Advertisement

Automatic pectoral muscle removal in mammograms

  • Samuel RahimetoEmail author
  • Taye Girma Debelee
  • Dereje Yohannes
  • Friedhelm Schwenker
Original Paper
  • 2 Downloads

Abstract

The pectoral muscle is the high-intensity region in most mediolateral oblique (MLO) views of mammograms. Since it appears at the same intensity as most abnormalities it should be removed for successful classification. Removal of pectoral muscle is often a challenging task since its position, size and shape are different for different patients and it may not occur at all. In this paper, an efficient technique for the detection and removal of pectoral muscle is proposed. The algorithm is tested and proved efficient over a wide range of pectoral muscle types and datasets based on IOU and RMSE value.

Keywords

Pectoral muscle Thresholding Morphological operations RMSE IOU 

Notes

References

  1. Abeje S, Seme A, Tiblet A (2019) Factors associated with breast cancer screening awareness and practices of women in addis ababa, ethiopia. BMC Women’s Health 19(4):1–8Google Scholar
  2. Angelov P, Sadeghi-Tehran P, Ramezani R (2010) An approach to automatic real-time novelty detection, object identification, and tracking in video streams based on recursive density estimation and evolving takagi-sugeno fuzzy systems. Int J Intell Syst 26(3):189–205CrossRefGoogle Scholar
  3. Arafa A, El-Sokary N, Asad A, Hefny H (2019) Computer-aided detection system for breast cancer based on GMM and SVM. Arab J Nucl Sci Appl 52(2):142–150Google Scholar
  4. Boss RSC, Thangavel K, Daniel D, Arul P (2013) Automatic mammogram image breast region extraction and removal of pectoral muscle. Int J Sci Eng Res 4(5):1–8Google Scholar
  5. Charate AP, Jamge SB (2017) The preprocessing methods of mammogram images for breast cancer detection. Int J Recent Innov Trends Comput Commun 5(1):261–264Google Scholar
  6. Chen C, Liu G, Sudlow G, Wang J (2014) Shape-based automatic detection of pectoral muscle boundary in mammograms. J Med Biol Eng 5:315–322Google Scholar
  7. Sissons C (2018) What does breast cancer look like on a mammogram? In: Medical news today. https://www.medicalnewstoday.com/articles/322068.php. Accessed 10 Feb 2019
  8. Debelee TG, Amirian M, Ibenthal A, Palm G, Schwenker F (2018) Classification of mammograms using convolutional neural network based feature extraction. LNICST 244:89–98Google Scholar
  9. Debelee TG, Gebreselasie A, Schwenker F, Amirian M, Yohannes D (2019) Classification of mammograms using texture and cnn based extracted features. J Biom Biomater Biomed Eng 42:79–97Google Scholar
  10. Debelee TG, Schwenker F, Rahimeto S, Yohannes D (2019) Evaluation of modified adaptive k-means segmentation algorithm. Comput Vis Media.  https://doi.org/10.1007/s41095-019-0151-2 CrossRefGoogle Scholar
  11. Makandar A, Halalli B (2016) Pre-processing of mammography image for early detection of breast cancer. Int J Comput Appl 144(3):11–15Google Scholar
  12. Mughal B, Muhammad N, Sharif M, Rehman A, Saba T (2018)  Removal of pectoral muscle based on topographic map and shape-shifting silhouette. BMC Cancer 18:1–14.  https://doi.org/10.1186/s12885-018-4638-5 CrossRefGoogle Scholar
  13. Sargana AB, Angelov P, Habib Z (2017) A comprehensive review on handcrafted and learning-based action representation approaches for human activity recognition. Appl Sci 7:110 (01)CrossRefGoogle Scholar
  14. Sheba KU, Raj Gladston S (2018) An approach for automatic lesion detection in mammograms. Cogent Eng 5(1444320):1–16Google Scholar
  15. Slavkovic-Ilic M, Gavrovska A, Milivojevic M et al (2016) Breast region segmentation and pectoral muscle removal in mammograms. Telfor Journal 8:50–55.  https://doi.org/10.5937/telfor1601050s CrossRefGoogle Scholar
  16. Toshpulatov Z, Bria A (2018) Pectoral-Muscle-Segmentation-using-Watershed-algorithm. In: GitHub. https://github.com/zafaruzmedtec/Pectoral-Muscle-Segmentation-using-Watershed-algorithm. Accessed 16 Mar 2019
  17. Vaidehi K, Subashini TS (2013) Automatic identification and elimination of pectoral muscle in digital mammograms. Int J Comput Appl 75(14):15–18Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.College of Electrical and Mechanical EngineeringAddis Ababa Science and Technology UniversityAddis AbabaEthiopia
  2. 2.Institute of Neural Information ProcessingUniversity of UlmUlmGermany
  3. 3.Department of Computer EngineeringAddis Ababa Science and Technology UniversityAddis AbabaEthiopia

Personalised recommendations