Links & Downloads
Res. Biomed. Eng. 2017; 33
10.1590/2446-4740.07916 doi: http://dx.doi.org/10.1590/2446-4740.07916
Abstract:Introduction: Breast cancer is the first leading cause of death for women in Brazil as well as in most countries in the world. Due to the relation between the breast density and the risk of breast cancer, in medical practice, the breast density classification is merely visual and dependent on professional experience, making this task very subjective. The purpose of this paper is to investigate image features based on histograms and Haralick texture descriptors so as to separate mammographic images into categories of breast density using an Artificial Neural Network. Methods: We used 307 mammographic images from the INbreast digital database, extracting histogram features and texture descriptors of all mammograms and selecting them with the K-means technique. Then, these groups of selected features were used as inputs of an Artificial Neural Network to classify the images automatically into the four categories reported by radiologists. Results: An average accuracy of 92.9% was obtained in a few tests using only some of the Haralick texture descriptors. Also, the accuracy rate increased to 98.95% when texture descriptors were mixed with some features based on a histogram. Conclusion: Texture descriptors have proven to be better than gray levels features at differentiating the breast densities in mammographic images. From this paper, it was possible to automate the feature selection and the classification with acceptable error rates since the extraction of the features is suitable to the characteristics of the images involving the problem.
Keywords:Artificial neural networks, Breast density, BI-RADS™, CAD, Digital mammography, Feature selection.
Beale MH, Hagan MT, Demuth HB. Neural network toolbox: users guide. Natick: Mathworks; 2015.
D’Orsi C, Basset L, Feig S. Illustrated breast imaging reporting and data system American College of Radiology. Reston: American College of Radiology; 1998.
Gonzalez RC, Woods RE. Digital image processing. 3th ed. Upper Saddle River: Prentice Hall; 2007.
Haralick RM, Shanmugam K, Dinstein I. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics. 1973; SMC-3(6):610-21. http://dx.doi.org/10.1109/TSMC.1973.4309314.
Hartigan JA, Wong MA. Algorithm AS 136: a K-means clustering algorithm. Applied Statistics. 1979; 28(1):100-8. http://dx.doi.org/10.2307/2346830.
Haykin S. Neural networks: a comprehensive foundation. 2nd ed. Englewoods Cliffs: Prentice Hall; 2004.
Heine JJ, Scott CG, Sellers TA, Brandt KR, Serie DJ, Wu FF, Morton MJ, Schueler BA, Couch FJ, Olson JE, Pankratz VS, Vachon CM. A novel automated mammographic density measure and breast cancer risk. Journal of the National Cancer Institute. 2012; 104(13):1028-37. PMid:22761274. http://dx.doi.org/10.1093/jnci/djs254.
Horsthemke WH, Raicu DS. Organ analysis and classification using principal component and linear discriminant analysis. In: Pluim JPW, Reinhardt JM, editors. Medical Imaging: Proceedings of SPIE: International Society for Optics and Photonics; 2007 Mar 5; San Diego, US. Bellingham: SPIE; 2007. p. 65124A-11.
Instituto Nacional de Câncer. Estimativa 2016: Incidência de câncer no Brasil. Rio de Janeiro: INCA; 2016.
Islam MJ, Ahmadi M, Sid-Ahmed MA. An efficient automatic mass classification method in digitized mammograms using artificial neural network. Int J Artif Intell Appl. 2010; 1(3):1-13. http://dx.doi.org/10.5121/ijaia.2010.1301.
Kallenberg MGJ, Lokate M, van Gils CH, Karssemeijer N. Automatic breast density segmentation: an integration of different approaches. Physics in Medicine and Biology. 2011; 56(9):2715-29. PMid:21464531. http://dx.doi.org/10.1088/0031-9155/56/9/005.
Karssemeijer N. Automated classification of parenchymal patterns in mammograms. Physics in Medicine and Biology. 1998; 43(2):365-78. PMid:9509532. http://dx.doi.org/10.1088/0031-9155/43/2/011.
Keller BM, Nathan DL, Wang Y, Zheng Y, Gee JC, Conant EF, Kontos D. Estimation of breast percent density in raw and processed full field digital mammography images via adaptive fuzzy c-means clustering and support vector machine segmentation. Medical Physics. 2012; 39(8):4903-17. PMid:22894417. http://dx.doi.org/10.1118/1.4736530.
Kim Y, Hong BW, Kim SJ, Kim JH. A population-based tissue probability map-driven level set method for fully automated mammographic density estimations. Medical Physics. 2014; 41(7):71905. PMid:24989383. http://dx.doi.org/10.1118/1.4881525.
Kovács ZL. Redes neurais artificiais. 2nd ed. São Paulo: Acadêmica; 1996.
Llobet R, Pollán M, Antón J, Miranda-García J, Casals M, Martínez I, Ruiz-Perales F, Pérez-Gómez B, Salas-Trejo D, Pérez-Cortés JC. Semi-automated and fully automated mammographic density measurement and breast cancer risk prediction. Computer Methods and Programs in Biomedicine. 2014; 116(2):105-15. PMid:24636804. http://dx.doi.org/10.1016/j.cmpb.2014.01.021.
Manduca A, Carston MJ, Heine JJ, Scott CG, Pankratz VS, Brandt KR, Sellers TA, Vachon CM, Cerhan JR. Texture features from mammographic images and risk of breast cancer. Cancer Epidemiology, Biomarkers & Prevention. 2009; 18(3):837-45. PMid:19258482. http://dx.doi.org/10.1158/1055-9965.EPI-08-0631.
Mercado CL. BI-RADS Update. Radiologic Clinics of North America. 2014; 52(3):481-7. PMid:24792650. http://dx.doi.org/10.1016/j.rcl.2014.02.008.
Moreira IC, Amaral I, Domingues I, Cardoso A, Cardoso MJ, Cardoso JS. INbreast: toward a full-field digital mammographic database. Academic Radiology. 2012; 19(2):236-48. PMid:22078258. http://dx.doi.org/10.1016/j.acra.2011.09.014.
Mousa DS, Mello-Thoms C, Ryan EA, Lee WB, Pietrzyk MW, Reed WM, et al. Mammographic density and cancer detection: does digital imaging challenge our current understanding. Academic Radiology. 2014; 21(11):1377-85. PMid:25097013. http://dx.doi.org/10.1016/j.acra.2014.06.004.
Mustra M, Grgić M, Delač K. Breast density classification using multiple feature selection. Autom J Control Meas Electron Comput Commun. 2012; 53(4):362-72. http://dx.doi.org/10.7305/automatika.53-4.281.
Oliver A, Freixenet J, Marti R, Pont J, Perez E, Denton ERE, Zwiggelaar R. A novel breast tissue density classification methodology. IEEE Transactions on Information Technology in Biomedicine. 2008; 12(1):55-65. PMid:18270037. http://dx.doi.org/10.1109/TITB.2007.903514.
Oliver A, Freixenet J, Zwiggelaar R. Automatic classification of breast density. In: Image Processing: Proceedings of IEEE International Conference; 2005 Sept 11-14; Genova, Italy. USA: IEEE; 2005. p. II-1258. http://dx.doi.org/10.1109/ICIP.2005.1530291.
Oliver A, Lladó X, Pérez E, Pont J, Denton ERE, Freixenet J, Martí J. A statistical approach for breast density segmentation. Journal of Digital Imaging. 2010; 23(5):527-37. PMid:19506953. http://dx.doi.org/10.1007/s10278-009-9217-5.
Patterson DW. Artificial neural networks: theory and applications. 1st ed. Upper Saddle River: Prentice Hall; 1998.
Petroudi S, Kadir T, Brady M. Automatic classification of mammographic parenchymal patterns: a statistical approach. In: Engineering in Medicine and Biology Society: Proceedings of the 25th Annual International Conference of the IEEE; 2003 Sept 17-21; Cancún, Mexico. USA: IEEE; 2003. p. 798-801.
Pisano ED, Gatsonis C, Hendrick E, Yaffe M, Baum JK, Acharyya S, Conant EF, Fajardo LL, Bassett L, D’Orsi C, Jong R, Rebner M. Diagnostic performance of digital versus film mammography for breast-cancer screening. The New England Journal of Medicine. 2005; 353(17):1773-83. PMid:16169887. http://dx.doi.org/10.1056/NEJMoa052911.
Riascos A. Vertical mammaplasty for breast reduction. Aesthetic Plastic Surgery. 1999; 23(3):213-7. PMid:10384021. http://dx.doi.org/10.1007/s002669900270.
Rouhi R, Jafari M, Kasaei S, Keshavarzian P. Benign and malignant breast tumors classification based on region growing and CNN segmentation. Expert Systems with Applications. 2015; 42(3):990-1002. http://dx.doi.org/10.1016/j.eswa.2014.09.020.
Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature. 1988; 323(6088):533-8. http://dx.doi.org/10.1038/323533a0.
Senie RT, Lesser M, Kinne DW, Rosen PP. Method of tumor detection influences disease-free survival of women with breast carcinoma. Cancer. 1994; 73(6):1666-72. PMid:8156494. http://dx.doi.org/10.1002/1097-0142(19940315)73:6<1666::AID-CNCR2820730619>3.0.CO;2-E.
Siegel RL, Miller KD, Jemal A. Cancer statistics, 2017. CA: a Cancer Journal for Clinicians. 2017; 67(1):7-30. PMid:28055103. http://dx.doi.org/10.3322/caac.21387.
Tabár L, Tot T, Dean PB. Breast Cancer: the art and science of early detection with mammography: perception, interpretation, histopathologic correlation. Stuttgart: Thieme; 2005. p. 405-38.
Wang XH, Good WF, Chapman BE, Chang Y-H, Poller WR, Chang TS, Hardesty LA. Automated assessment of the composition of breast tissue revealed on tissue-thickness-corrected mammography. AJR. American Journal of Roentgenology. 2003; 180(1):257-62. PMid:12490516. http://dx.doi.org/10.2214/ajr.180.1.1800257.
Zhou C, Chan H-P, Petrick N, Helvie MA, Goodsitt MM, Sahiner B, Hadjiiski LM. Computerized image analysis: Estimation of breast density on mammograms. Medical Physics. 2001; 28(6):1056-69. PMid:11439475. http://dx.doi.org/10.1118/1.1376640.