Statistical modelling of lines and structures in mammograms

Reyer Zwiggelaar; Tim Parr; Caroline Boggis; Sue Astley; Christopher J. Taylor

doi:10.1007/3-540-63046-5_34

Statistical modelling of lines and structures in mammograms

Reyer Zwiggelaar, Tim Parr, Caroline Boggis, Sue Astley, Christopher J. Taylor

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

2 Citations (Scopus)

Abstract

Computer-aided mammographic prompting systems require the reliable detection of a variety of signs of cancer. The emphasis of the work described is the correct classification of linear structures in mammograms. Statistical modelling, based on principal component analysis (PCA), has been developed for describing the cross-sectional profiles of linear structures, the motivation being that the shapes of intensity profiles may be characteristic of the type of structure. PCA models have been applied to whole mammograms to obtain images in which spicules, linear structures associated with stellate lesions, are emphasised. The aim is to improve the performance of automatic stellate lesion detection by concentrating on those structures most likely to be associated with lesions.

Original language	English
Title of host publication	Information Processing in Medical Imaging
Subtitle of host publication	15th International Conference, IPMI'97, Poultney, Vermont, USA, June 9-13, 1997, Proceedings
Editors	James Duncan, Gene Gindi
Publisher	Springer Nature
Pages	405-410
Number of pages	6
ISBN (Electronic)	978-3-540-69070-2
ISBN (Print)	3540630465, 9783540630463
DOIs	https://doi.org/10.1007/3-540-63046-5_34
Publication status	Published - 21 May 1997
Externally published	Yes
Event	Proceedings of the 15th International Conference : Information Processing in Medical Imaging - Poultney, United States of America Duration: 09 Jun 1997 → 13 Jun 1997

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Nature
Volume	1230
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	Proceedings of the 15th International Conference
Abbreviated title	IPMI'97
Country/Territory	United States of America
City	Poultney
Period	09 Jun 1997 → 13 Jun 1997

UN SDGs

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

Access to Document

10.1007/3-540-63046-5_34

Permanent link

Persistent link

Cite this

Zwiggelaar, R., Parr, T., Boggis, C., Astley, S., & Taylor, C. J. (1997). Statistical modelling of lines and structures in mammograms. In J. Duncan, & G. Gindi (Eds.), Information Processing in Medical Imaging: 15th International Conference, IPMI'97, Poultney, Vermont, USA, June 9-13, 1997, Proceedings (pp. 405-410). (Lecture Notes in Computer Science; Vol. 1230). Springer Nature. https://doi.org/10.1007/3-540-63046-5_34

@inproceedings{0fcf24911f4b4591bb1b40c27aac6fa0,

title = "Statistical modelling of lines and structures in mammograms",

abstract = "Computer-aided mammographic prompting systems require the reliable detection of a variety of signs of cancer. The emphasis of the work described is the correct classification of linear structures in mammograms. Statistical modelling, based on principal component analysis (PCA), has been developed for describing the cross-sectional profiles of linear structures, the motivation being that the shapes of intensity profiles may be characteristic of the type of structure. PCA models have been applied to whole mammograms to obtain images in which spicules, linear structures associated with stellate lesions, are emphasised. The aim is to improve the performance of automatic stellate lesion detection by concentrating on those structures most likely to be associated with lesions.",

author = "Reyer Zwiggelaar and Tim Parr and Caroline Boggis and Sue Astley and Taylor, {Christopher J.}",

note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 1997.; Proceedings of the 15th International Conference : Information Processing in Medical Imaging, IPMI'97 ; Conference date: 09-06-1997 Through 13-06-1997",

year = "1997",

month = may,

day = "21",

doi = "10.1007/3-540-63046-5_34",

language = "English",

isbn = "3540630465",

series = "Lecture Notes in Computer Science",

publisher = "Springer Nature",

pages = "405--410",

editor = "James Duncan and Gene Gindi",

booktitle = "Information Processing in Medical Imaging",

address = "Switzerland",

}

Zwiggelaar, R, Parr, T, Boggis, C, Astley, S & Taylor, CJ 1997, Statistical modelling of lines and structures in mammograms. in J Duncan & G Gindi (eds), Information Processing in Medical Imaging: 15th International Conference, IPMI'97, Poultney, Vermont, USA, June 9-13, 1997, Proceedings. Lecture Notes in Computer Science, vol. 1230, Springer Nature, pp. 405-410, Proceedings of the 15th International Conference , Poultney, Vermont, United States of America, 09 Jun 1997. https://doi.org/10.1007/3-540-63046-5_34

Statistical modelling of lines and structures in mammograms. / Zwiggelaar, Reyer; Parr, Tim; Boggis, Caroline et al.
Information Processing in Medical Imaging: 15th International Conference, IPMI'97, Poultney, Vermont, USA, June 9-13, 1997, Proceedings. ed. / James Duncan; Gene Gindi. Springer Nature, 1997. p. 405-410 (Lecture Notes in Computer Science; Vol. 1230).

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

TY - GEN

T1 - Statistical modelling of lines and structures in mammograms

AU - Zwiggelaar, Reyer

AU - Parr, Tim

AU - Boggis, Caroline

AU - Astley, Sue

AU - Taylor, Christopher J.

PY - 1997/5/21

Y1 - 1997/5/21

N2 - Computer-aided mammographic prompting systems require the reliable detection of a variety of signs of cancer. The emphasis of the work described is the correct classification of linear structures in mammograms. Statistical modelling, based on principal component analysis (PCA), has been developed for describing the cross-sectional profiles of linear structures, the motivation being that the shapes of intensity profiles may be characteristic of the type of structure. PCA models have been applied to whole mammograms to obtain images in which spicules, linear structures associated with stellate lesions, are emphasised. The aim is to improve the performance of automatic stellate lesion detection by concentrating on those structures most likely to be associated with lesions.

AB - Computer-aided mammographic prompting systems require the reliable detection of a variety of signs of cancer. The emphasis of the work described is the correct classification of linear structures in mammograms. Statistical modelling, based on principal component analysis (PCA), has been developed for describing the cross-sectional profiles of linear structures, the motivation being that the shapes of intensity profiles may be characteristic of the type of structure. PCA models have been applied to whole mammograms to obtain images in which spicules, linear structures associated with stellate lesions, are emphasised. The aim is to improve the performance of automatic stellate lesion detection by concentrating on those structures most likely to be associated with lesions.

UR - http://www.scopus.com/inward/record.url?scp=77954631619&partnerID=8YFLogxK

U2 - 10.1007/3-540-63046-5_34

DO - 10.1007/3-540-63046-5_34

M3 - Conference Proceeding (Non-Journal item)

SN - 3540630465

SN - 9783540630463

T3 - Lecture Notes in Computer Science

SP - 405

EP - 410

BT - Information Processing in Medical Imaging

A2 - Duncan, James

A2 - Gindi, Gene

PB - Springer Nature

T2 - Proceedings of the 15th International Conference

Y2 - 9 June 1997 through 13 June 1997

ER -

Zwiggelaar R, Parr T, Boggis C, Astley S, Taylor CJ. Statistical modelling of lines and structures in mammograms. In Duncan J, Gindi G, editors, Information Processing in Medical Imaging: 15th International Conference, IPMI'97, Poultney, Vermont, USA, June 9-13, 1997, Proceedings. Springer Nature. 1997. p. 405-410. (Lecture Notes in Computer Science). doi: 10.1007/3-540-63046-5_34

Statistical modelling of lines and structures in mammograms

Abstract

Publication series

Conference

UN SDGs

Access to Document

Permanent link

Other files and links

Fingerprint

Cite this