Learning density independent texture features

Michiel Gijsbertus J. Kallenberg; Mads Nielsen; Katharina Holland; Nico Karssemeijer; Christian Igel; Martin Lillholm

doi:10.1007/978-3-319-41546-8_38

Learning density independent texture features

Michiel Gijsbertus J. Kallenberg, Mads Nielsen, Katharina Holland, Nico Karssemeijer, Christian Igel, Martin Lillholm

Department of Computer Science

Abstract

Breast cancer risk assessment is becoming increasingly important in clinical practice. It has been suggested that features that characterize mammographic texture are more predictive for breast cancer than breast density. Yet, strong correlation between both types of features is an issue in many studies. In this work we investigate a method to generate texture features and/or scores that are independent of breast density. The method is especially useful in settings where features are learned from the data itself. We evaluate our method on a case control set comprising 394 cancers, and 1182 healthy controls. We show that the learned density independent texture features are significantly associated with breast cancer risk. As such it may aid in exploring breast characteristics that are predictive of breast cancer irrespective of breast density. Furthermore it offers opportunities to enhance personalized breast cancer screening beyond breast density.

Original language	English
Title of host publication	Breast Imaging : 13th International Workshop, IWDM 2016, Malmö, Sweden, June 19-22, 2016, Proceedings
Editors	Anders Tingberg, Kristina Lång, Pontus Timberg
Number of pages	8
Publisher	Springer
Publication date	2016
Pages	299-306
Chapter	38
ISBN (Print)	978-3-319-41545-1
ISBN (Electronic)	978-3-319-41546-8
DOIs	https://doi.org/10.1007/978-3-319-41546-8_38
Publication status	Published - 2016
Event	13th International Workshop on Breast Imaging - Malmö Live, Malmö, Sweden Duration: 19 Jun 2016 → 22 Jun 2016 Conference number: 13

Conference

Conference	13th International Workshop on Breast Imaging
Number	13
Location	Malmö Live
Country/Territory	Sweden
City	Malmö
Period	19/06/2016 → 22/06/2016

Series	Lecture notes in computer science
Volume	9699
ISSN	0302-9743

UN SDGs

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

Access to Document

10.1007/978-3-319-41546-8_38

Cite this

Kallenberg, M. G. J., Nielsen, M., Holland, K., Karssemeijer, N., Igel, C., & Lillholm, M. (2016). Learning density independent texture features. In A. Tingberg, K. Lång, & P. Timberg (Eds.), Breast Imaging: 13th International Workshop, IWDM 2016, Malmö, Sweden, June 19-22, 2016, Proceedings (pp. 299-306). Springer. Lecture notes in computer science Vol. 9699 https://doi.org/10.1007/978-3-319-41546-8_38

Learning density independent texture features. / Kallenberg, Michiel Gijsbertus J.; Nielsen, Mads; Holland, Katharina et al.

Breast Imaging: 13th International Workshop, IWDM 2016, Malmö, Sweden, June 19-22, 2016, Proceedings. ed. / Anders Tingberg; Kristina Lång; Pontus Timberg. Springer, 2016. p. 299-306 (Lecture notes in computer science, Vol. 9699).

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

Kallenberg, MGJ, Nielsen, M, Holland, K, Karssemeijer, N, Igel, C & Lillholm, M 2016, Learning density independent texture features. in A Tingberg, K Lång & P Timberg (eds), Breast Imaging: 13th International Workshop, IWDM 2016, Malmö, Sweden, June 19-22, 2016, Proceedings. Springer, Lecture notes in computer science, vol. 9699, pp. 299-306, 13th International Workshop on Breast Imaging, Malmö, Sweden, 19/06/2016. https://doi.org/10.1007/978-3-319-41546-8_38

Kallenberg MGJ, Nielsen M, Holland K, Karssemeijer N, Igel C , Lillholm M. Learning density independent texture features. In Tingberg A, Lång K, Timberg P, editors, Breast Imaging: 13th International Workshop, IWDM 2016, Malmö, Sweden, June 19-22, 2016, Proceedings. Springer. 2016. p. 299-306. (Lecture notes in computer science, Vol. 9699). doi: 10.1007/978-3-319-41546-8_38

@inproceedings{f4eef6de331c49699f0a8604b8b2b220,

title = "Learning density independent texture features",

abstract = "Breast cancer risk assessment is becoming increasingly important in clinical practice. It has been suggested that features that characterize mammographic texture are more predictive for breast cancer than breast density. Yet, strong correlation between both types of features is an issue in many studies. In this work we investigate a method to generate texture features and/or scores that are independent of breast density. The method is especially useful in settings where features are learned from the data itself. We evaluate our method on a case control set comprising 394 cancers, and 1182 healthy controls. We show that the learned density independent texture features are significantly associated with breast cancer risk. As such it may aid in exploring breast characteristics that are predictive of breast cancer irrespective of breast density. Furthermore it offers opportunities to enhance personalized breast cancer screening beyond breast density.",

author = "Kallenberg, {Michiel Gijsbertus J.} and Mads Nielsen and Katharina Holland and Nico Karssemeijer and Christian Igel and Martin Lillholm",

year = "2016",

doi = "10.1007/978-3-319-41546-8_38",

language = "English",

isbn = "978-3-319-41545-1",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "299--306",

editor = "Anders Tingberg and Kristina L{\aa}ng and Pontus Timberg",

booktitle = "Breast Imaging",

note = "13th International Workshop on Breast Imaging, IWDM 2016 ; Conference date: 19-06-2016 Through 22-06-2016",

}

TY - GEN

T1 - Learning density independent texture features

AU - Kallenberg, Michiel Gijsbertus J.

AU - Nielsen, Mads

AU - Holland, Katharina

AU - Karssemeijer, Nico

AU - Igel, Christian

AU - Lillholm, Martin

N1 - Conference code: 13

PY - 2016

Y1 - 2016

N2 - Breast cancer risk assessment is becoming increasingly important in clinical practice. It has been suggested that features that characterize mammographic texture are more predictive for breast cancer than breast density. Yet, strong correlation between both types of features is an issue in many studies. In this work we investigate a method to generate texture features and/or scores that are independent of breast density. The method is especially useful in settings where features are learned from the data itself. We evaluate our method on a case control set comprising 394 cancers, and 1182 healthy controls. We show that the learned density independent texture features are significantly associated with breast cancer risk. As such it may aid in exploring breast characteristics that are predictive of breast cancer irrespective of breast density. Furthermore it offers opportunities to enhance personalized breast cancer screening beyond breast density.

AB - Breast cancer risk assessment is becoming increasingly important in clinical practice. It has been suggested that features that characterize mammographic texture are more predictive for breast cancer than breast density. Yet, strong correlation between both types of features is an issue in many studies. In this work we investigate a method to generate texture features and/or scores that are independent of breast density. The method is especially useful in settings where features are learned from the data itself. We evaluate our method on a case control set comprising 394 cancers, and 1182 healthy controls. We show that the learned density independent texture features are significantly associated with breast cancer risk. As such it may aid in exploring breast characteristics that are predictive of breast cancer irrespective of breast density. Furthermore it offers opportunities to enhance personalized breast cancer screening beyond breast density.

U2 - 10.1007/978-3-319-41546-8_38

DO - 10.1007/978-3-319-41546-8_38

M3 - Article in proceedings

SN - 978-3-319-41545-1

T3 - Lecture notes in computer science

SP - 299

EP - 306

BT - Breast Imaging

A2 - Tingberg, Anders

A2 - Lång, Kristina

A2 - Timberg, Pontus

PB - Springer

T2 - 13th International Workshop on Breast Imaging

Y2 - 19 June 2016 through 22 June 2016

ER -

Learning density independent texture features

Abstract

Conference

UN SDGs

Access to Document

Fingerprint

Cite this