized digital database for screening mammography (DDSM). Experimental results show that our network structure significantly improves on previously suggested methods.

Original language	English
Title of host publication	2016 IEEE International Symposium on Biomedical Imaging
Subtitle of host publication	From Nano to Macro, ISBI 2016 - Proceedings
Publisher	IEEE Computer Society
Pages	726-730
Number of pages	5
ISBN (Electronic)	9781479923502
DOIs	https://doi.org/10.1109/isbi.2016.7493369
State	Published - 15 Jun 2016
Event	2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Prague, Czech Republic Duration: 13 Apr 2016 → 16 Apr 2016

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2016-June
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016
Country/Territory	Czech Republic
City	Prague
Period	13/04/16 → 16/04/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

Computer-aided diagnosis (CADx)
Mammography
Microcalcifications
deep-learning
multi-view analysis

Access to Document

10.1109/isbi.2016.7493369

Cite this

Bekker, A. J., Greenspan, H., & Goldberger, J. (2016). A multi-view deep learning architecture for classification of breast microcalcifications. In 2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings (pp. 726-730). Article 7493369 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2016-June). IEEE Computer Society. https://doi.org/10.1109/isbi.2016.7493369

@inproceedings{2fd0246cd06e45fdb87bf24e376c818e,

title = "A multi-view deep learning architecture for classification of breast microcalcifications",

abstract = "In this paper we address the problem of differentiating between malignant and benign tumors based on their appearance in the CC and MLO mammography views. Classification of clustered breast microcalcifications into benign and malignant categories is an extremely challenging task for computerized algorithms and expert radiologists alike. We describe a deep-learning classification method that is based on two view-level decisions, implemented by two neural networks, followed by a single-neuron layer that combines the viewlevel decisions into a global decision that mimics the biopsy results. Our method is evaluated on a large multi-view dataset extracted from the standardized digital database for screening mammography (DDSM). Experimental results show that our network structure significantly improves on previously suggested methods.",

keywords = "Computer-aided diagnosis (CADx), Mammography, Microcalcifications, deep-learning, multi-view analysis",

author = "Bekker, {Alan Joseph} and Hayit Greenspan and Jacob Goldberger",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 ; Conference date: 13-04-2016 Through 16-04-2016",

year = "2016",

month = jun,

day = "15",

doi = "10.1109/isbi.2016.7493369",

language = "אנגלית",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

pages = "726--730",

booktitle = "2016 IEEE International Symposium on Biomedical Imaging",

address = "ארצות הברית",

}

Bekker, AJ, Greenspan, H & Goldberger, J 2016, A multi-view deep learning architecture for classification of breast microcalcifications. in 2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings., 7493369, Proceedings - International Symposium on Biomedical Imaging, vol. 2016-June, IEEE Computer Society, pp. 726-730, 2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016, Prague, Czech Republic, 13/04/16. https://doi.org/10.1109/isbi.2016.7493369

A multi-view deep learning architecture for classification of breast microcalcifications. / Bekker, Alan Joseph; Greenspan, Hayit; Goldberger, Jacob.
2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings. IEEE Computer Society, 2016. p. 726-730 7493369 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2016-June).

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

TY - GEN

T1 - A multi-view deep learning architecture for classification of breast microcalcifications

AU - Bekker, Alan Joseph

AU - Greenspan, Hayit

AU - Goldberger, Jacob

PY - 2016/6/15

Y1 - 2016/6/15

N2 - In this paper we address the problem of differentiating between malignant and benign tumors based on their appearance in the CC and MLO mammography views. Classification of clustered breast microcalcifications into benign and malignant categories is an extremely challenging task for computerized algorithms and expert radiologists alike. We describe a deep-learning classification method that is based on two view-level decisions, implemented by two neural networks, followed by a single-neuron layer that combines the viewlevel decisions into a global decision that mimics the biopsy results. Our method is evaluated on a large multi-view dataset extracted from the standardized digital database for screening mammography (DDSM). Experimental results show that our network structure significantly improves on previously suggested methods.

AB - In this paper we address the problem of differentiating between malignant and benign tumors based on their appearance in the CC and MLO mammography views. Classification of clustered breast microcalcifications into benign and malignant categories is an extremely challenging task for computerized algorithms and expert radiologists alike. We describe a deep-learning classification method that is based on two view-level decisions, implemented by two neural networks, followed by a single-neuron layer that combines the viewlevel decisions into a global decision that mimics the biopsy results. Our method is evaluated on a large multi-view dataset extracted from the standardized digital database for screening mammography (DDSM). Experimental results show that our network structure significantly improves on previously suggested methods.

KW - Computer-aided diagnosis (CADx)

KW - Mammography

KW - Microcalcifications

KW - deep-learning

KW - multi-view analysis

UR - http://www.scopus.com/inward/record.url?scp=84978394324&partnerID=8YFLogxK

U2 - 10.1109/isbi.2016.7493369

DO - 10.1109/isbi.2016.7493369

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:84978394324

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 726

EP - 730

BT - 2016 IEEE International Symposium on Biomedical Imaging

PB - IEEE Computer Society

T2 - 2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016

Y2 - 13 April 2016 through 16 April 2016

ER -

Bekker AJ, Greenspan H, Goldberger J. A multi-view deep learning architecture for classification of breast microcalcifications. In 2016 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Proceedings. IEEE Computer Society. 2016. p. 726-730. 7493369. (Proceedings - International Symposium on Biomedical Imaging). doi: 10.1109/isbi.2016.7493369

A multi-view deep learning architecture for classification of breast microcalcifications

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this