Breast Lesion Segmentation Method Using Ultrasound Images
Breast cancer is one of the leading causes of death among women. A non-invasive ultrasound examination enables the location and type of lesion. The radiologist, based on the 2D ultrasound image, estimates the volume of the lesion and performs a core needle biopsy procedure. The lesion segmentation may support the diagnostic and therapeutic process. The purpose of this study is to develop a method of breast tumor segmentation using two-dimensional ultrasound images. The lesion mask is based on the fusion of several methods. The proposed method employs active contour models, gradient vector flow, region growing, thresholding, image gradient, watershed transform and morphological operations. The effectiveness of the method was checked with Dice, Jaccard and specificity coefficients. Median values were 0.915, 0.862 and 0.996, respectively.
KeywordsBreast ultrasound Breast lesion Ultrasound image segmentation Image processing
This research was partially supported by the Polish National Centre for Research and Development (NCBR), grant no. STRATEGMED2 /267398/3/NCBR/2015.
The authors would also like to thank Andre Woloshuk for his English language corrections.
- 1.Ferlay, J., Hery, C., Autier, P., Sankaranarayanan, R.: Global burden of breast cancer. In: Breast Cancer Epidemiology, pp. 1–19 (2010)Google Scholar
- 4.Lee, L.K., Liew, S.C.: Breast ultrasound automated ROI segmentation with region growing. In: 2015 4th International Conference on Software Engineering and Computer Systems (ICSECS), pp. 177–182 (2015)Google Scholar
- 5.Galinska, M., Ogieglo, W., Wijata, A., Juszczyk, J., Czajkowska, J.: Breast cancer segmentation method in ultrasound images. In: Gzik, M., Tkacz, E., Paszenda, Z., Piętka, E. (eds.) Innovations in Biomedical Engineering, IBE 2017, Advances in Intelligent Systems and Computing, vol. 623, pp. 23–31 (2017)Google Scholar
- 6.Wieclawek, W., Rudzki, M., Wijata, A., Galinska, M.: Preliminary development of an automatic breast tumour segmentation algorithm from ultrasound volumetric images. In: Proceedings 6th International Conference Information Technology in Biomedicine, pp. 77–88 (2018)Google Scholar
- 11.Minavathi, Murali, S., Dinesh, M.S.: Classification of mass in breast ultrasound images using image processing techniques. Int. J. Comput. Appl. 42(10), 29–36 (2012)Google Scholar
- 13.Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: Computer Vision and Pattern Recognition, pp. 60–65 (2005)Google Scholar
- 15.Xu, C., Prince, J.: Gradient vector flow: a new external force for snakes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 66–71 (1997)Google Scholar