ABSTRACT
Mammographic breast density is an early indicator of a patient's risk for breast cancer development. Although the direct cause is not fully understood, increased mammographic breast density increases the chance of developing breast cancer. Based on the density pattern exhibited, a patient's breast density score is assigned by a radiologist using one of four categories outlined by the Breast Imaging Reporting and Data Systems (BI-RADS). The subjective nature of pattern-based assessment of patient breast density can result in increased intra- and inter-rater variability. The identification of objective quantitative scoring systems for breast density lends the opportunity to provide patients and radiologists with increased granularity and precision over the four subjective BI-RADS classes. We propose a quantitative breast-density approach using semantic segmentation to assign each of a patient's breasts with a density value. Using the values for each breast, a patient-level density value can be used to determine the patient's placement on a linear density scale along with the probability that the patient belongs to each of the BI-RADS breast-density classes. We use accuracy and kappa scores to determine the performance of the algorithm with BI-RADS classification. Results show comparative classification and performance can be achieved between our semantic segmentation methodology and previous work which implemented a Vision Transformer (ViT)-based breast-density classification algorithm.
- [n. d.]. ACR statement on reporting breast density in mammography reports and patient summaries. https://www.acr.org/Advocacy-and-Economics/ACR-Position-Statements/Reporting-Breast-Density. Accessed: 2022-11-10.Google Scholar
- [n. d.]. DenseBreast-info, Inc. Legislative information. https://densebreast-info.org/legislative-information Accessed: 2023-1-2.Google Scholar
- [n. d.]. Densitas. https://densitashealth.ca/solutions/density/ Accessed: 2023-1-5.Google Scholar
- [n. d.]. PowerLook Density Assessment. https://www.icadmed.com/powerlook-density-assessment.html Accessed: 2023-1-5.Google Scholar
- [n. d.]. Synthesized 2D Mammographic Imaging Theory and Clinical Performance. https://www.hologic.com/sites/default/files/C-View%20White%20Paper%2C%20Dr.%20Andrew%20Smith.pdf Accessed: 2023-1-5.Google Scholar
- LW Bassett, IA Hirbawi, N DeBruhl, and MK Hayes. 1993. Mammographic positioning: evaluation from the view box. Radiology 188, 3 (1993), 803--806.Google ScholarCross Ref
- J W Byng, N F Boyd, E Fishell, R A Jong, and M J Yaffe. 1994. The quantitative analysis of mammographic densities. Phys. Med. Biol. 39, 10 (Oct. 1994), 1629--1638.Google ScholarCross Ref
- Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. 2017. Rethinking Atrous Convolution for Semantic Image Segmentation. Google ScholarCross Ref
- Stefano Ciatto, Daniela Bernardi, Massimo Calabrese, Manuela Durando, Maria Adalgisa Gentilini, Giovanna Mariscotti, Francesco Monetti, Enrica Moriconi, Barbara Pesce, Antonella Roselli, Carmen Stevanin, Margherita Tapparelli, and Nehmat Houssami. 2012. A first evaluation of breast radiological density assessment by QUANTRA software as compared to visual classification. Breast 21, 4 (Aug. 2012), 503--506.Google ScholarCross Ref
- Lee R Dice. 1945. Measures of the amount of ecologic association between species. Ecology 26, 3 (July 1945), 297--302.Google ScholarCross Ref
- C D'orsi, E A Sickles, E B Mendelson, and E A Morris. 2013. Breast Imaging Reporting and Data System: ACR BI-RADS breast imaging atlas. American College of Radiology, Reston, Va.Google Scholar
- Carl D'Orsi, L Bassett, S Feig, et al. 2018. Breast imaging reporting and data system (BI-RADS). Breast imaging atlas, 4th edn. American College of Radiology, Reston (2018).Google Scholar
- Mikael Eriksson, Kamila Czene, Yudi Pawitan, Karin Leifland, Hatef Darabi, and Per Hall. 2017. A clinical model for identifying the short-term risk of breast cancer. Breast Cancer Res. 19, 1 (Dec. 2017).Google ScholarCross Ref
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep Residual Learning for Image Recognition. Google ScholarCross Ref
- Lewis I Held, Jr. 2009. SYMMETRY AND ASYMMETRY. In Quirks of Human Anatomy. Cambridge University Press, Cambridge, 17--32.Google Scholar
- Itseez. 2015. Open Source Computer Vision Library. https://github.com/itseez/opencv.Google Scholar
- Davood Karimi, Haoran Dou, Simon K Warfield, and Ali Gholipour. 2020. Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis. Med. Image Anal. 65, 101759 (Oct. 2020), 101759.Google ScholarCross Ref
- Brad M Keller, Jinbo Chen, Dania Daye, Emily F Conant, and Despina Kontos. 2015. Preliminary evaluation of the publicly available Laboratory for Breast Radiodensity Assessment (LIBRA) software tool: comparison of fully automated area and volumetric density measures in a case-control study with digital mammography. Breast Cancer Res. 17, 1 (Dec. 2015).Google ScholarCross Ref
- Jingmei Li, Laszlo Szekely, Louise Eriksson, Boel Heddson, Ann Sundbom, Kamila Czene, Per Hall, and Keith Humphreys. 2012. High-throughput mammographic-density measurement: a tool for risk prediction of breast cancer. Breast Cancer Res. 14, 4 (Aug. 2012).Google ScholarCross Ref
- Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. In Computer Vision - ECCV 2014, David Fleet, Tomas Pajdla, Bernt Schiele, and Tinne Tuytelaars (Eds.). Springer International Publishing, Cham, 740--755.Google ScholarCross Ref
- Chen-Chung Liu, Chung-Yen Tsai, Jui Liu, Chun-Yuan Yu, and Shyr-Shen Yu. 2012. A pectoral muscle segmentation algorithm for digital mammograms using Otsu thresholding and multiple regression analysis. Computers and Mathematics with Applications 64, 5 (2012), 1100--1107. Advanced Technologies in Computer, Consumer and Control. Google ScholarDigital Library
- Ann B Nattinger and Julie L Mitchell. 2016. Breast cancer screening and prevention. Ann. Intern. Med. 164, 11 (June 2016), ITC81.Google ScholarCross Ref
- Kwan-Hoong Ng, Cheng-Har Yip, and Nur Aishah Mohd Taib. 2012. Standardisation of clinical breast-density measurement. Lancet Oncol. 13, 4 (April 2012), 334--336.Google ScholarCross Ref
- Arnau Oliver, Meritxell Tortajada, Xavier Lladó, Jordi Freixenet, Sergi Ganau, Lidia Tortajada, Mariona Vilagran, Melcior Sentís, and Robert Martí. 2015. Breast density analysis using an automatic density segmentation algorithm. J. Digit. Imaging 28, 5 (Oct. 2015), 604--612.Google ScholarCross Ref
- E A Ooms, H M Zonderland, M J C Eijkemans, M Kriege, B Mahdavian Delavary, C W Burger, and A C Ansink. 2007. Mammography: Interobserver variability in breast density assessment. Breast 16, 6 (Dec. 2007), 568--576.Google ScholarCross Ref
- Shivaji Pawar, Suhas Sapate, and Kamal Sharma. 2020. Machine learning approach towards mammographic breast density measurement for breast cancer risk prediction: An overview. SSRN Electron. J. (2020).Google Scholar
- Payam Refaeilzadeh, Lei Tang, and Huan Liu. 2009. Cross-Validation. Encyclopedia of Database Systems 532--538 (01 2009), 532--538. Google ScholarCross Ref
- Conrad Testagrose, Vikash Gupta, Barbaros S. Erdal, Richard D. White, Robert W. Maxwell, Xudong Liu, Indika Kahanda, Sherif Elfayoumy, William Klostermeyer, and Mutlu Demirer. 2022. Impact of Concatenation of Digital Craniocaudal Mammography Images on a Deep-Learning Breast-Density Classifier Using Inception-V3 and ViT. In 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 3399--3406. Google ScholarCross Ref
- Mohammad Usman, Tehseen Zia, and Ali Tariq. 2022. Analyzing transfer learning of vision transformers for interpreting chest radiography. J. Digit. Imaging (July 2022).Google Scholar
- C H van Gils, J D Otten, A L Verbeek, and J H Hendriks. 1998. Mammographic breast density and risk of breast cancer: masking bias or causality? Eur. J. Epidemiol. 14, 4 (June 1998), 315--320.Google ScholarCross Ref
- John N. Wolfe. 1976. Risk for breast cancer development determined by mammographic parenchymal pattern. Cancer 37, 5 (1976), 2486--2492. <2486::AID-CNCR2820370542>3.0.CO;2-8 Google ScholarCross Ref
Index Terms
- Breast-Density Semantic Segmentation with Probability Scaling for BI-RADS Assessment using DeepLabV3
Recommendations
Breast Density Assessment Using Breast Tomosynthesis Images
IWDM 2016: Proceedings of the 13th International Workshop on Breast Imaging - Volume 9699In this work we evaluate an approach for breast density assessment of digital breast tomosynthesis DBT data using the central projection image. A total of 348 random cases both FFDM CC and MLO views and DBT MLO views were collected using a Siemens ...
Do Women with Low Breast Density Have Regionally High Breast Density?
IWDM 2016: Proceedings of the 13th International Workshop on Breast Imaging - Volume 9699Average volumetric breast density has been found to be associated with interval cancers. The association is believed to be partly due to mammographic masking. We asked if regional density may be a more sensitive descriptor of masking than average ...
Mammographic Density Over Time in Women With and Without Breast Cancer
IWDM 2016: Proceedings of the 13th International Workshop on Breast Imaging - Volume 9699This study compared mammographic density over time between women who developed breast cancer cases and women who did not controls. Cases had an initial negative mammographic screen and another three years later when cancer was diagnosed. Cases were ...
Comments