Automated texture scoring for assessing breast cancer masking risk in full field digital mammography

Publikation: Bidrag til tidsskriftKonferenceabstrakt i tidsskriftForskningfagfællebedømt

Standard

Automated texture scoring for assessing breast cancer masking risk in full field digital mammography. / Kallenberg, Michiel Gijsbertus J; Petersen, Peter Kersten; Lillholm, Martin; Jørgensen, Dan Richter; Diao, Pengfei; Holland, Katharina; Karssemeijer, Nico; Igel, Christian; Nielsen, Mads.

I: Insights into Imaging, Bind 6, Nr. 1, Supplement, B-0212, 2015.

Publikation: Bidrag til tidsskriftKonferenceabstrakt i tidsskriftForskningfagfællebedømt

Harvard

Kallenberg, MGJ, Petersen, PK, Lillholm, M, Jørgensen, DR, Diao, P, Holland, K, Karssemeijer, N, Igel, C & Nielsen, M 2015, 'Automated texture scoring for assessing breast cancer masking risk in full field digital mammography', Insights into Imaging, bind 6, nr. 1, Supplement, B-0212. https://doi.org/10.1007/s13244-015-0387-z

APA

Kallenberg, M. G. J., Petersen, P. K., Lillholm, M., Jørgensen, D. R., Diao, P., Holland, K., ... Nielsen, M. (2015). Automated texture scoring for assessing breast cancer masking risk in full field digital mammography. Insights into Imaging, 6(1, Supplement), [B-0212]. https://doi.org/10.1007/s13244-015-0387-z

Vancouver

Kallenberg MGJ, Petersen PK, Lillholm M, Jørgensen DR, Diao P, Holland K o.a. Automated texture scoring for assessing breast cancer masking risk in full field digital mammography. Insights into Imaging. 2015;6(1, Supplement). B-0212. https://doi.org/10.1007/s13244-015-0387-z

Author

Kallenberg, Michiel Gijsbertus J ; Petersen, Peter Kersten ; Lillholm, Martin ; Jørgensen, Dan Richter ; Diao, Pengfei ; Holland, Katharina ; Karssemeijer, Nico ; Igel, Christian ; Nielsen, Mads. / Automated texture scoring for assessing breast cancer masking risk in full field digital mammography. I: Insights into Imaging. 2015 ; Bind 6, Nr. 1, Supplement.

Bibtex

@article{5cfc4d54b9b24553b860f85ff5ef9915,
title = "Automated texture scoring for assessing breast cancer masking risk in full field digital mammography",
abstract = "PURPOSE: The goal of this work is to develop a method to identify women at high risk for having breast cancer that is easily missed in regular mammography screening. Such a method will provide a rationale for selecting women for adjunctive screening. It goes beyond current risk assessment models that are not specifically adapted to reduce the number of interval cancers. METHOD AND MATERIALS: From the Dutch breast cancer screening program we collected 109 cancers that were screen negative and subsequently appeared as interval cancers, and 327 age matched healthy controls. To obtain mammograms without signs of cancerous tissue, we took the contralateral mammograms. We developed a novel machine learning based method called convolutional sparse autoencoder (CSAE) to characterize mammographic texture. The CSAE was trained and tested on raw mammograms to separate interval cancers from controls in a five-fold cross validation. To assess the independency of the texture scores of breast density, density was determined for each image using Volpara. RESULTS: The odds ratios for interval cancer were 1.59 (95{\%}CI: 0.76-3.32), 2.07 (1.02-4.20), and 3.14 (1.60-6.17) for quartile 2, 3 and 4 respectively, relative to quartile 1. Correlation between the texture scores and breast density was 0.59 (0.52-0.64). Breast density adjusted odds ratios, as determined with logistic regression, were 1.49 (0.71-3.13), 1.58 (0.75-3.33), and 1.97 (0.91-4.27). CONCLUSIONS: The CSAE texture score is independently associated with the risk of having a breast cancer that is missed in regular mammography screening. As such it offers opportunities to further enhance personalized breast cancer screening.",
author = "Kallenberg, {Michiel Gijsbertus J} and Petersen, {Peter Kersten} and Martin Lillholm and J{\o}rgensen, {Dan Richter} and Pengfei Diao and Katharina Holland and Nico Karssemeijer and Christian Igel and Mads Nielsen",
year = "2015",
doi = "10.1007/s13244-015-0387-z",
language = "English",
volume = "6",
journal = "Insights into Imaging",
issn = "1869-4101",
publisher = "SpringerOpen",
number = "1, Supplement",
note = "ECR 2015 - European Congress of Radiology, ECR 2015 ; Conference date: 04-03-2015 Through 08-03-2015",

}

RIS

TY - ABST

T1 - Automated texture scoring for assessing breast cancer masking risk in full field digital mammography

AU - Kallenberg, Michiel Gijsbertus J

AU - Petersen, Peter Kersten

AU - Lillholm, Martin

AU - Jørgensen, Dan Richter

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 identify women at high risk for having breast cancer that is easily missed in regular mammography screening. Such a method will provide a rationale for selecting women for adjunctive screening. It goes beyond current risk assessment models that are not specifically adapted to reduce the number of interval cancers. METHOD AND MATERIALS: From the Dutch breast cancer screening program we collected 109 cancers that were screen negative and subsequently appeared as interval cancers, and 327 age matched healthy controls. To obtain mammograms without signs of cancerous tissue, we took the contralateral mammograms. We developed a novel machine learning based method called convolutional sparse autoencoder (CSAE) to characterize mammographic texture. The CSAE was trained and tested on raw mammograms to separate interval cancers from controls in a five-fold cross validation. To assess the independency of the texture scores of breast density, density was determined for each image using Volpara. RESULTS: The odds ratios for interval cancer were 1.59 (95%CI: 0.76-3.32), 2.07 (1.02-4.20), and 3.14 (1.60-6.17) for quartile 2, 3 and 4 respectively, relative to quartile 1. Correlation between the texture scores and breast density was 0.59 (0.52-0.64). Breast density adjusted odds ratios, as determined with logistic regression, were 1.49 (0.71-3.13), 1.58 (0.75-3.33), and 1.97 (0.91-4.27). CONCLUSIONS: The CSAE texture score is independently associated with the risk of having a breast cancer that is missed in regular mammography screening. As such it offers opportunities to further enhance personalized breast cancer screening.

AB - PURPOSE: The goal of this work is to develop a method to identify women at high risk for having breast cancer that is easily missed in regular mammography screening. Such a method will provide a rationale for selecting women for adjunctive screening. It goes beyond current risk assessment models that are not specifically adapted to reduce the number of interval cancers. METHOD AND MATERIALS: From the Dutch breast cancer screening program we collected 109 cancers that were screen negative and subsequently appeared as interval cancers, and 327 age matched healthy controls. To obtain mammograms without signs of cancerous tissue, we took the contralateral mammograms. We developed a novel machine learning based method called convolutional sparse autoencoder (CSAE) to characterize mammographic texture. The CSAE was trained and tested on raw mammograms to separate interval cancers from controls in a five-fold cross validation. To assess the independency of the texture scores of breast density, density was determined for each image using Volpara. RESULTS: The odds ratios for interval cancer were 1.59 (95%CI: 0.76-3.32), 2.07 (1.02-4.20), and 3.14 (1.60-6.17) for quartile 2, 3 and 4 respectively, relative to quartile 1. Correlation between the texture scores and breast density was 0.59 (0.52-0.64). Breast density adjusted odds ratios, as determined with logistic regression, were 1.49 (0.71-3.13), 1.58 (0.75-3.33), and 1.97 (0.91-4.27). CONCLUSIONS: The CSAE texture score is independently associated with the risk of having a breast cancer that is missed in regular mammography screening. As such it offers opportunities to further enhance personalized breast cancer screening.

U2 - 10.1007/s13244-015-0387-z

DO - 10.1007/s13244-015-0387-z

M3 - Conference abstract in journal

C2 - 25708994

VL - 6

JO - Insights into Imaging

JF - Insights into Imaging

SN - 1869-4101

IS - 1, Supplement

M1 - B-0212

T2 - ECR 2015 - European Congress of Radiology

Y2 - 4 March 2015 through 8 March 2015

ER -

ID: 168600399