Breast Skin-Line Estimation and Breast Segmentation in Mammograms using Fast-Marching Method

Authors: Roshan Dharshana Yapa, Koichi Harada

Abstract:

Breast skin-line estimation and breast segmentation is an important pre-process in mammogram image processing and computer-aided diagnosis of breast cancer. Limiting the area to be processed into a specific target region in an image would increase the accuracy and efficiency of processing algorithms. In this paper we are presenting a new algorithm for estimating skin-line and breast segmentation using fast marching algorithm. Fast marching is a partial-differential equation based numerical technique to track evolution of interfaces. We have introduced some modifications to the traditional fast marching method, specifically to improve the accuracy of skin-line estimation and breast tissue segmentation. Proposed modifications ensure that the evolving front stops near the desired boundary. We have evaluated the performance of the algorithm by using 100 mammogram images taken from mini-MIAS database. The results obtained from the experimental evaluation indicate that this algorithm explains 98.6% of the ground truth breast region and accuracy of the segmentation is 99.1%. Also this algorithm is capable of partially-extracting nipple when it is available in the profile.

Keywords: Mammogram, fast marching method, mathematical morphology.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1074657

References:

[1] Kass M, Witkin A, Terzopoulos D., Snakes: Active Contour Models., Int. J. Computer Vision, 1987; 1(4), pp 321-31.
[2] Mclnemey T, Terzopoulos D., Deformable models in medical image analysis: a survey, Med. Img. Anal, 1996; 1(2), pp 91-108.
[3] R. Malladi, J. A. Sethian, and B.C. Vemuri, Shape modeling with front propagation: A level set approach, in IEEE Trns. On Pattern Analysis and Machine Intelligence, 1995; 17(2), pp 158-175.
[4] V. Caselles, R. Kimmel, and G. Sapiro, Geodisk Snakes, Proc. of ICCV, MIT Cambridge MA, 1995.
[5] J.A. Sethian, Level set methods and fast marching method: evolving interfaces in computational geometry, fluid mechanics, computer vision, and material science., Cambridge University Press, 1999.
[6] P.C. Johns, M.J. Yaffe, X-ray characterization of normal and neoplastic breast tissue, Phys. Med. Biol, 1987; 32, pp 675-695.
[7] The Mammographic Image Analysis Society, Digital Mammography Database ver 1.2, (http://www.wiau.man.ac.uk/services/MIAS/MIASweb.html).
[8] Wirth W., Nikitenko D., Lyon J., Segmentation of Breast Region in Mammograms using a Rule-Based Fuzzy Reasoning Algorithm. ICGSTGraphics, Vision and Image Processing Journal, 2005; 5(2); pp 45-54.
[9] Luc Vincent. Morphological Area Opening and Closing for Grayscale Images, Proc. NATO Shape in Picture Workshop, Driebergen, The Netherlands, Springer-Verlag, pp. 197-208, September 1992.
[10] Soille P., Morphological Image Analysis: Principles and Applications. Springer-Verlag. 2003.
[11] Wirth M.A., Lyon J., Nikitenko N., Stapinski A. Removing Radioopaque Artifacts from Mammograms using Area Morphology. In Proc. of SPIE Medical Imaging: Image Processing. pp 1054-1065. 2004.
[12] Salembier P., Serra J. Flat Zones Filtering, Connected Operators, and Filters by Reconstruction. IEEE Transaction on Image Processing, 4(8), pp 1153-1160. 1995.
[13] Hoyer A., Spiesberg W., Computerized mammogram processing. In: Phillips Technical Review. Vol. (38), pp 347-355, 1979.
[14] Lau T., Bischoff W., Automated Detection of Breast Tumours Using the Asymmetry Approach. In. Computers and Bio-Medical Research. Vol. (24), pp 273-295, 1991.
[15] Bick U., Giger M. L., Schmidt R.A., Nishikawa R.M., Wolverton D.E., Doi K., Automated Segmentation of Digitized Mammograms. Academic Rediology, Vol. 2(2), pp 1-9, 1995.
[16] Masek M., Attikiouzel Y., Skin-Air Interface Extraction from Mammograms Using an Automatic Local Thresholding Algorithm. In; ICB Brono CR, pp 204-206, 2000.
[17] Abdel-Mottaleb M., Carman C.S., Hill C.R., Vafai S., Locating the Boundary Between the Breast Skin Edge and the Background in Digitized Mammograms. In Porc. Of the 3rd International Workshop on Digital Mammography, pp 467-470, 1996.
[18] Mendez A.J., Tahoces P.J., Lado M.J., Souto M., Correa J.L., Vidal J.J., Automatic Detection of Breast Boarder and Nipple in Mammograms. Computer Methods and Programs in Bio-Medicine, 49, pp 253-262, 1996.
[19] Karssemeijer N., te Brake G., Combining Single View Features and Asymmetry for Detection of Mass Lesions. In IWDM, pp 1107-1108, 1998.
[20] Chandrasekhar R., Attikiouzel Y., Automatic Breast Boarder Segmentation by Background Modelling and Subtraction. In Proc. of the 5th International Workshop on Digital Mammography, pp 560-565, 2000.
[21] Wirth M.A., Stapinski A., Segmentation of the Breast Region in Mammograms using Active Contours. In Proc. of Visual Communication and Image Processing, 5510, pp 1995-2006, 2003.