Advertisement

Neural Computing and Applications

, Volume 30, Issue 4, pp 1317–1340 | Cite as

A joint intensity and edge magnitude-based multilevel thresholding algorithm for the automatic segmentation of pathological MR brain images

  • Taranjit Kaur
  • Barjinder Singh Saini
  • Savita Gupta
Original Article
  • 181 Downloads

Abstract

Multilevel thresholding is one of the most popular image segmentation techniques due to its simplicity and accuracy. Most of the thresholding approaches use either the histogram of an image or information from the grey-level co-occurrence matrix (GLCM) to compute the threshold. The medical images like MRI usually have vague boundaries and poor contrast. So, segmenting these images using solely histogram or texture attributes of GLCM proves to be insufficient. This paper proposes a novel multilevel thresholding approach for automatic segmentation of tumour lesions from magnetic resonance images. The proposed technique exploits both intensity and edge magnitude information present in image histogram and GLCM to compute the multiple thresholds. Subsequently, using both attributes, a hybrid fitness function has been formulated which can capture the variations in intensity and the edge magnitude present in different tumour groups effectively. Mutation-based particle swarm optimization (MPSO) technique has been used to optimize the fitness function so as to mitigate the problem of high computational complexity existing in the exhaustive search methods. Moreover, MPSO has better exploration capabilities as compared to conventional particle swarm optimization. The performance of the devised technique has been evaluated and compared with two other intensity- and texture-based approaches using three different measures: Jaccard, Dice and misclassification error. To compute these quantitative metrics, experiments were conducted on a series of images, including low-grade glioma tumour volumes taken from brain tumour image segmentation benchmark 2012 and 2015 data sets and real clinical tumour images. Experimental results show that the proposed approach outperforms the other competing algorithms by achieving an average value equal to 0.752, 0.854, 0.0052; 0.648, 0.762, 0.0177; 0.710, 0.813, 0.0148 and 0.886, 0.937, 0.0037 for four different data sets.

Keywords

Automatic segmentation Multilevel thresholding MPSO Intensity Edge magnitude 

Notes

Acknowledgements

The authors gratefully acknowledge the efforts by Dr. Sandeep Singh Pawar (Advance Diagnostic Centre, Ludhiana, Punjab) for providing the clinical data and the interpretations.

Funding

This research received no specific grant from any funding agency in the public, commercial or not-for-profit sectors.

Compliance with ethical standards

Conflict of interest

None declared.

Ethical approval

This research has been approved by the Research Advisory Committee of the Institute. In addition, all of the procedures performed during the image acquisition process comply with the ethical standards of the diagnostic centre from which the image data have been taken.

References

  1. 1.
    Ganesan K, Acharya UR, Chua CK et al (2013) Computer-aided breast cancer detection using mammograms: a review. IEEE Rev Biomed Eng 6:77–98CrossRefGoogle Scholar
  2. 2.
    Iftekharuddin KM, Zheng J, Islam MA, Ogg RJ (2009) Fractal-based brain tumor detection in multimodal MRI. Appl Math Comput 207:23–41MathSciNetzbMATHGoogle Scholar
  3. 3.
    Zhang T, Xia Y, Dagan D (2014) Hidden Markov random field model based brain MR image segmentation using clonal selection algorithm and Markov chain Monte Carlo method. Biomed Signal Process Control 12:10–18CrossRefGoogle Scholar
  4. 4.
    Joe BN, Fukui MB, Meltzer CC et al (1999) Brain tumor volume measurement: comparison of manual and semi automated methods. Radiology 212:811–816CrossRefGoogle Scholar
  5. 5.
    Fletcher-Heath LM, Hall LO, Goldgof DB, Murtagh FR (2001) Automatic segmentation of non-enhancing brain tumors in magnetic resonance images. Artif Intell Med 21:43–63CrossRefGoogle Scholar
  6. 6.
    Liu J, Udupa JK, Odhner D et al (2005) A system for brain tumor volume estimation via MR imaging and fuzzy connectedness. Comput Med Imaging Graph 29:21–34CrossRefGoogle Scholar
  7. 7.
    Vijayakumar C, Damayanti G, Pant R, Sreedhar CM (2007) Segmentation and grading of brain tumors on apparent diffusion coefficient images using self-organizing maps. Comput Med Imaging Graph 31:473–484CrossRefGoogle Scholar
  8. 8.
    Corso JJ, Sharon E, Dube S et al (2008) Efficient multilevel brain tumor segmentation with integrated bayesian model classification. IEEE Trans Med Imaging 27:629–640CrossRefGoogle Scholar
  9. 9.
    Wang T, Cheng I, Basu A (2009) Fluid vector flow and applications in brain tumor segmentation. IEEE Trans Biomed Eng 56:781–789CrossRefGoogle Scholar
  10. 10.
    Khotanlou H, Colliot O, Atif J, Bloch I (2009) 3D brain tumor segmentation in MRI using fuzzy classification, symmetry analysis and spatially constrained deformable models. Fuzzy Sets Syst 160:1457–1473MathSciNetCrossRefGoogle Scholar
  11. 11.
    Cordier N, Menze B, Delingette H, Ayache N (2013) Patch-based segmentation of brain tissues. In: Menze B, Reyes M, Jakab A, Gerstner E, Kirby J, Kalpathy-Cramer J, Farahani K (eds) MICCAI chall. Multimodal brain tumor segmentation. IEEE, Nagoya, pp 6–17Google Scholar
  12. 12.
    Doyle S, Vasseur F, Dojat M, Forbes F (2013) Fully automatic brain tumor segmentation from multiple MR sequences using hidden Markov fields and variational EM. In: Menze B, Reyes M, Jakab A, Gerstner E, Kirby J, Kalpathy-Cramer J, Farahani K (eds) MICCAI chall. Multimodal brain tumor segmentation. IEEE, Nagoya, pp 18–22Google Scholar
  13. 13.
    Festa J, Pereira S, Mariz JA et al (2013) Automatic brain tumor segmentation of multi-sequence MR images using random decision forests. In: Menze B, Reyes M, Jakab A, Gerstner E, Kirby J, Kalpathy-Cramer J, Farahani K (eds) MICCAI chall. Multimodal brain tumor segmentation. IEEE, Nagoya, pp 23–26Google Scholar
  14. 14.
    Meier R, Bauer S, Slotboom J et al (2013) A hybrid model for multimodal brain tumor segmentation. In: Menze B, Reyes M, Jakab A, Gerstner E, Kirby J, Kalpathy-Cramer J, Farahani K (eds) MICCAI chall. Multimodal brain tumor segmentation. IEEE, Nagoya, pp 31–37Google Scholar
  15. 15.
    Reza S, Iftekharuddin KM (2013) Multi-class abnormal brain tissue segmentation using texture features. In: Menze B, Reyes M, Jakab A, Gerstner E, Kirby J, Kalpathy-Cramer J, Farahani K (eds) MICCAI chall. Multimodal brain tumor segmentation. IEEE, Nagoya, pp 38–42Google Scholar
  16. 16.
    Zhao L, Sarikaya D, Corso JJ (2013) Automatic brain tumor segmentation with MRF on supervoxels. In: Menze B, Reyes M, Jakab A, Gerstner E, Kirby J, Kalpathy-Cramer J, Farahani K (eds) MICCAI chall. Multimodal brain tumor segmentation. IEEE, Nagoya, pp 51–57Google Scholar
  17. 17.
    Geremia E, Menze BH, Ayache N (2012) Spatial decision forests for glioma segmentation in multi-channel MR images. In: MICCAI chall. Multimodal brain tumor segmentation. pp 14–18Google Scholar
  18. 18.
    Parisot S, Wells W, Chemouny S et al (2014) Concurrent tumor segmentation and registration with uncertainty-based sparse non-uniform graphs. Med Image Anal 18:647–659CrossRefGoogle Scholar
  19. 19.
    Njeh I, Sallemi L, Ben AI et al (2015) 3D multimodal MRI brain glioma tumor and edema segmentation: a graph cut distribution matching approach. Comput Med Imaging Graph 40:108–119CrossRefGoogle Scholar
  20. 20.
    Chaddad A (2015) Automated feature extraction in brain tumor by magnetic resonance imaging using gaussian mixture models. J Biomed Imaging 2015:8Google Scholar
  21. 21.
    Mokji MM, Abu Bakar SAR (2007) Adaptive thresholding based on co-occurrence matrix edge information. J Comput 2:44–52CrossRefGoogle Scholar
  22. 22.
    Panda R, Agrawal S, Bhuyan S (2013) Expert systems with applications edge magnitude based multilevel thresholding using Cuckoo search technique. Expert Syst Appl 40:7617–7628CrossRefGoogle Scholar
  23. 23.
    Vidya KS, Ng EY, Acharya UR et al (2015) Computer-aided diagnosis of myocardial infarction using ultrasound images with DWT, GLCM and HOS methods: a comparative study. Comput Biol Med 62:86–93CrossRefGoogle Scholar
  24. 24.
    Acharya UR, Faust O, Sree SV et al (2012) ThyroScreen system: high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform. Comput Methods Programs Biomed 107:233–241CrossRefGoogle Scholar
  25. 25.
    Sathya PD, Kayalvizhi R (2011) Amended bacterial foraging algorithm for multilevel thresholding of magnetic resonance brain images. Measurement 44:1828–1848CrossRefGoogle Scholar
  26. 26.
    Sathya PD, Kayalvizhi R (2011) Modified bacterial foraging algorithm based multilevel thresholding for image segmentation. Eng Appl Artif Intell 24:595–615CrossRefGoogle Scholar
  27. 27.
    Manikandan S, Ramar K, Iruthayarajan MW, Srinivasagan KG (2014) Multilevel thresholding for segmentation of medical brain images using real coded genetic algorithm. Measurement 47:558–568CrossRefGoogle Scholar
  28. 28.
    Bhandari AK, Kumar A, Singh GK (2015) Modified artificial bee colony based computationally efficient multilevel thresholding for satellite image segmentation using kapur’s, otsu and tsallis functions. Expert Syst Appl 42:1573–1601CrossRefGoogle Scholar
  29. 29.
    Andrews PS (2006) An investigation into mutation operators for particle swarm optimization. In: 2006 IEEE international conference evolutionary computation. IEEE, Vancouver, pp 1044–1051Google Scholar
  30. 30.
    Kennedy J, Eberhart R (1995) Particle swarm optimization. In: International conference on neural networks (ICNN’95). IEEE, Perth, pp 1942–1948Google Scholar
  31. 31.
    Ratnaweera A, Halgamuge SK, Watson HC (2004) Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients. IEEE Trans Evol Comput 8:240–255CrossRefGoogle Scholar
  32. 32.
    Shi Y, Eberhart RC (1999) Emperical study of particle swarm optimization. In: IEEE congress on evolutionary computation. IEEE, Washington, DC, pp 101–106Google Scholar
  33. 33.
    Menze BH, Jakab A, Bauer S et al (2014) The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging 34:1993–2024CrossRefGoogle Scholar
  34. 34.
    Islam A, Reza SMS, Iftekharuddin KM (2013) Multifractal texture estimation for detection and segmentation of brain tumors. IEEE Trans Biomed Eng 60:3204–3215CrossRefGoogle Scholar
  35. 35.
    Chaira T (2011) A novel intuitionistic fuzzy C means clustering algorithm and its application to medical images. Appl Soft Comput 11:1711–1717CrossRefGoogle Scholar
  36. 36.
    Saba L, Gao H, Raz E et al (2014) Semiautomated analysis of carotid artery wall thickness in MRI. J Magn Reson Imaging 39:1457–1467CrossRefGoogle Scholar
  37. 37.
    Acharya UR, Sree SV, Kulshreshtha S et al (2014) GyneScan: an improved online paradigm for screening of ovarian cancer via tissue characterization. Technol Cancer Res Treat 13:529–539. doi: 10.7785/tcrtexpress.2013.600273 CrossRefGoogle Scholar
  38. 38.
    Acharya UR, Sree SV, Saba L et al (2013) Ovarian tumor characterization and classification using ultrasound—a new online paradigm. J Digit Imaging 26:544–553CrossRefGoogle Scholar
  39. 39.
    Acharya UR, Mookiah MRK, Vinitha Sree S et al (2013) Atherosclerotic plaque tissue characterization in 2D ultrasound longitudinal carotid scans for automated classification: a paradigm for stroke risk assessment. Med Biol Eng Comput 51:513–523CrossRefGoogle Scholar
  40. 40.
    Leong SS, Vijayananthan A, Yaakup NA et al (2016) Observer performance in characterization of carotid plaque texture and surface characteristics with 3D versus 2D ultrasound. Comput Biol Med 78:58–64CrossRefGoogle Scholar
  41. 41.
    Acharya UR, Raghavendra U, Fujita H et al (2016) Automated characterization of fatty liver disease and cirrhosis using curvelet transform and entropy features extracted from ultrasound images. Comput Biol, MedGoogle Scholar
  42. 42.
    Acharya UR, Sree SV, Ribeiro R et al (2012) Data mining framework for fatty liver disease classification in ultrasound: a hybrid feature extraction paradigm. Med Phys 39:4255CrossRefGoogle Scholar
  43. 43.
    Acharya UR, Faust O, Sree SV et al (2012) An accurate and generalized approach to plaque characterization in 346 carotid ultrasound scans. IEEE Trans Instrum Meas 61:1045–1053CrossRefGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2016

Authors and Affiliations

  • Taranjit Kaur
    • 1
  • Barjinder Singh Saini
    • 1
  • Savita Gupta
    • 2
  1. 1.Department of Electronics and Communication EngineeringDr. B. R. Ambedkar National Institute of TechnologyJalandharIndia
  2. 2.Department of Computer Science and Engineering, UIET, Sector 25Panjab UniversityChandigarhIndia

Personalised recommendations