Abstract
In this paper, we present a work on breast density classification performed with deep residual neural network and we discuss the future analysis we could perform. Breast density is one of the most important breast cancer risk factor and it represents the amount of fibroglandular tissue with respect to fat tissue as seen on a mammographic exam. However, it is not easy to include it in risk models because of its variability among women and its qualitative definition. We trained a deep CNN to perform breast density classification in two ways. First, we classified mammograms using two “super-classes” that are dense and non-dense breast. Second, we trained the residual neural network to classify mammograms according to the four classes of the BI-RADS standard. We obtained very good results compared to our literature knowledge in terms of accuracy and recall. In the near future, we are going to improve the robustness of our algorithm with respect to the mammographic systems used and we want to include pathological exams too. Then we want to study and characterize the CNN-extracted features in order to identify the most significant for breast density. Finally, we want to study how to quantitatively measure the precision of the network in capturing the significative part of the images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alonzo-Proulx, O., Mawdsley, G.E., Patrie, J.T., Yaffe, M.J., Harvey, J.A.: Reliability of automated breast density measurements. Radiology 275(2), 366–376 (2015). https://doi.org/10.1148/radiol.15141686. http://pubs.rsna.org/doi/10.1148/radiol.15141686
Chollet, F.: Keras Documentation. https://keras.io/
Ciatto, S., et al.: Categorizing breast mammographicdensity: intra- and interobserver reproducibility of BI-RADS densitycategories. Breast 14(4), 269–275 (2005). https://doi.org/10.1016/j.breast.2004.12.004. http://linkinghub.elsevier.com/retrieve/pii/S0960977604002498
Dance, D.R., Christofides, S., McLean, I.D., Maidment, A.D.A., Ng, K.H.: Diagnostic Radiology Physics: A Handbook for Teachers and Students, 710 p. (2014)
Ekpo, E.U., Ujong, U.P., Mello-Thoms, C., McEntee, M.F.: Assessment of interradiologist agreement regarding mammographic breast density classification using the fifth edition of the BI-RADS atlas. Am. J. Roentgenol. 206(5), 1119–1123 (2016). https://doi.org/10.2214/AJR.15.15049. http://www.ajronline.org/doi/10.2214/AJR.15.15049
Fonseca, P., Castañeda, B., Valenzuela, R., Wainer, J.: Breast density classification with convolutional neural networks. In: Beltrán-Castañón, C., Nyström, I., Famili, F. (eds.) CIARP 2016. LNCS, vol. 10125, pp. 101–108. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-52277-7_13
He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition. arXiv:1512.03385 [cs], December 2015
International Agency for Research on Cancer (2018). http://gco.iarc.fr/today/home
Ioffe, S., Szegedy, C.: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv:1502.03167, February 2015
Krishnan, K., et al.: Longitudinal study of mammographic density measures that predict breast cancer risk. Cancer Epidemiol. Biomark. Prev. 26(4), 651–660 (2017). https://doi.org/10.1158/1055-9965.EPI-16-0499. http://cebp.aacrjournals.org/lookup/doi/10.1158/1055-9965.EPI-16-0499
Lizzi, F., et al.: Residual Convolutional Neural Networks for Breast Density Classification (2019). https://doi.org/10.5220/0007522202580263
Løberg, M., Lousdal, M.L., Bretthauer, M., Kalager, M.: Benefits and harms of mammography screening. Breast Cancer Res. 17(1) (2015). https://doi.org/10.1186/s13058-015-0525-z. http://breast-cancer-research.biomedcentral.com/articles/10.1186/s13058-015-0525-z
McCormack, V.A.: Breast density and parenchymal patterns as markers of breast cancer risk: a meta-analysis. Cancer Epidemiol. Biomark. Prev. 15(6), 1159–1169 (2006). https://doi.org/10.1158/1055-9965.EPI-06-0034. http://cebp.aacrjournals.org/cgi/doi/10.1158/1055-9965.EPI-06-0034
Miglioretti, D.L., et al.: Radiation-induced breast cancer incidence and mortality from digital mammography screening: a modeling study. Ann. Internal Med. 164(4), 205 (2016). https://doi.org/10.7326/M15-1241. http://annals.org/article.aspx?doi=10.7326/M15-1241
Sickles, E., D’Orsi, C., Bassett, L., et al.: ACR BI-RADS®. Atlas, Breast Imaging Reporting and Data System (2013)
Siegel, R.L., Miller, K.D., Jemal, A.: Cancer statistics, 2019: Cancer Statistics, 2019. CA: A Cancer J. Clin. 69(1), 7–34 (2019). https://doi.org/10.3322/caac.21551. http://doi.wiley.com/10.3322/caac.21551
Wu, N., et al.: Breast density classification with deep convolutional neural networks. arXiv:1711.03674 [cs, stat], November 2017
Acknowledgments
This work has been partially supported by the RADIOMA Project, funded by Fondazione Pisa, Technological and Scientific Research Sector, Via Pietro Toselli 29, Pisa.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Lizzi, F., Laruina, F., Oliva, P., Retico, A., Fantacci, M.E. (2019). Residual Convolutional Neural Networks to Automatically Extract Significant Breast Density Features. In: Vento, M., et al. Computer Analysis of Images and Patterns. CAIP 2019. Communications in Computer and Information Science, vol 1089. Springer, Cham. https://doi.org/10.1007/978-3-030-29930-9_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-29930-9_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-29929-3
Online ISBN: 978-3-030-29930-9
eBook Packages: Computer ScienceComputer Science (R0)