An intensity factorized thresholding based segmentation technique with gradient discrete wavelet fusion for diagnosing stroke and tumor in brain MRI

  • B. DeepaEmail author
  • M. G. Sumithra


The detection of a brain tumor and stroke from the magnetic resonance imaging (MRI) is one of the critical tasks in recent days for neuro-radiologists. So, various segmentation techniques are developed customarily, but it fails to provide an accurate diagnosis. To elucidate this problem, this paper aims to develop a fusion based segmentation technique for the detection of MRI brain tumor and stroke. The MRI brain images considered here include T1-weighted (T1-w), T2-weighted (T2-w), Diffusion Weighted Imaging (DWI), and Fluid-attenuated Inversion Recovery (FLAIR). The first step in the proposed methodology includes Gradient based Discrete Wavelet Transform as an image fusion technique with the target gradient estimation process. The different image fusion combinations include T1-w and T2-w, T1-w and DWI, T1-w and FLAIR, T2-w and DWI, T2-w and FLAIR, DWI and FLAIR. Secondly, the visual quality of the image is improved by applying the histogram equalization method. Finally, an Intensity Factorized Thresholding technique is proposed for segmentation in order to emphasis the diagnosis of tumor and stroke affected region in the given MRI brain image based on the pixel intensity. Here, the segmented results of both original (non-fused) and fused images are evaluated for predicting the accurate region of tumor and stroke. During experiments, the performance of both existing and proposed techniques are evaluated by using various measures like sensitivity, specificity, accuracy, Positive Predictive Value, Negative Predictive Value, Rand Index, Global Consistency Error, Variation of Information, Jaccard and Dice coefficients. From the obtained result, it is concluded that fusion based segmentation technique is giving better results than non-fusion based segmentation techniques. Among the fusion based segmented result, T2-w and FLAIR fused segmented result is superior to other fusion combinations for detecting tumor. Similarly, DWI and FLAIR fused segmented result is better than other fusion combinations for diagnosing stroke.


Image fusion Magnetic resonance image (MRI) Tumor and stroke detection Histogram equalization Discrete wavelet transformation Intensity factorized segmentation 



  1. Baselice, F., Ferraioli, G., & Pascazio, V. (2015). A novel statistical approach for brain MR images segmentation based on relaxation times. BioMed Research International, vol. 2015.Google Scholar
  2. Bauer, S., Wiest, R., Nolte, L.-P., & Reyes, M. (2013). A survey of MRI-based medical image analysis for brain tumor studies. Physics in Medicine & Biology, 58, R97.CrossRefGoogle Scholar
  3. Bojorquez, J. Z., Bricq, S., Walker, P. M., & Lalande, A. (2015). Automatic classification of tissues using T1 and T2 relaxation times from prostate MRI: A step towards generation of PET/MR attenuation map. In 2015 IEEE international conference on image processing (ICIP), 2015, pp. 1185–1189.Google Scholar
  4. Chavan, S. S., Mahajan, A., Talbar, S. N., Desai, S., Thakur, M., & D’cruz, A. (2017). Nonsubsampled rotated complex wavelet transform (NSRCxWT) for medical image fusion related to clinical aspects in neurocysticercosis. Computers in Biology and Medicine, 81, 64–78.CrossRefGoogle Scholar
  5. Deepa, M. G. S. B. (2016). An intelligent hybrid approach for brain pathology detection in MRI images. Pakistan Journal of Biotechnology, 13, 7–12.Google Scholar
  6. El-Dahshan, E.-S. A., Mohsen, H. M., Revett, K., & Salem, A.-B. M. (2014). Computer-aided diagnosis of human brain tumor through MRI: A survey and a new algorithm. Expert Systems with Applications, 41, 5526–5545.CrossRefGoogle Scholar
  7. Griffis, J. C., Allendorfer, J. B., & Szaflarski, J. P. (2016). Voxel-based Gaussian naïve Bayes classification of ischemic stroke lesions in individual T1-weighted MRI scans. Journal of Neuroscience Methods, 257, 97–108.CrossRefGoogle Scholar
  8. Gupta, N., & Mittal, A. (2014). Brain Ischemic stroke segmentation: A survey. Journal of Multi Disciplinary Engineering Technologies, 8, 1.Google Scholar
  9. Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., et al. (2017). Brain tumor segmentation with deep neural networks. Medical Image Analysis, 35, 18–31.CrossRefGoogle Scholar
  10. He, Z., Wang, X., Wu, Y., Jia, J., Hu, Y., Yang, X., et al. (2014). Treadmill pre-training ameliorates brain edema in ischemic stroke via down-regulation of aquaporin-4: an MRI study in rats. PLoS ONE, 9, e84602.CrossRefGoogle Scholar
  11. Huijts, M., Duits, A., Van Oostenbrugge, R. J., Kroon, A. A., De Leeuw, P. W., & Staals, J. (2013). Accumulation of MRI markers of cerebral small vessel disease is associated with decreased cognitive function: A study in first-ever lacunar stroke and hypertensive patients. Frontiers in Aging Neuroscience, 5, 72.CrossRefGoogle Scholar
  12. Ilunga-Mbuyamba, E., Avina-Cervantes, J. G., Garcia-Perez, A., de Jesus Romero-Troncoso, R., Aguirre-Ramos, H., Cruz-Aceves, I., et al. (2017). Localized active contour model with background intensity compensation applied on automatic MR brain tumor segmentation. Neurocomputing, 220, 84–97.CrossRefGoogle Scholar
  13. Karthikeyan, S., & Ezhilarasi, M. (2016). Automatic stroke lesion segmentation from diffusion weighted MRI IMAGES. International Journal of Advanced Engineering Tech, 111, 115.Google Scholar
  14. Li, Y., Jia, F., & Qin, J. (2016). Brain tumor segmentation from multimodal magnetic resonance images via sparse representation. Artificial Intelligence in Medicine, 73, 1–13.CrossRefGoogle Scholar
  15. Liu, X., Mei, W., & Du, H. (2017). Structure tensor and nonsubsampled shearlet transform based algorithm for CT and MRI image fusion. Neurocomputing, 235, 131–139.CrossRefGoogle Scholar
  16. Mahmood, Q., Li, S., Fhager, A., Candefjord, S., Chodorowski, A., Mehnert, A., et al. (2015). A comparative study of automated segmentation methods for use in a microwave tomography system for imaging intracerebral hemorrhage in stroke patients. Journal of Electromagnetic Analysis and Applications, 7, 152.CrossRefGoogle Scholar
  17. Maier, O., Wilms, M., & Handels, H. (2015). Random forests with selected features for stroke lesion segmentation. Ischemic Stroke Lesion Segmentation, p. 17.Google Scholar
  18. Menze, B. H., Jakab, A., Bauer, S., Kalpathy-Cramer, J., Farahani, K., Kirby, J., et al. (2015). The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Transactions on Medical Imaging, 34, 1993.CrossRefGoogle Scholar
  19. Menze, B. H., Van Leemput, K., Lashkari, D., Riklin-Raviv, T., Geremia, E., Alberts, E., et al. (2016). A generative probabilistic model and discriminative extensions for brain lesion segmentation—with application to tumor and stroke. IEEE Transactions on Medical Imaging, 35, 933–946.CrossRefGoogle Scholar
  20. Pereira, S., Pinto, A., Alves, V., & Silva, C. A. (2016). Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Transactions on Medical Imaging, 35, 1240–1251.CrossRefGoogle Scholar
  21. Reza, S. M., Pei, L., & Iftekharuddin, K. (2015). Ischemic stroke lesion segmentation using local gradient and texture features. Ischemic Stroke Lesion Segmentation, p. 23.Google Scholar
  22. Staals, J., Makin, S. D., Doubal, F. N., Dennis, M. S., & Wardlaw, J. M. (2014). Stroke subtype, vascular risk factors, and total MRI brain small-vessel disease burden. Neurology, 83, 1228–1234.CrossRefGoogle Scholar
  23. Vishnuvarthanan, G., Rajasekaran, M. P., Subbaraj, P., & Vishnuvarthanan, A. (2016). An unsupervised learning method with a clustering approach for tumor identification and tissue segmentation in magnetic resonance brain images. Applied Soft Computing, 38, 190–212.CrossRefGoogle Scholar
  24. Wang, Y., Katsaggelos, A. K., Wang, X., & Parrish, T. B. (2016). A deep symmetry convnet for stroke lesion segmentation. In Image processing (ICIP), 2016 IEEE international conference on, 2016, pp. 111–115.Google Scholar
  25. Wei, Y., & Brown, H. K. (2015). A novel segmentation approach for brain tumor in MRI.Google Scholar
  26. Xu, X., Wang, Y., & Chen, S. (2016a). Medical image fusion using discrete fractional wavelet transform. Biomedical Signal Processing and Control, 27, 103–111.CrossRefGoogle Scholar
  27. Xu, X., Wang, Y., Yang, G., & Hu, Y. (2016). Image enhancement method based on fractional wavelet transform. In Signal and image processing (ICSIP), IEEE international conference on, 2016, pp. 194–197.Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of ECEJayaram College of Engineering and TechnologyTrichyIndia
  2. 2.Department of ECEKPR Institute of Engineering and TechnologyCoimbatoreIndia

Personalised recommendations