The Detection of Abnormal Masses in Mammograms

Reyer Zwiggelaar; James E. Schumm; Christopher J. Taylor

The Detection of Abnormal Masses in Mammograms

Reyer Zwiggelaar, James E. Schumm, Christopher J. Taylor

University of Manchester

Research output: Contribution to conference › Paper › peer-review

Abstract

Recursive median filtering can be applied to images at a number of scales and orientations giving a scale space description at a pixel level. The resulting scale-orientation signatures can be used to discriminate between different structures, most easily between linear and blob-like structures, but also to describe any remaining texture in the image. As a specific example, the technique is applied to mammography, in the detection of mass-like structures associated with spiculated lesions. For structures of diameter 12mm, a sensitivity of 80% is achieved with 0.25 false positives per image, which compares favourably with the best results found in the literature.

Original language	English
Number of pages	5
Publication status	Published - Jul 1997
Externally published	Yes
Event	Medical Image Understanding and Analysis (MIUA) 1997 - Oxford, United Kingdom of Great Britain and Northern Ireland Duration: 01 Jul 1997 → …

Conference

Conference	Medical Image Understanding and Analysis (MIUA) 1997
Abbreviated title	MIUA 1997
Country/Territory	United Kingdom of Great Britain and Northern Ireland
City	Oxford
Period	01 Jul 1997 → …

Permanent link

Persistent link

Cite this

@conference{46e53b43573147d7aa26b7567b908cd8,

title = "The Detection of Abnormal Masses in Mammograms",

abstract = "Recursive median filtering can be applied to images at a number of scales and orientations giving a scale space description at a pixel level. The resulting scale-orientation signatures can be used to discriminate between different structures, most easily between linear and blob-like structures, but also to describe any remaining texture in the image. As a specific example, the technique is applied to mammography, in the detection of mass-like structures associated with spiculated lesions. For structures of diameter 12mm, a sensitivity of 80% is achieved with 0.25 false positives per image, which compares favourably with the best results found in the literature.",

author = "Reyer Zwiggelaar and Schumm, {James E.} and Taylor, {Christopher J.}",

year = "1997",

month = jul,

language = "English",

note = "Medical Image Understanding and Analysis (MIUA) 1997, MIUA 1997 ; Conference date: 01-07-1997",

}

TY - CONF

T1 - The Detection of Abnormal Masses in Mammograms

AU - Zwiggelaar, Reyer

AU - Schumm, James E.

AU - Taylor, Christopher J.

PY - 1997/7

Y1 - 1997/7

N2 - Recursive median filtering can be applied to images at a number of scales and orientations giving a scale space description at a pixel level. The resulting scale-orientation signatures can be used to discriminate between different structures, most easily between linear and blob-like structures, but also to describe any remaining texture in the image. As a specific example, the technique is applied to mammography, in the detection of mass-like structures associated with spiculated lesions. For structures of diameter 12mm, a sensitivity of 80% is achieved with 0.25 false positives per image, which compares favourably with the best results found in the literature.

AB - Recursive median filtering can be applied to images at a number of scales and orientations giving a scale space description at a pixel level. The resulting scale-orientation signatures can be used to discriminate between different structures, most easily between linear and blob-like structures, but also to describe any remaining texture in the image. As a specific example, the technique is applied to mammography, in the detection of mass-like structures associated with spiculated lesions. For structures of diameter 12mm, a sensitivity of 80% is achieved with 0.25 false positives per image, which compares favourably with the best results found in the literature.

M3 - Paper

T2 - Medical Image Understanding and Analysis (MIUA) 1997

Y2 - 1 July 1997

ER -