Risk Assessment: the use of Background Texture in Mammographic Imaging

Lilian Blot; Erika R. E. Denton; Reyer Zwiggelaar

doi:10.1007/978-3-642-59327-7_127

Risk Assessment: the use of Background Texture in Mammographic Imaging

Lilian Blot, Erika R. E. Denton, Reyer Zwiggelaar

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

Abstract

We have developed an approach to the separation of background texture and structures in images. This technique is based on the statistical difference between local and median co-occurrence matrices. In this paper we investigate if the classification of mammographic parenchymal patterns can be improved if anatomical structures can be removed from the image and the classification is based only on the background texture information. A comparison of two techniques — one developed by Byng, the other developed by Karssemeijer — applied to the original and reconstructed images is presented. To validate our approach, we use a dataset where each mammogram has been classified by experts using two different approaches: Wolf grades and the six classes described by Boyd.

Original language	English
Title of host publication	Digital Mammography
Subtitle of host publication	IWDM 2002 — 6th International Workshop on Digital Mammography
Editors	Heinz-Otto Peitgen
Publisher	Springer Nature
Pages	541-543
Number of pages	3
ISBN (Electronic)	978-3-642-59327-7
ISBN (Print)	978-3-642-63936-4
DOIs	https://doi.org/10.1007/978-3-642-59327-7_127
Publication status	Published - 27 Sept 2011
Externally published	Yes
Event	6th International Workshop on Digital Mammography - Bremen, Germany Duration: 22 Jun 2002 → 25 Jun 2002

Workshop

Workshop	6th International Workshop on Digital Mammography
Abbreviated title	IWDM 2002
Country/Territory	Germany
City	Bremen
Period	22 Jun 2002 → 25 Jun 2002

Access to Document

10.1007/978-3-642-59327-7_127

Permanent link

Persistent link

Cite this

@inproceedings{4c65e1e932e544f6a41d0eca481079aa,

title = "Risk Assessment: the use of Background Texture in Mammographic Imaging ",

abstract = "We have developed an approach to the separation of background texture and structures in images. This technique is based on the statistical difference between local and median co-occurrence matrices. In this paper we investigate if the classification of mammographic parenchymal patterns can be improved if anatomical structures can be removed from the image and the classification is based only on the background texture information. A comparison of two techniques — one developed by Byng, the other developed by Karssemeijer — applied to the original and reconstructed images is presented. To validate our approach, we use a dataset where each mammogram has been classified by experts using two different approaches: Wolf grades and the six classes described by Boyd.",

author = "Lilian Blot and Denton, {Erika R. E.} and Reyer Zwiggelaar",

year = "2011",

month = sep,

day = "27",

doi = "10.1007/978-3-642-59327-7_127",

language = "English",

isbn = "978-3-642-63936-4",

pages = "541--543",

editor = "Heinz-Otto Peitgen",

booktitle = "Digital Mammography",

publisher = "Springer Nature",

address = "Switzerland",

note = "6th International Workshop on Digital Mammography, IWDM 2002 ; Conference date: 22-06-2002 Through 25-06-2002",

}

Blot, L, Denton, ERE & Zwiggelaar, R 2011, Risk Assessment: the use of Background Texture in Mammographic Imaging . in H-O Peitgen (ed.), Digital Mammography: IWDM 2002 — 6th International Workshop on Digital Mammography. Springer Nature, pp. 541-543, 6th International Workshop on Digital Mammography, Bremen, Germany, 22 Jun 2002. https://doi.org/10.1007/978-3-642-59327-7_127

Risk Assessment: the use of Background Texture in Mammographic Imaging . / Blot, Lilian; Denton, Erika R. E.; Zwiggelaar, Reyer.
Digital Mammography: IWDM 2002 — 6th International Workshop on Digital Mammography. ed. / Heinz-Otto Peitgen. Springer Nature, 2011. p. 541-543.

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

TY - GEN

T1 - Risk Assessment

T2 - 6th International Workshop on Digital Mammography

AU - Blot, Lilian

AU - Denton, Erika R. E.

AU - Zwiggelaar, Reyer

PY - 2011/9/27

Y1 - 2011/9/27

N2 - We have developed an approach to the separation of background texture and structures in images. This technique is based on the statistical difference between local and median co-occurrence matrices. In this paper we investigate if the classification of mammographic parenchymal patterns can be improved if anatomical structures can be removed from the image and the classification is based only on the background texture information. A comparison of two techniques — one developed by Byng, the other developed by Karssemeijer — applied to the original and reconstructed images is presented. To validate our approach, we use a dataset where each mammogram has been classified by experts using two different approaches: Wolf grades and the six classes described by Boyd.

AB - We have developed an approach to the separation of background texture and structures in images. This technique is based on the statistical difference between local and median co-occurrence matrices. In this paper we investigate if the classification of mammographic parenchymal patterns can be improved if anatomical structures can be removed from the image and the classification is based only on the background texture information. A comparison of two techniques — one developed by Byng, the other developed by Karssemeijer — applied to the original and reconstructed images is presented. To validate our approach, we use a dataset where each mammogram has been classified by experts using two different approaches: Wolf grades and the six classes described by Boyd.

U2 - 10.1007/978-3-642-59327-7_127

DO - 10.1007/978-3-642-59327-7_127

M3 - Conference Proceeding (Non-Journal item)

SN - 978-3-642-63936-4

SP - 541

EP - 543

BT - Digital Mammography

A2 - Peitgen, Heinz-Otto

PB - Springer Nature

Y2 - 22 June 2002 through 25 June 2002

ER -

Risk Assessment: the use of Background Texture in Mammographic Imaging

Abstract

Workshop

Access to Document

Permanent link

Fingerprint

Cite this