Skip to main content

Advertisement

Springer Nature Link
Log in

An automatic MRI brain image segmentation technique using edge–region-based level set

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Digital transformation has brought radical changes in several domains. Particularly, image processing techniques have been generally used in medical, security, and monitoring applications. Image segmentation is a specific task where an image is partitioned in meaningful segments, containing similar features and properties. Its aim is to simplify the original image for easy analysis since relevant information is highlighted. These techniques are commonly used to support medical experts in detecting areas of interest in medical images. Level set method is a methodology for image segmentation, which works with minimizing energy for segmentation of the image by active contours. The areas inside each contour belong to distinct segments. In active contour-based models, the level of each contour changes according to the intensity values (region-based active contours) or the gradient variations (edge-based active contours). Here, a new edge–region level set algorithm for image segmentation is proposed which controls the curve movement based on both intensity and gradient values. Moreover, the original active contour model has been modified by considering both the mean and the variance values of the pixels’ neighborhood, instead of the mean value only. Indeed, in homogeneous regions with the same mean value could be assigned to the same segment while belonging to different ones. Since the initial curve definition is crucial for level set methods, a new methodology for initial curve detection based on Canny edge detector has been proposed. Experiments have been conducted on brain tumor magnetic resonance imaging (MRI). Images from Whole Brain Atlas (Harvard University Medical School) datasets, part Neoplastic Disease (brain tumor) have been used. Results have shown that the suggested approach is able to accurately detect tumor regions in the images and to overcome the original active contour models such as CV, LBF, and LIF. Using semi-average filter in pre-processing stage can strengthen edges and it led to detecting more strong edges in Canny edge detector.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Data Availability

The datasets analyzed during the current study are available in the Whole Brain Atlas dataset, Neoplastic Disease (brain tumor) part, www.med.harvard.edu/aanlib.

Notes

  1. https://www.med.harvard.edu/aanlib/home.html

References

  1. Weller M, Wick W, Aldape K et al (2015) Glioma. Nat Rev Dis Primers 1:15017

    Article  Google Scholar 

  2. Vlaardingerbroek MT, Boer JA (2013) Magnetic resonance imaging: theory and practice. Springer Science & Business Media

    Google Scholar 

  3. Hameurlaine M, Moussaoui A (2019) Survey of brain tumor segmentation techniques on magnetic resonance imaging. Nano Biomed Eng 11(2):178–191

    Article  Google Scholar 

  4. Bajaj AS, Chouhan U (2020) A review of various machine learning techniques for brain tumor detection from mri images. Curr Med Imag 16(8):937–945

    Article  Google Scholar 

  5. Magadza T, Viriri S (2021) Deep learning for brain tumor segmentation: a survey of state-of-the-art. J Imag 7(2):19

    Article  Google Scholar 

  6. Lella E, Vessio G (2020) Ensembling complex network ‘perspectives’ for mild cognitive impairment detection with artificial neural networks. Pattern Recogn Lett 136:168–174

    Article  Google Scholar 

  7. Mahdi M, Nasser A (2021) A three-stage shearlet-based algorithm for vessel segmentation in medical imaging. Pattern Anal Appl. https://doi.org/10.1007/S10044-020-00915-3

    Article  Google Scholar 

  8. Siadat M, Aghazadeh N, Akbarifard F, Brismar H (2019) Joint image deconvolution and separation using mixed dictionaries. IEEE Trans Image Process 28(8):3936–3945

    Article  MathSciNet  MATH  Google Scholar 

  9. Cigaroudy LS, Aghazadeh N (2017) A new multiphase segmentation method using eigenvectors based on k real number. Circuits Syst Signal Process 36(4):1445–1454. https://doi.org/10.1007/S00034-016-0359-7

    Article  MathSciNet  MATH  Google Scholar 

  10. Cigaroudy LS, Aghazadeh N (2017) A multiphase segmentation method based on binary segmentation method for Gaussian noisy image. Signal Image Video Process 11(5):825–831. https://doi.org/10.1007/S11760-016-1028-9

    Article  MATH  Google Scholar 

  11. Aghazadeh N, Akbarifard F, Ladan SC (2016) A restoration-segmentation algorithm based on flexible Arnoldi-Tikhonov method and curvelet denoising. Signal, Image Video Process 10(5):935–942. https://doi.org/10.1007/S11760-015-0843-8

    Article  Google Scholar 

  12. Cigaroudy LS, Aghazadeh N (2022) A Binary-Segmentation algorithm based on shearlet transform and eigenvectors, 2nd International Conference on Pattern Recognition and Image Analysis (IPRIA). https://doi.org/10.1109/PRIA.2015.7161618.

  13. Narkhede HP (2013) Review of image segmentation techniques. Int J Sci Modern Eng 1(8):54–61

    Google Scholar 

  14. Caponetti L, Castellano G, Corsini V (2017) Mr brain image segmentation: a framework to compare different clustering techniques. Information 8(4):38

    Article  Google Scholar 

  15. Liu T, Xu H, Jin W, Liu Z, Zhao Y, Tian W (2014) Medical image segmentation based on a hybrid region-based active contour model. Comput Math Methods Med 2014:1–10. https://doi.org/10.1155/2014/890725

    Article  MATH  Google Scholar 

  16. An J-H, Chen Y (2007) Region based image segmentation using a modified Mumford-Shah algorithm. In: International conference on scale space and variational methods in computer vision. Springer, pp 733–742

  17. Muller S, Ochs P, Weickert J, Graf N (2016) Robust interactive multi-label segmentation with an advanced edge detector. In: German conference on pattern recognition. Springer, pp 117–128

  18. Xiangyang X, Shengzhou X, Jin L, Song E (2011) Characteristic analysis of Otsu threshold and its applications. Pattern Recognit Lett 32(7):956–961

    Article  Google Scholar 

  19. Mehndiratta A, Giesed F (2011) Brain tumor imaging. In book: Diagnostic Techniques and Surgical Management of Brain Tumors. https://doi.org/10.5772/23507

  20. Khairandish MO, Sharma M, Jain V, Chatterjee JM, Jhanjhi NZ (2022) A Hybrid CNN-SVM threshold segmentation approach for tumor detection and classification of MRI brain images. IRBM 43(4):290–299

    Article  Google Scholar 

  21. Sivakumar V, Janakiraman N (2020) A novel method for segmenting brain tumor using modified watershed algorithm in MRI image with FPGA. Biosystems 198:104226. https://doi.org/10.1016/j.biosystems.2020.104226

    Article  Google Scholar 

  22. Daimary D, Mayur BB, Khwairakpam A, Debdatta K (2020) Brain tumor segmentation from MRI images using hybrid convolutional neural networks. Proc Computer Sci 167:2419–2428

    Article  Google Scholar 

  23. Jaspin Jeba Sheela C, Suganthi G (2022) Automatic brain tumor segmentation from MRI using greedy snake model and fuzzy C-means optimization. J King Saud Univ- Computer Inf Sci 34(3):557–566

    Google Scholar 

  24. Amin J, Sharif M, Gul N, Yasmin M, Shad SA (2020) Brain tumor classification based on DWT fusion of MRI sequences using convolutional neural network. Pattern Recognit Lett 129:115–122

    Article  Google Scholar 

  25. Mumford DB, Shah J (1989) Optimal approximations by piecewise smooth functions and associated variational problems. Commun Pure Appl Math 25:46

    MathSciNet  MATH  Google Scholar 

  26. Bickey KS, Vansh K, Rohan R, Sakil A, Anshul S (2020) Evaluation and comparative study of edge detection techniques. IOSR J Computer Eng 22(5):06–15

    Google Scholar 

  27. Sert E, Avci D (2019) A new edge detection approach via neutrosophy based on maximum norm entropy. Expert Syst Appl 115:499–511

    Article  Google Scholar 

  28. Sangeetha D, Deepa P (2019) FPGA implementation of cost-effective robust Canny edge detection algorithm. J Real-Time Image Process 16(4):957–970. https://doi.org/10.1007/s11554-016-0582-2

    Article  Google Scholar 

  29. Kim W, Kim C (2012) Active contours driven by the salient edge energy model. IEEE Trans Image Process 22:1667–1673

    MathSciNet  MATH  Google Scholar 

  30. Lecellier F et al (2010) k Region-based active contours with exponential family observations. J Math Imag Vis 36:28

    Article  MathSciNet  Google Scholar 

  31. Cohen R (2011) The chan-vese algorithm. http://arxiv.org/abs/1107.2782

  32. Osher S, Sethian JA (1988) Fronts propagating with curvature-dependent speed: Algorithm based on Hamilton-Jacobi formulations. J Comput Phys 79(1):12–49

    Article  MathSciNet  MATH  Google Scholar 

  33. Ali H, Badshah N, Chen K, Khan G (2016) A variational model with hybrid images data fitting energies for segmentation of images with intensity inhomogeneity. Pattern Recognit 51:27–42

    Article  MATH  Google Scholar 

  34. Wang X, Huang D, Xu H (2010) An efficient local Chan-Vese model for image segmentation. Pattern Recognit 43(3):603–618

    Article  MATH  Google Scholar 

  35. Mabood L, Ali H, Badshah N, Ullah T (2015) Absolute median deviation based a robust image segmentation model. J Inf Commun Technol 9(1):13–22

    Google Scholar 

  36. Zhang K, Song H, Zhang L (2010) Active contours driven by local image fitting energy. Pattern Recognit 43(4):1199–1206

    Article  MATH  Google Scholar 

  37. Jayadevappa D, Kumar S, Murty D (2011) Medical image segmentation algorithms using deformable models: a review. IETE Tech Rev 28(3):248–255

    Article  Google Scholar 

  38. Li C, Wang X, Eberl S, Fulham M, Feng D (2013) Robust model for segmenting images with/without intensity inhomogeneities. IEEE Trans Image Process 22(8):3296–3309

    Article  Google Scholar 

  39. Wang B, Gao X, Tao D, Li X (2014) A nonlinear adaptive level set for image segmentation. IEEE Trans Cybern 44(3):418–428

    Article  Google Scholar 

  40. Wang H, Liu M (2013) Active contours driven by local gaussian distribution fitting energy based on local entropy. Int J Pattern Recognit Artif Intell 27(6):1073–1089

    Article  MathSciNet  Google Scholar 

  41. Chen F, Yu H, Hu R (2013) Shape sparse representation for joint object classification and segmentation. IEEE Trans Image Process 22(3):992–1004

    Article  MathSciNet  MATH  Google Scholar 

  42. Mylona E, Savelonas M, Maroulis D (2014) Automated adjustment of region-based active contour parameters using local image geometry. IEEE Trans Cybern 44(12):2757–2770

    Article  Google Scholar 

  43. Yang X, Gao X, Li J, Han B (2014) A shape-initialized and intensity-adaptive level set method for auroral oval segmentation. Inf. Sci. 277(2):794–807

    Article  Google Scholar 

  44. Hong-Kai ZT, Chan B, Merriman SO (1996) A variational level set approach to multiphase motion. J Comput Phys 127(1):179–195

    Article  MathSciNet  MATH  Google Scholar 

  45. Chan TF, Vese LA (2001) Active contours without edges. IEEE Trans Image Process 10(2):266–277

    Article  MATH  Google Scholar 

  46. Li Bing N, Chui Chee K, Chang S, Ong Sim H (2011) Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation. Computers Biol Med 41(1):1–10

    Article  Google Scholar 

  47. Li C, Kao C-Y, Gore JC, Ding Z (2007) Implicit active contours driven by local binary Fitting energy, In 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp 1–7

  48. Li C, Kao C-Y, Gore JC, Ding Z (2008) Minimization of region scalable fitting energy for image segmentation. IEEE Trans Image Process 17(10):1940–1949

    Article  MathSciNet  MATH  Google Scholar 

  49. Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 6:679–698

    Article  Google Scholar 

  50. https://www.med.harvard.edu/aANliB/home.html

  51. Hunderi AH, Karunakaran N (2013) Segmentation of medical image data using level set methods, master thesis, department of computer and information science, Norwegian University of Science and Technology

Download references

Author information

Authors and Affiliations

  1. Image Processing Laboratory, Department of Mathematics, Azarbaijan Shahid Madani University, Tabriz, Iran

    Nasser Aghazadeh, Paria Moradi & Parisa Noras

  2. Department of Computer Science, University of Bari, Bari, Italy

    Giovanna Castellano

Authors
  1. Nasser Aghazadeh
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Paria Moradi
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Giovanna Castellano
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Parisa Noras
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Nasser Aghazadeh.

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

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Aghazadeh, N., Moradi, P., Castellano, G. et al. An automatic MRI brain image segmentation technique using edge–region-based level set. J Supercomput 79, 7337–7359 (2023). https://doi.org/10.1007/s11227-022-04948-9

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-022-04948-9

Keywords