Levels Propagation Approach to Image Segmentation: Application to Breast MR Images

  • Fatah BouchebbahEmail author
  • Hachem Slimani


Accurate segmentation of a breast tumor region is fundamental for treatment. Magnetic resonance imaging (MRI) is a widely used diagnostic tool. In this paper, a new semi-automatic segmentation approach for MRI breast tumor segmentation called Levels Propagation Approach (LPA) is introduced. The introduced segmentation approach takes inspiration from tumor propagation and relies on a finite set of nested and non-overlapped levels. LPA has several features: it is highly suitable to parallelization and offers a simple and dynamic possibility to automate the threshold selection. Furthermore, it allows stopping of the segmentation at any desired limit. Particularly, it allows to avoid to reach the breast skin-line region which is known as a significant issue that reduces the precision and the effectiveness of the breast tumor segmentation. The proposed approach have been tested on two clinical datasets, namely RIDER breast tumor dataset and CMH-LIMED breast tumor dataset. The experimental evaluations have shown that LPA has produced competitive results to some state-of-the-art methods and has acceptable computation complexity.


Levels Propagation Image segmentation Breast MRI Tumor 



The authors are thankful to the anonymous referees for their valuable suggestions and comments which have helped in improving the quality of the paper and its presentation. Furthermore, we would like to thank the hospital staff of Chahids Mahmoudi Hospital, Tizi Ouzou, Algeria, who generously allowed us to collect real MRI breast images from the radiology service of their establishment. Most particularly, we are grateful to Dr Farid Kechih for his inestimable help, especially in anonymazing the medical images, making and validating the associated ground truth of the constructed dataset (CMH-LIMED). We also thank Mr Hamid Slimani, Mr Youcef Hannou, and Dr Mohamed Rabia for facilitating the contact with the hospital staff.


  1. 1.
    Hecht F, Pessoa CF, Gentile LB, Rosenthal D, Carvalho DP, Fortunato RS: The role of oxidative stress on breast cancer development and therapy. Tumor Biol 37: 4281–4291, 2016CrossRefGoogle Scholar
  2. 2.
    World Health Organization (2018) Available at Accessed on October 20th
  3. 3.
    Banaie M, Soltanian-Zadeh H, Saligheh-Rad HR, Gity M: Spatiotemporal features of DCE-MRI for breast cancer diagnosis. Comput Methods Programs Biomed 155: 153–164, 2018CrossRefGoogle Scholar
  4. 4.
    Ferreira A, Gentil F, Tavares JMR: Segmentation algorithms for ear image data towards biomechanical studies. Comput Methods Biomech Biomed Engin 17: 888–904, 2014CrossRefGoogle Scholar
  5. 5.
    Mughal B, Sharif M: Automated detection of breast tumor in different imaging modalities: A Review. Current Medical Imaging Reviews 13: 121–139, 2017CrossRefGoogle Scholar
  6. 6.
    Scoggins M, Dogan B, Ma J, Wei W, Song JB, Candelaria RP, Litton JK, Arun B: Short breast MRI screening trial in women at high-risk for breast cancer. J Clin Oncol 35: e13049, 2017CrossRefGoogle Scholar
  7. 7.
    Ma Z, Tavares JMR, Jorge RN, Mascarenhas T: A review of algorithms for medical image segmentation and their applications to the female pelvic cavity. Comput Methods Biomech Biomed Engin 13: 235–246, 2010CrossRefGoogle Scholar
  8. 8.
    Singh SP, Urooj S: An improved CAD system for breast cancer diagnosis based on generalized pseudo-Zernike moment and Ada-DEWNN classifier. J Med Syst 40: 105–118, 2016CrossRefGoogle Scholar
  9. 9.
    Jida S, Aksasse B, Ouanan M (2017) Face segmentation and detection using Voronoi diagram and 2D histogram. In: Intelligent systems and computer vision, Fez, 1-5Google Scholar
  10. 10.
    Oliveira RB, Mercedes Filho E, Ma Z, Papa JP, Pereira AS, Tavares JMR: Computational methods for the image segmentation of pigmented skin lesions: a review. Comput Methods Programs Biomed 131: 127–141, 2016CrossRefGoogle Scholar
  11. 11.
    Shi J, Sahiner B, Chan HP, Paramagul C, Hadjiiski LM, Helvie M, Chenevert T: Treatment response assessment of breast masses on dynamic contrast-enhanced magnetic resonance scans using fuzzy c-means clustering and level set segmentation. Med Phys 36: 5052–5063, 2009CrossRefGoogle Scholar
  12. 12.
    Yin D, Lu RW (2015) A method of breast tumour MRI segmentation and 3D reconstruction. In: 7th International conference on information technology in medicine and education, Huangshan, 23-26Google Scholar
  13. 13.
    Liu H, Liu Y, Zhao Z, Zhang L, Qiu T: A new background distribution-based active contour model for three-dimensional lesion segmentation in breast DCE-MRI. Med Phys 41(8), Part 1, 2014Google Scholar
  14. 14.
    Agner SC, Xu J, Madabhushi A: Spectral embedding based active contour (SEAC) for lesion segmentation on breast dynamic contrast enhanced magnetic resonance imaging. Med Phys 40(3), 2013Google Scholar
  15. 15.
    Al-Faris AQ, Ngah UK, Isa NAM, Shuaib IL: Computer-aided segmentation system for breast MRI tumour using modified automatic seeded region growing (BMRI-MASRG). J Digit Imaging 27: 133–144, 2014CrossRefGoogle Scholar
  16. 16.
    Cui Y, Tan Y, Zhao B, Liberman L, Parbhu R, Kaplan J, Theodoulou M, Hudis C, Schwartz LH: Malignant lesion segmentation in contrast-enhanced breast MR images based on the marker-controlled watershed. Med Phys 36: 4359–4369, 2009CrossRefGoogle Scholar
  17. 17.
    Azmi R, Anbiaee R, Norozi N, Salehi L, Amirzadi A: IMPST: a new interactive self-training approach to segmentation suspicious lesions in breast MRI. J Med Signals Sensors 1: 138–148, 2011Google Scholar
  18. 18.
    Fix E, Hodges JL (1951) Discriminatory analysis, nonparametric discrimination: Consistency properties, Technical Report 4, USAF School of Aviation Medicine, Randolph fiels TXGoogle Scholar
  19. 19.
    Yao J, Chen J, Chow C: Breast tumor analysis in dynamic contrast enhanced MRI using texture features and wavelet transform. IEEE J Sel Top Sign Proces 3: 94–100, 2009CrossRefGoogle Scholar
  20. 20.
    Wu Q, Salganicoff M, Krishnan A, Fussell DS, Markey MK (2006) Interactive lesion segmentation on dynamic contrast enhanced breast MRI using a markov model. In: Proc. SPIE medical imaging: Image processing, 6144, San DiegoGoogle Scholar
  21. 21.
    Chen W, Giger ML, Bick U: A fuzzy c-means (FCM)-based approach for computerized segmentation of breast lesions in dynamic contrast-enhanced MR Images. Acad Radiol 13: 63–72, 2006CrossRefGoogle Scholar
  22. 22.
    Moftah HM, Azar AT, Al-Shammari ET, Ghali NI, Hassanien AE, Shoman M: Adaptive K-means clustering algorithm for MR breast image segmentation. Neural Comput Appl 24: 1917–1928, 2014CrossRefGoogle Scholar
  23. 23.
    Hassanien AE, Moftah HM, Azar A T, Shoman M: MRI breast cancer diagnosis hybrid approach using adaptive ant-based segmentation and multilayer perceptron neural networks classifier. Appl Soft Comput 14: 62–71, 2014CrossRefGoogle Scholar
  24. 24.
    McClymont D, Mehnert A, Trakic A, Kennedy D, Crozier S: Fully automatic lesion segmentation in breast MRI using mean-shift and graph-cuts on a region adjacency graph. J Magn Reson Imaging 39: 795–804, 2014CrossRefGoogle Scholar
  25. 25.
    Yu N, Wu J, Weinstein SP, Gaonkar B, Keller BM, Ashraf AB, Jiang Y, Davatzikos C, Conant EF, Kontos D (2015) A superpixel-based framework for automatic tumor segmentation on breast DCE-MRI. In Proc. SPIE medical imaging: Computer-aided diagnosis, 9414, OrlandoGoogle Scholar
  26. 26.
    Jayender J, Chikarmane S, Jolesz FA, Gombos E: Automatic segmentation of invasive breast carcinomas from dynamic contrast-enhaced MRI using time series analysis. J Magn Reson Imaging 40: 467–475, 2014CrossRefGoogle Scholar
  27. 27.
    Maicas G, Carneiro G, Bradley AP (2017) Globally optimal breast mass segmentation from DCE-MRI using deep semantic segmentation as shape prior. In: 14th international symposium on biomedical imaging, Melbourne, 305-309Google Scholar
  28. 28.
    Zaheeruddin Z, Jaffery ZA, Singh L (2012) Detection and shape feature extraction of breast tumor in mammograms. In: Proceedings of the world congress on engineering, London, pp 719–724Google Scholar
  29. 29.
    Xie X, Yeo SY, Mirmehdi M, Sazonov I, Nithiarasu P: Image gradient based level set methods in 2D and 3D. In: (González HM, et al, Eds.) Deformation Models, Netherlands, 2013, pp 101–120Google Scholar
  30. 30.
    Pavlidis G (2017) Segmentation of digital images. In: Mixed Raster Content. Signals and communication technology, Singapore, 213-260Google Scholar
  31. 31.
    Nowell PC: The clonal evolution of tumor cell populations. Science 194: 23–28, 1976CrossRefGoogle Scholar
  32. 32.
    Visvader JE: Cells of origin in cancer. Nature 469: 314–322, 2011CrossRefGoogle Scholar
  33. 33.
    Scott RE, Wille JJ, Wier ML: Mechanisms for the initiation and promotion of carcinogenesis: a review and a new concept. Mayo Clin Proc 59: 107–117, 1984CrossRefGoogle Scholar
  34. 34.
    Adams R, Bischof L: Seeded region growing. IEEE Trans Pattern Anal Mach Intell 16: 641–647, 1994CrossRefGoogle Scholar
  35. 35.
    Malek AA, Rahman WEZWA, Haris MHM, Jalil UMA: Segmenting masses in ultrasound images by using seed based region growing and mathematical morphology. Adv Sci Lett 23: 11512–11516, 2017CrossRefGoogle Scholar
  36. 36.
    Shrivastava A, Chaudhary A, Kulshreshtha D, Singh VP, Srivastava R (2017) Automated digital mammogram segmentation using dispersed region growing and sliding window algorithm. In: 2nd international conference on image, vision and computing, Chengdu, pp 366–370Google Scholar
  37. 37.
    Solves LJ, Monserrat C, Rupérez MJ, Naranjo V, Alajami M, Feliu F, Garcìa M, Lloret M: MRI skin segmentation for the virtual deformation of the breast under mammographic compression. Stud Health Technol Inform 173: 483–489, 2012Google Scholar
  38. 38.
    Al-Faris AQ, Isa NAM, Ngah UK, Shuaib IL (2015) Automatic exclusion of skin border regions from breast MRI using proposed combined approach. In: 2nd international conference on biomedical engineering, Perlis, pp 1–6Google Scholar
  39. 39.
    Meyer CR, Chenevert TL, Galbán CJ, Johnson TD, Hamstra DA, Rehemtulla A, Ross BD (2015) Data from RIDER-Breast-MRI. The cancer imaging archive.
  40. 40.
    Li C, Huang R, Ding Z, Gatenby J, Metaxas DN, Gore JC: A level set method for image segmentation in the presence of intensity inhomogeneities with application to MRI. IEEE Trans Image Process 20: 2007–2016, 2011CrossRefGoogle Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2019

Authors and Affiliations

  1. 1.LIMED Laboratory, Computer Science DepartmentUniversity of BejaiaBejaiaAlgeria

Personalised recommendations