Skip to main content
SpringerLink
Log in

Graph Theory Based Segmentation of Magnetic Resonance Images for Brain Tumor Detection

  • APPLICATION PROBLEMS
  • Published:
Pattern Recognition and Image Analysis Aims and scope Submit manuscript

Abstract

Segmentation process is very challenging task in medical imaging field. Efficient segmentation of magnetic resonance image (MRI) is very much necessary requirement in medical imaging, because such kind images have complex tissues, texture, structures, and edges, so this results in difficulty to detect any brain related diseases. Different magnetic field used depending MR scanner machine effects on variation of brightness in MR images. In this research, the graph theory based segmentation method has been proposed, because it has flexibility representing any complex structure. Before segmentation process, MR images are preprocessed using region of interest, inverse method, and boundary detection method. In this method the segmentation of MRI brain images is performed as a weighted directed graph is constructed to the polar image, where nodes in the graph correspond to every pixel of image in the graph and edge weight is determined as cost of group of pixels in the image. After that, a cost function is calculated based on relative edge weight similarity; minimization of this cost using minimum spanning tree algorithm leads to minimum path graph, which is equivalent to shortest path. Image segmentation is performed using obtained path in the graph on required region of interest on MR images to detect brain tumors.

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

Access this article

Log in via an institution

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.

Similar content being viewed by others

REFERENCES

  1. P. Agrawal, G. Ojha, and M. Bhattacharya, “A Generic Algorithm for Segmenting a Specified Region of Interest Based on Chanvese’s Algorithm and Active Contours,” in Artificial Intelligence and Evolutionary Computations in Engineering Systems, Ed. by S. Dash, M. Bhaskar, B. Panigrahi, and S. Das, Advances in Intelligent Systems and Computing, vol. 394 (Springer, New Delhi, 2016), pp. 239–247. https://doi.org/10.1007/978-81-322-2656-7_21

  2. A. A. Taha and A. Hanbury, “Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool,” BMC Med. Imaging 15, 29 (2015). https://doi.org/10.1186/s12880-015-0068-x

    Article  Google Scholar 

  3. M. Balafar, “Fuzzy C-mean based brain MRI segmentation algorithms,” Artif. Intell. Rev. 41, 441–449 (2014). https://doi.org/10.1007/s10462-012-9318-2

    Article  Google Scholar 

  4. B. Kayalibay, G. Jensen, P. van der Smagt, “CNN-based segmentation of medical imaging data.” arXiv:1701.03056 [cs.CV]

  5. M. B. Cuadra, V. Duay, J.-Ph. Thiran, “Atlas-based segmentation,” in Handbook of Biomedical Imaging, Ed. by N. Paragios, J. Duncan, and N. Ayache (Springer, Boston, 2015), pp. 221–244. https://doi.org/10.1007/978-0-387-09749-7_12

    Book  Google Scholar 

  6. I. Despotović, B. Goossens, and W. Philips, “MRI segmentation of the human brain: challenges, methods, and applications,” Comput. Math. Methods Med. 2015, 450341 (2015). https://doi.org/10.1155/2015/450341

    Article  Google Scholar 

  7. R. Gonzalez and E. R. Woods, Digital Image Processing (2002), 2nd ed.

    Google Scholar 

  8. K. K. Jena, “Application of a Nobel approach for edge detection of images,” J. Image Process. Artif. Intell. 1 (1), 1–6 (2005).

    Google Scholar 

  9. R. S. Kamathe and K. R. Joshi, “A novel method based on independent component analysis for brain MR image tissue classification into CSF, WM and GM for atrophy detection in Alzheimer’s disease,” Biomed. Signal Process. Control 40, 41–48 (2018). https://doi.org/10.1016/j.bspc.2017.09.005

    Article  Google Scholar 

  10. M. Kulkarni, A. N. Naik, and A. P. Bhadvankar, “Review paper on image processing techniques,” Int. J. Sci. Res. Dev. 3 (10), 320–325 (2015). https://doi.org/10.1109/ICSensT.2012.6461695

  11. J. Lai and H. Zhu, “A fusion algorithm: Fully convolutional networks and Student’s-t mixture model for brain magnetic resonance imaging segmentation,” in 25th IEEE Int. Conf. on Image Processing (ICIP), Athens, 2018 (IEEE, 2018), pp. 1598–1602. https://doi.org/10.1109/ICIP.2018.8451615

  12. B. H. Menze, A. Jakab, S. Bauer, J. Kalpathy-Cramer, K. Farahani, J. Kirby, et al., “The multimodal brain tumor image segmentation benchmark (BRATS),” IEEE Trans. Med. Imaging 34, 1993–2024 (2015). https://doi.org/10.1109/TMI.2014.2377694

    Article  Google Scholar 

  13. P. Moeskops, M. A. Viergever, A. M. Mendrik, L. S. de Vries, M. J. N. L. Benders, and I. Išgum, “Automatic segmentation of MR brain images with a convolutional neural network,” IEEE Trans. Med. Imaging 35, 1252–1261 (2016). https://doi.org/10.1109/TMI.2016.2548501

    Article  Google Scholar 

  14. P. Ghosh, S. K. Das, and K. Mali, “Comparative analysis of proposed FCM clustering integrated enhanced firefly-optimized algorithm (En-FAOFCM) for MR image segmentation and performance evaluation,” J. Image Process. Pattern Recognit. Prog. 3 (1), 32–44 (2016).

    Google Scholar 

  15. S. Salti, A. Petrelli, F. Tombari, N. Fioraio, and L. Di Stefano, “Traffic sign detection via interest region extraction,” Pattern Recognit. 48, 1039–1049 (2015). https://doi.org/10.1016/j.patcog.2014.05.017

    Article  Google Scholar 

  16. S. Saman and S. J. Narayanan, “Survey on brain tumor segmentation and feature extraction of MR images,” Int. J. Multimedia Inf. Retr. 8, 79–99 (2019). https://doi.org/10.1007/s13735-018-0162-2

    Article  Google Scholar 

  17. S. Valverde, A. Oliver, E. Roura, S. González-Villà, D. Pareto, J. C. Vilanova, L. Ramió-Torrentà, À. Rovira, and X. Lladó, “Automated tissue segmentation of MR brain images in the presence of white matter lesions,” Med. Image Anal. 35, 446–457 (2017). https://doi.org/10.1016/j.media.2016.08.014

    Article  Google Scholar 

  18. S. Sun and R. Zhang, “Region of interest extraction of medical image based on improved region growing algorithm,” in Proc. 2017 Int. Conf. on Material Science, Energy and Environmental Engineering (MSEEE 2017), Xi’an, China, 2017, Advances in Engineering Research, vol. 125 (Atlantis Press, 2017), pp. 360–364. https://doi.org/10.2991/mseee-17.2017.87

  19. E. Shelhamer, J. Long, and T. Darrell, “Fully convolutional networks for semantic segmentation,” IEEE Trans. Pattern Anal. Mach. Intell. 39, 640–651 (2017). https://doi.org/10.1109/TPAMI.2016.2572683

    Article  Google Scholar 

  20. G. T. Shrivakshan and C. Chandrasekar, “A comparison of various edge detection techniques used in image processing,” Int. J. Comput. Sci. Issues 9, 272–276 (2012).

    Google Scholar 

  21. K. Ungru and X. Jiang, “Dynamic programming based segmentation in biomedical imaging,” Comput. Struct. Biotechnol. J. 15, 255–264 (2017). https://doi.org/10.1016/j.csbj.2017.02.001

    Article  MATH  Google Scholar 

  22. M. Vaezi, C. Kai Chua, and S. Meng Chou, “Improving the process of making rapid prototyping models from medical ultrasound images,” Rapid Prototyping J. 18, 287–298 (2012). https://doi.org/10.1108/13552541211231716

    Article  Google Scholar 

  23. V. Chaurasia, P. Soniya, Y. Kurmi, and A. Modi, “Feature-based segmentation of brain tumor in MRI images,” in Proc. Fourth Int. Conf. on Microelectronics, Computing and Communication Systems, Ed. by V. Nath and J. K. Mandal, Lecture Notes in Electrical Engineering, vol. 673 (Springer, Singapore, 2021), pp. 219–231. https://doi.org/10.1007/978-981-15-5546-6_18

  24. Q. N. Vo, S. H. Kim, H. J. Yang, and G. S. Lee, “Text line segmentation using a fully convolutional network in handwritten document images,” IET Image Process. 12, 438–446 (2018). https://doi.org/10.1049/iet-ipr.2017.0083

    Article  Google Scholar 

  25. W. Zhu and Y. Shen, “A region growing segmentation approach for MRI brain image processing,” in IEEE 13th Int. Conf. on Anti-Counterfeiting, Security, and Identification (ASID), Xiamen, China, 2019 (IEEE, 2019), pp. 188–191. https://doi.org/10.1109/ICASID.2019.8925066

  26. X. Yang and B. Fei, “A multiscale and multiblock fuzzy c-means classification method for brain MR images,” Med. Phys. 38, 2879–2891 (2011).  https://doi.org/10.1118/1.3584199

    Article  Google Scholar 

  27. R. Yogamangalam, “Segmentation techniques comparison in image processing,” Int. J. Eng. Technol. 5, 307–313 (2013).

    Google Scholar 

Download references

ACKNOWLEDGMENTS

We thank Dr. Partha Sarathi (Vydehi Institute of Medical Science) for providing patient samples. We also thank management of Dr. AIT for giving continuous support in all aspects of this research.

Author information

Authors and Affiliations

  1. CSE Department, Dr.AIT, 560056, Bangalore, India

    S. K. Mamatha & N. Shalini

  2. CSE Department, RVCE, 560059, Bangalore, India

    H. K. Krishnappa

Authors
  1. S. K. Mamatha
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. H. K. Krishnappa
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. N. Shalini
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to S. K. Mamatha, H. K. Krishnappa or N. Shalini.

Ethics declarations

COMPLIANCE WITH ETHICAL STANDARDS

This article is a completely original work of its authors; it has not been published before and will not be sent to other publications until the PRIA Editorial Board decides not to accept it for publication.

Conflict of Interest

The process of writing and the content of the article do not give grounds for raising the issue of a conflict of interest.

Additional information

Mamatha S.K. received BE degree in Computer Science and Engineering from Visvesvaraya Technological University, Belgaum, India in 2008 and MTech degree in Computer Engineering from Visvesvaraya Technological University, Belgaum, India in 2014. Her research interests include Image Processing and Medical imaging applications. Currently she is working as an Assistant Professor of Computer Science and Engineering in Dr. Ambedkar Institute of Technology, Bangalore.

Dr. Krishnappa H.K. received MTech degree in Computer Science and Engineering from Visvesvaraya Technological University Belgaum, India and PhD degree in Computer Science from Visvesvaraya Technological University, Belgaum, India in 2014. His research interests include Theoretical Computer Science, Image Processing and Pattern Recognition. Currently he is working as an Associate Professor of Computer Science and Engineering in R.V. College of Engineering, Bangalore.

Shalini N. received BE degree in Information Science and Engineering from Visvesvaraya Technological University, Belgaum, India in 2015 and MTech degree in Computer Science and Engineering from Visvesvaraya Technological University, Belgaum, India in 2017. Her research interests include image processing and IoT. Currently she is working as an Assistant Professor of Computer Science and Engineering in Dr. Ambedkar Institute of Technology, Bangalore.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mamatha, S.K., Krishnappa, H.K. & Shalini, N. Graph Theory Based Segmentation of Magnetic Resonance Images for Brain Tumor Detection. Pattern Recognit. Image Anal. 32, 153–161 (2022). https://doi.org/10.1134/S1054661821040167

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1054661821040167

Keywords:

Search

Navigation