Automatic Segmentation and Classification of Masses from Digital Mammograms

  • Basma A. Mohamed Faculty of Engineering, Biomedical Engineering Department, Helwan University, Cairo, Egypt
  • Nancy M Salem Faculty of Engineering, Biomedical Engineering Department, Helwan University, Cairo, Egypt
  • Marwa M Hadhoud Faculty of Engineering, Biomedical Engineering Department, Helwan University, Cairo, Egypt
  • Ahmed F Seddik Faculty of Computer Science, Nahda University (NUB)
Keywords: Breast Cancer, Digital Mammograms, Otsuís threshold, BI-RADSô Categories.


Breast cancer is one of the leading causes of death among female cancer patients. Mammography is the most efficient method for the early detection of abnormalities that are associated with breast cancer. Masses and microcalcifications are the most popular abnormalities that indicate breast cancer. The proposed paper intends to develop an automated system for assisting the analysis of digital mammograms. First, a preprocessing step is applied to enhance images followed by a segmentation step that is based on morphological operations and Otsus thresholding techniques. Thereafter, shape features are extracted from the segmented region and used in the classification process. Finally, the classification step to classify the segmented shape as round, oval, lobular, or irregular. The algorithm is tested using 270 mammogram images from the Women Health Care Program (WHC) and 142 publicly available images from the Digital Database for Screening Mammography (DDSM). Results show that the proposed technique effectively detects and segments masses from mammogram images. The shape of segmented masses is classified into either round, oval, lobular, or irregular. Round and oval shapes are classified with 100% accuracy while lobular and irregular shapes results in accuracy of 93% using the ANN for the WHC dataset. On the other hand, accuracy for images from the DDSM is 100% and 91.3% respectively.


(1) Breast Cancer Foundation of Egypt (BCFE),, 2014.

(2) Verma, B., P. McLeod, and A. Klevansky, A novel soft cluster neural network for the classification of suspicious areas in digital mammograms, Pattern Recognition, 2009. 42 (9): p. 1845-1852.

(3) Heath, M., et al., The digital database for screening mammography, Proceedings of the International Workshop on Digital Mammography 2000. p. 212-218.

(4) ACR, Breast imaging reporting and data system (BI-RADS), Breast Imaging Atlas, 4th ed., American College of Radiology, Reston, VA, 2010.

(6) Tzikopoulosa, S., et al., A fully automated scheme for mammographic segmentation and classification based on breast density and asymmetry, Computers Methods and Programs in Biomedicine, 2011. (102): p. 47-63.

(8) Nunes, A., A. Silva, and A. Paiva, Detection of masses in mammographic images using geometry, Simpson's Diversity Index and SVM, Journal of Signal and Imaging Systems Engineering, 2010. 3(1): p. 43-51.

(9) Retico, A., et al., An automatic system to discriminate malignant from benign massive lesions on mammograms, Nuclear Instrumentation and Methods in Physics Research, 2006. 569(2): p. 596-600.

(10) B. Surendiran and A. Vadivel, Classifying mammographic masses into BI-RADSTM shape categories using various geometric and shape features, International Journal of Biomedical Signal Processing, 2011. 2(1): p. 43-47.

(11) Vadivel, A., and B. Surendiran, A fuzzy rule-based approach for characterization of mammogram masses into BI-RADS shape categories, Computers in Biology and Medicine, 2013. 43: p. 259-267.

(12) Costa, D., et al., Independent component analysis in breast tissues mammograms images classification using LDA and SVM, Information technology Application in Biomedicine, 2007. p. 231-234.

(13) De Nazar Silva, J., et al., Automatic detection of masses in mammograms using quality threshold clustering, correlogram function, and SVM, Journal of Digital Imaging, 2015. 28 (3): p. 323-373.

(14) Women Health Care Program,, 2007.

(15) Heath, M., K. Bowyer, and D. Kopans, Current status of the digital database for screening mammography, Digital Mammography, Kluwer Academic Publishers: p. 457-460.

(16) Otsu, N., A threshold selection method from gray-level histograms, Systems, Man, and Cybernetics, IEEE Transactions on, 1979. 9(1): p. 62-66.

(17) Gonzalez, R., R. Woods, and S. Eddins, Digital image processing using MATLAB, Gatesmark Publishing; 2nd edition, 2009.

(18) Schalkoff, R., Artificial neural networks. McGraw Hill, Publishers,

p. 146-118.

Altman, N. S., An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician, 1992. 46(3): p. 175-185.

How to Cite
Mohamed, B. A., Salem, N. M., Hadhoud, M. M., & Seddik, A. F. (2016). Automatic Segmentation and Classification of Masses from Digital Mammograms. European Journal of Applied Sciences, 4(4), 17.