Assessing breast cancer masking risk in full field digital mammography with automated texture analysis

Publikation: Bidrag til bog/antologi/rapportKonferenceabstrakt i proceedingsForskningfagfællebedømt

Standard

Assessing breast cancer masking risk in full field digital mammography with automated texture analysis. / Kallenberg, Michiel Gijsbertus J; Lillholm, Martin; Diao, Pengfei; Holland, Katharina; Karssemeijer, Nico; Igel, Christian; Nielsen, Mads.

7th International Workshop on Breast Densitometry and Cancer Risk Assessment (Non-CME). University of California, 2015. s. 109.

Publikation: Bidrag til bog/antologi/rapportKonferenceabstrakt i proceedingsForskningfagfællebedømt

Harvard

Kallenberg, MGJ, Lillholm, M, Diao, P, Holland, K, Karssemeijer, N, Igel, C & Nielsen, M 2015, Assessing breast cancer masking risk in full field digital mammography with automated texture analysis. i 7th International Workshop on Breast Densitometry and Cancer Risk Assessment (Non-CME). University of California, s. 109, 7th International Workshop on Breast Densitometry and Cancer Risk Assessment, 2015, San Francisco, USA, 10/06/2015.

APA

Kallenberg, M. G. J., Lillholm, M., Diao, P., Holland, K., Karssemeijer, N., Igel, C., & Nielsen, M. (2015). Assessing breast cancer masking risk in full field digital mammography with automated texture analysis. I 7th International Workshop on Breast Densitometry and Cancer Risk Assessment (Non-CME) (s. 109). University of California.

Vancouver

Kallenberg MGJ, Lillholm M, Diao P, Holland K, Karssemeijer N, Igel C o.a. Assessing breast cancer masking risk in full field digital mammography with automated texture analysis. I 7th International Workshop on Breast Densitometry and Cancer Risk Assessment (Non-CME). University of California. 2015. s. 109

Author

Kallenberg, Michiel Gijsbertus J ; Lillholm, Martin ; Diao, Pengfei ; Holland, Katharina ; Karssemeijer, Nico ; Igel, Christian ; Nielsen, Mads. / Assessing breast cancer masking risk in full field digital mammography with automated texture analysis. 7th International Workshop on Breast Densitometry and Cancer Risk Assessment (Non-CME). University of California, 2015. s. 109

Bibtex

@inbook{5e830fdec2e74a4a865a6e1fb8ef62ca,
title = "Assessing breast cancer masking risk in full field digital mammography with automated texture analysis",
abstract = "Purpose:The goal of this work is to develop a method to assess the risk of breast cancer masking, based on image characteristics beyond breast density.Method:From the Dutch breast cancer screening program we collected 285 screen detected cancers, and 109 cancers that were screen negative and subsequently appeared as interval cancers. To obtain mammograms without cancerous tissue, we took the contralateral mammograms. We developed a novel machine learning based method called convolutional sparse autoencoder to characterize mammographic texture. The method was trained and tested on raw mammograms to determine cancer detection status in a five-fold cross validation. To assess the interaction of the texture scores with breast density, Volpara Density Grade was determined for each image.Results:We grouped women into low (VDG 1/2) versus high (VDG 3/4) dense, and low (Quartile 1/2) versus high (Q 3/4) texture risk score. We computed odds ratios for breast cancer masking risk (i.e. interval versus screen detected cancer) for each of the subgroups. The odds ratio was 1.63 (1.04-2.53 95{\%}CI) in the high dense group (as compared to the low dense group), whereas for the high texture score group (as compared to the low texture score group) this odds ratio was2.19 (1.37-3.49). Women who were classified as low dense but had a high texture score had a higher masking risk (OR 1.66 (0.53-5.20)) than women with dense breasts but a low texture score.Conclusion:Mammographic texture is associated with breast cancer masking risk. As such, automatic texture analysis offers opportunities to enhance personalized breast cancer screening. We were able to identify a subgroup of women who are at an increased risk of having a cancer that is not detected due to textural masking, even though their breasts are non-dense.",
author = "Kallenberg, {Michiel Gijsbertus J} and Martin Lillholm and Pengfei Diao and Katharina Holland and Nico Karssemeijer and Christian Igel and Mads Nielsen",
year = "2015",
language = "English",
pages = "109",
booktitle = "7th International Workshop on Breast Densitometry and Cancer Risk Assessment (Non-CME)",
publisher = "University of California",
note = "7th International Workshop on Breast Densitometry and Cancer Risk Assessment, 2015 ; Conference date: 10-06-2015 Through 12-06-2015",

}

RIS

TY - ABST

T1 - Assessing breast cancer masking risk in full field digital mammography with automated texture analysis

AU - Kallenberg, Michiel Gijsbertus J

AU - Lillholm, Martin

AU - Diao, Pengfei

AU - Holland, Katharina

AU - Karssemeijer, Nico

AU - Igel, Christian

AU - Nielsen, Mads

PY - 2015

Y1 - 2015

N2 - Purpose:The goal of this work is to develop a method to assess the risk of breast cancer masking, based on image characteristics beyond breast density.Method:From the Dutch breast cancer screening program we collected 285 screen detected cancers, and 109 cancers that were screen negative and subsequently appeared as interval cancers. To obtain mammograms without cancerous tissue, we took the contralateral mammograms. We developed a novel machine learning based method called convolutional sparse autoencoder to characterize mammographic texture. The method was trained and tested on raw mammograms to determine cancer detection status in a five-fold cross validation. To assess the interaction of the texture scores with breast density, Volpara Density Grade was determined for each image.Results:We grouped women into low (VDG 1/2) versus high (VDG 3/4) dense, and low (Quartile 1/2) versus high (Q 3/4) texture risk score. We computed odds ratios for breast cancer masking risk (i.e. interval versus screen detected cancer) for each of the subgroups. The odds ratio was 1.63 (1.04-2.53 95%CI) in the high dense group (as compared to the low dense group), whereas for the high texture score group (as compared to the low texture score group) this odds ratio was2.19 (1.37-3.49). Women who were classified as low dense but had a high texture score had a higher masking risk (OR 1.66 (0.53-5.20)) than women with dense breasts but a low texture score.Conclusion:Mammographic texture is associated with breast cancer masking risk. As such, automatic texture analysis offers opportunities to enhance personalized breast cancer screening. We were able to identify a subgroup of women who are at an increased risk of having a cancer that is not detected due to textural masking, even though their breasts are non-dense.

AB - Purpose:The goal of this work is to develop a method to assess the risk of breast cancer masking, based on image characteristics beyond breast density.Method:From the Dutch breast cancer screening program we collected 285 screen detected cancers, and 109 cancers that were screen negative and subsequently appeared as interval cancers. To obtain mammograms without cancerous tissue, we took the contralateral mammograms. We developed a novel machine learning based method called convolutional sparse autoencoder to characterize mammographic texture. The method was trained and tested on raw mammograms to determine cancer detection status in a five-fold cross validation. To assess the interaction of the texture scores with breast density, Volpara Density Grade was determined for each image.Results:We grouped women into low (VDG 1/2) versus high (VDG 3/4) dense, and low (Quartile 1/2) versus high (Q 3/4) texture risk score. We computed odds ratios for breast cancer masking risk (i.e. interval versus screen detected cancer) for each of the subgroups. The odds ratio was 1.63 (1.04-2.53 95%CI) in the high dense group (as compared to the low dense group), whereas for the high texture score group (as compared to the low texture score group) this odds ratio was2.19 (1.37-3.49). Women who were classified as low dense but had a high texture score had a higher masking risk (OR 1.66 (0.53-5.20)) than women with dense breasts but a low texture score.Conclusion:Mammographic texture is associated with breast cancer masking risk. As such, automatic texture analysis offers opportunities to enhance personalized breast cancer screening. We were able to identify a subgroup of women who are at an increased risk of having a cancer that is not detected due to textural masking, even though their breasts are non-dense.

M3 - Conference abstract in proceedings

SP - 109

BT - 7th International Workshop on Breast Densitometry and Cancer Risk Assessment (Non-CME)

PB - University of California

T2 - 7th International Workshop on Breast Densitometry and Cancer Risk Assessment, 2015

Y2 - 10 June 2015 through 12 June 2015

ER -

ID: 162988220