Abstract
In this paper, we propose four variants of the Markov random field model by using constrained clustering for breast mass segmentation. These variants were tested with a set of images extracted from a public database. The obtained results have shown that the proposed variants, which allow to include additional information in the form of constraints to the clustering process, present better visual segmentation results than the original model, as well as a lower final energy which implies a better quality in the final segmentation. Specifically, the centroid initialization method used by our variants allows us to locate about 90% of the regions of interest that contain a mass, which subsequently with the pairwise constraints helped us recover a maximum of 93% of the masses. The segmentation results are also quantitatively evaluated using three supervised segmentation measures. These measures show that the mass segmentation quality of the proposed variants, considering the breast density level, is consistent with the corresponding segmentation annotated by specialized radiologists.
Similar content being viewed by others
Notes
This database is available at https://bcdr.eu/
References
Abbas Q., Celebi M E, Garcia I F (2013) Breast mass segmentation using region-based and edge-based methods in a 4-stage multiscale system. Biomed Signal Process Control 8(2):204–214
Ahmed M N, Yamany S M, Mohamed N, Farag A A, Moriarty T (2002) A modified fuzzy C-means algorithm for bias field estimation and segmentation of mri data. IEEE Trans Med Imaging 21(3):193–199. https://doi.org/10.1109/42.996338
Barker S A, Rayner P J (2000) Unsupervised image segmentation using Markov random field models. Pattern Recognit 33(4):587–602. https://doi.org/10.1016/S0031-3203(99)00074-6
Basu S, Banerjee A, Mooney R J (2004) Active semi-supervision for pairwise constrained clustering. In: Proceedings of the 2004 SIAM international conference on data mining, pp 333–344
Basu S, Bilenko M, Banerjee A, Mooney R (2006) Probabilistic semi-supervised clustering with constraints. In: Chapelle O, Scholkopf B, Zien A (eds) Semi-supervised learning. Massachusetts Institute of Technology Press, pp 73–102
Berber T, Alpkocak A, Balci P, Dicle O (2013) Breast mass contour segmentation algorithm in digital mammograms. Comput Methods Progr Biomed 110(2):150–159
Besag J (1986) On the statistical analysis of dirty pictures. J R Stat Soc Series B (Methodol) 48(3):259–279. https://doi.org/10.1111/j.2517-6161.1986.tb01412.x
Bezdek J C, Ehrlich R, Full W (1984) FCM: the fuzzy c-means clustering algorithm. Comput Geosci 10(2–3):191–203. https://doi.org/10.1016/0098-3004(84)90020-7
Bilenko M, Basu S (2004) A comparison of inference techniques for semi-supervised clustering with hidden Markov random fields. In: Proceedings of the ICML-2004 workshop on statistical relational learning and its connections to other fields, pp 17–22
Bilenko M, Basu S, Mooney R J (2004) Integrating constraints and metric learning in semi-supervised clustering. In: Proceedings of the twenty-first international conference on machine learning, pp 839–846
Bozek J, Delac K, Grgic M (2008) Computer-aided detection and diagnosis of breast abnormalities in digital mammography. In: Proceedings of the 50th IEEE international symposium ELMAR, vol 1, pp 45–52
Cai J, Liu Z Q (2002) Pattern recognition using Markov random field models. Pattern Recognit 35(3):725–733. https://doi.org/10.1016/S0031-3203(01)00071-1
Cai W, Chen S, Zhang D (2007) Fast and robust fuzzy c-means clustering algorithms incorporating local information for image segmentation. Pattern Recognit 40(3):825–838. https://doi.org/10.1016/j.patcog.2006.07.011
Cárdenas-Sánchez J, Bargalló-Rocha J E, Erazo-Valle A, Chacón A P, Valero-Castillo V, Pérez-Sánchez V (2015) Consenso Mexicano sobre diagnóstico y tratamiento del cáncer mamario. Gaceta Mexicana de Oncología 14(Supl 2):2–55
Chen S, Zhang D (2004) Robust image segmentation using fcm with spatial constraints based on new kernel-induced distance measure. IEEE Trans Syst Man Cyber Part B (Cybern) 34(4):1907–1916. https://doi.org/10.1109/TSMCB.2004.831165
Cheng H, Shi X, Min R, Hu L, Cai X, Du H (2006) Approaches for automated detection and classification of masses in mammograms. Pattern Recognit 39(4):646–668. https://doi.org/10.1016/j.patcog.2005.07.006
Chu J, Min H, Liu L, Lu W (2015) A novel computer aided breast mass detection scheme based on morphological enhancement and SLIC superpixel segmentation. Med Phys 42(7):3859–3869. https://doi.org/10.1118/1.4921612
Duarte J M, Fred A L, Duarte F J F (2013) A constraint acquisition method for data clustering. In: Proceedings of the 18th CIARP, vol 8258(I), pp 108–116
Duarte J M, Fred A L, Duarte F J F (2014) Constraint acquisition methods for data clustering. Intell Data Anal 18(6S):S47–S64. https://doi.org/10.3233/IDA-140708
Elazab A, Wang C, Jia F, Wu J, Li G, Hu Q (2015) Segmentation of brain tissues from magnetic resonance images using adaptively regularized kernel-based fuzzy-means clustering. Comput Math Methods Med 2015. https://doi.org/10.1155/2015/485495
GCO: Breast-GLOBOCAN (2018) International Agency for Research on Cancer. https://gco.iarc.fr/today/data/factsheets/cancers/20-Breast-fact-sheet.pdf (accessed Jun 2019)
Geman S, Graffigne C (1986) Markov random field image models and their applications to computer vision. In: Proceedings of the 1986 international congress of mathematicians, pp 1496– 1517
Gonzalez R C, Woods R E (2008) Digital image processing, 3rd edn. Prentice Hall, Upper Saddle River
Kamil M Y, Salih A M (2019) Mammography images segmentation via Fuzzy C-mean and K-mean. Int J Intell Eng Syst 12(1):22–29
Katartzis A, Sahli H, Cornelis J, Fotopoulos S, Panayiotakis G (2002) Model-based technique for the measurement of skin thickness in mammography. Med Biol Eng Comput 40(2):153–162. https://doi.org/10.1007/BF02348119
Kom G, Tiedeu A, Kom M (2007) Automated detection of masses in mammograms by local adaptive thresholding. Comput Biol Med 37(1):37–48. https://doi.org/10.1016/j.compbiomed.2005.12.004
Krinidis S, Chatzis V (2010) A robust fuzzy local information c-means clustering algorithm. IEEE Trans Image Process 19(5):1328–1337. https://doi.org/10.1109/TIP.2010.2040763
Lewis S H, Dong A (2012) Detection of breast tumor candidates using marker-controlled watershed segmentation and morphological analysis. In: Proceedings of the 2012 IEEE Southwest symposium on image analysis and interpretation, pp 1–4
Li S Z (1994) Markov random field models in computer vision. In: Proceedings of the 3rd European conference on computer vision, vol 801, pp 361–370
Li S Z (1995) Markov random field modeling in computer vision. Springer, Berlin
Li H D, Kallergi M, Clarke L P, Jain V K, Clark R A (1995) Markov random field for tumor detection in digital mammography. IEEE Trans Med Imaging 14(3):565–576. https://doi.org/10.1109/42.414622
Li H, Wang Y, Liu K R, Lo S C, Freedman M T (2001) Computerized radiographic mass detection. I. Lesion site selection by morphological enhancement and contextual segmentation. IEEE Trans Med Imaging 20(4):289–301. https://doi.org/10.1109/42.921478
Lloyd S (1982) Least squares quantization in PCM. IEEE Trans Inf Theory 28(2):129–137. https://doi.org/10.1109/TIT.1982.1056489
Martin D, Fowlkes C, Tal D, Malik J (2001) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings of the 8th IEEE international conference on computer vision, vol 2, pp 416–423
Meilă M (2003) Comparing clusterings by the variation of information. In: Proceedings of the 16th annual conference on computational learning theory and 7th kernel workshop. Learning theory and kernel machines, vol 2777, pp 173–187
Morrow W M, Paranjape R B, Rangayyan R M, Desautels J L (1992) Region-based contrast enhancement of mammograms. IEEE Trans Med Imaging 11(3):392–406. https://doi.org/10.1109/42.158944
Moura D C, López M A G (2013) An evaluation of image descriptors combined with clinical data for breast cancer diagnosis. Int J Comput Assist Radiol Surg 8(4):561–574. https://doi.org/10.1007/s11548-013-0838-2
Oliver A, Freixenet J, Marti J, Pérez E, Pont J, Denton E R, Zwiggelaar R (2010) A review of automatic mass detection and segmentation in mammographic images. Med Image Anal 14(2):87–110. https://doi.org/10.1016/j.media.2009.12.005
Peng B, Zhang L, Zhang D (2013) A survey of graph theoretical approaches to image segmentation. Pattern Recognit 46(3):1020–1038. https://doi.org/10.1016/j.patcog.2012.09.015
Rand W M (1971) Objective criteria for the evaluation of clustering methods. J Am Stat Assoc 66(336):846–850. https://doi.org/10.1080/01621459.1971.10482356
Rodríguez-López V, Miranda-Luna R, Arias-Aguilar J A (2013) Detection of masses in mammogram images using morphological operators and Markov random fields. In: 12th Mexican international conference on artificial intelligence, pp 558– 569
Rojas-Dominguez A, Nandi A K (2008) Detection of masses in mammograms via statistically based enhancement, multilevel-thresholding segmentation, and region selection. Comput Med Imaging Graph 32(4):304–315. https://doi.org/10.1016/j.compmedimag.2008.01.006
Sampat M P, Markey M K, Bovik A C (2005) Computer-aided detection and diagnosis in mammography. Handb Image Video Process 2(1):1195–1217
Shinde M (2003) Computer aided diagnosis in digital mammography: classification of mass and normal tissue. Ph.D. thesis, University of South Florida USA
Suliga M, Deklerck R, Nyssen E (2008) Markov random field-based clustering applied to the segmentation of masses in digital mammograms. Comput Med Imaging Graph 32 (6):502–512. https://doi.org/10.1016/j.compmedimag.2008.05.004
Unnikrishnan R, Pantofaru C, Hebert M (2005) A measure for objective evaluation of image segmentation algorithms. In: Proceedings of the 2005 IEEE computer society conference on computer vision and pattern recognition—workshops, pp 34– 34
Vu V V, Labroche N, Bouchon-Meunier B (2010) An efficient active constraint selection algorithm for clustering. In: Proceedings of the 20th international conference on pattern recognition, pp 2969–2972
WHO (2014) WHO position paper on mammography screening. World Health Organization https://www.who.int/cancer/publications/mammography_screening/en/ (Accessed Jun 2019)
Xu S, Liu H, Song E (2011) Marker-controlled watershed for lesion segmentation in mammograms. J Digit Imaging 24(5):754–763. https://doi.org/10.1007/s10278-011-9365-2
Zhen L, Chan A K (2001) An artificial intelligent algorithm for tumor detection in screening mammogram. IEEE Trans Med Imaging 20(7):559–567. https://doi.org/10.1109/42.932741
Zonderland H, Smithuis R (2013) BI-RADS for mammography and ultrasound. Radiology department of the Academical Medical Centre in Amsterdam and the Rijnland hospital in Leiderdorp, the Netherlands http://www.radiologyassistant.nl/en/p53b4082c92130/bi-rads-for-mammography-and-ultrasound-2013.html (Accessed Jun 2019)
Acknowledgments
S. Hernández-Hernández acknowledges the Mexican National Council for Science and Technology (CONACYT) for her MSc fellowship. Also, this work was partially supported by CONACYT under the Catedra program number 1170.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Cruz-Barbosa, R., Hernández-Hernández, S. & Sucar, L.E. Mass segmentation of mammograms using Markov models associated with constrained clustering. Med Biol Eng Comput 58, 2475–2495 (2020). https://doi.org/10.1007/s11517-020-02221-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-020-02221-w