{"references": ["Kass M, Witkin A, Terzopoulos D., Snakes: Active Contour Models.,\nInt. J. Computer Vision, 1987; 1(4), pp 321-31.", "Mclnemey T, Terzopoulos D., Deformable models in medical image\nanalysis: a survey, Med. Img. Anal, 1996; 1(2), pp 91-108.", "R. Malladi, J. A. Sethian, and B.C. Vemuri, Shape modeling with front\npropagation: A level set approach, in IEEE Trns. On Pattern Analysis\nand Machine Intelligence, 1995; 17(2), pp 158-175.", "V. Caselles, R. Kimmel, and G. Sapiro, Geodisk Snakes, Proc. of ICCV,\nMIT Cambridge MA, 1995.", "J.A. Sethian, Level set methods and fast marching method: evolving\ninterfaces in computational geometry, fluid mechanics, computer vision,\nand material science., Cambridge University Press, 1999.", "P.C. Johns, M.J. Yaffe, X-ray characterization of normal and neoplastic\nbreast tissue, Phys. Med. Biol, 1987; 32, pp 675-695.", "The Mammographic Image Analysis Society, Digital Mammography\nDatabase ver 1.2,\n(http://www.wiau.man.ac.uk/services/MIAS/MIASweb.html).", "Wirth W., Nikitenko D., Lyon J., Segmentation of Breast Region in\nMammograms using a Rule-Based Fuzzy Reasoning Algorithm. ICGSTGraphics,\nVision and Image Processing Journal, 2005; 5(2); pp 45-54.", "Luc Vincent. Morphological Area Opening and Closing for Grayscale\nImages, Proc. NATO Shape in Picture Workshop, Driebergen, The\nNetherlands, Springer-Verlag, pp. 197-208, September 1992.\n[10] Soille P., Morphological Image Analysis: Principles and Applications.\nSpringer-Verlag. 2003.\n[11] Wirth M.A., Lyon J., Nikitenko N., Stapinski A. Removing Radioopaque\nArtifacts from Mammograms using Area Morphology. In Proc. of SPIE\nMedical Imaging: Image Processing. pp 1054-1065. 2004.\n[12] Salembier P., Serra J. Flat Zones Filtering, Connected Operators, and\nFilters by Reconstruction. IEEE Transaction on Image Processing, 4(8),\npp 1153-1160. 1995.\n[13] Hoyer A., Spiesberg W., Computerized mammogram processing. In:\nPhillips Technical Review. Vol. (38), pp 347-355, 1979.\n[14] Lau T., Bischoff W., Automated Detection of Breast Tumours Using the\nAsymmetry Approach. In. Computers and Bio-Medical Research. Vol.\n(24), pp 273-295, 1991.\n[15] Bick U., Giger M. L., Schmidt R.A., Nishikawa R.M., Wolverton D.E.,\nDoi K., Automated Segmentation of Digitized Mammograms. Academic\nRediology, Vol. 2(2), pp 1-9, 1995.\n[16] Masek M., Attikiouzel Y., Skin-Air Interface Extraction from\nMammograms Using an Automatic Local Thresholding Algorithm. In;\nICB Brono CR, pp 204-206, 2000.\n[17] Abdel-Mottaleb M., Carman C.S., Hill C.R., Vafai S., Locating the\nBoundary Between the Breast Skin Edge and the Background in\nDigitized Mammograms. In Porc. Of the 3rd International Workshop on\nDigital Mammography, pp 467-470, 1996.\n[18] Mendez A.J., Tahoces P.J., Lado M.J., Souto M., Correa J.L., Vidal J.J.,\nAutomatic Detection of Breast Boarder and Nipple in Mammograms.\nComputer Methods and Programs in Bio-Medicine, 49, pp 253-262,\n1996.\n[19] Karssemeijer N., te Brake G., Combining Single View Features and\nAsymmetry for Detection of Mass Lesions. In IWDM, pp 1107-1108,\n1998.\n[20] Chandrasekhar R., Attikiouzel Y., Automatic Breast Boarder\nSegmentation by Background Modelling and Subtraction. In Proc. of the\n5th International Workshop on Digital Mammography, pp 560-565, 2000.\n[21] Wirth M.A., Stapinski A., Segmentation of the Breast Region in\nMammograms using Active Contours. In Proc. of Visual Communication\nand Image Processing, 5510, pp 1995-2006, 2003."]}

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.