Deep CNN based MR image denoising for tumor segmentation using watershed transform

  • Authors

    • Ghazanfar Latif
    • D N.F. Awang Iskandar
    • Jaafar Alghazo
    • Mohsin Butt
    • Adil H. Khan
    https://doi.org/10.14419/ijet.v7i2.3.9964

    Received date: March 8, 2018

    Accepted date: March 8, 2018

    Published date: March 8, 2018

  • Deep CNN Denoising, Brain Tumor Segmentation, Anisotropic Diffusion, BraTS MRI, Rician Noise

  • Abstract

    Magnetic Resonance Imaging (MRI) is considered one of the most effective imaging techniques used in the medical field for both clinical investigation and diagnosis. This is due to the fact that MRI provides many critical features of the tissue including both physiological and chemical information. Rician noise affects MR images during acquisition thereby reducing the quality of the image and complicating the accurate diagnosis. In this paper, we propose a novel technique for MR image denoising using Deep Convolutional Neural Network (Deep CNN) and anisotropic diffusion (AD) which we will refer to as Deep CNN-AD. Watershed transform is then used to segment the tumorous portion of the denoised image.   The proposed method is tested on the BraTS MRI datasets. The proposed denoising method produced better results compared to previous methods. As denoising process affect the segmentation process therefore better denoised images by proposed technique produced more accurate segmentation with an average Specificity of 99.85% and dice coefficient of 90.46% thus indicating better performance of proposed technique.

  • References

    1. Kural, C., Pusat, S., Şentürk, T., Seçer, H.İ. and İzci, Y., (2011), “Extracranial metastases of anaplastic oligodendroglioma”, Journal of Clinical Neuroscience, 18(1), pp.136-138.
    2. Louis, D.N., Ohgaki, H., Wiestler, O.D., Cavenee, W.K., Burger, P.C., Jouvet, A., Scheithauer, B.W. and Kleihues, P., (2007) “The 2007 WHO classification of tumours of the central nervous system”, Acta neuropathologica, 114(2), pp.97-109.
    3. Van Meir, E.G., Hadjipanayis, C.G., Norden, A.D., Shu, H.K., Wen, P.Y. and Olson, J.J., (2010), “Exciting new advances in neu-ro‐oncology: The avenue to a cure for malignant glioma”, CA: a cancer journal for clinicians, 60(3), pp.166-193.
    4. Link, M.J. and Perry, A., (2009), “Meningioma Tumorigenesis: An Overview of Etiologic Factors”, In Meningiomas (pp. 137-145). Springer London.
    5. Nag, M.K., Koley, S., Chakraborty, C. and Sadhu, A.K., (2015), “Magnetic Resonance Image Quality Enhancement Using Trans-form Based Hybrid Filtering”, In Advancements of Medical Elec-tronics (pp. 39-48). Springer, New Delhi.
    6. Garg, S. and Kaur, J., (2013), “Improving segmentation by de-noising brain MRI images through interpolation median filter in ADTVFCM”, International Journal of Computer Trends and Tech-nology, 4(2), pp.187-188.
    7. Khan, A., Alasad, J. and Latif, G., (2017), “Speckle Suppression in Medical Ultrasound Images through Schur Decomposition”, IET Image Processing.
    8. Menze, B.H., Jakab, A., Bauer, S., Kalpathy-Cramer, J., Farahani, K., Kirby, J., Burren, Y., Porz, N., Slotboom, J., Wiest, R. and Lanczi, L., (2015), “The multimodal brain tumor image segmenta-tion benchmark (BRATS)”, IEEE transactions on medical imaging, 34(10), pp.1993-2024. Vancouver
    9. Balafar, M.A., Ramli, A.R., Saripan, M.I. and Mashohor, S., (2010), “Review of brain MRI image segmentation methods”, Artificial In-telligence Review, 33(3), pp.261-274.
    10. M.A .Balafar, (2012), “Review of noise reducing algorithms for brain MRI images”, International Journal on Technical and Physical Problems of Engineering, Published by International Organization of IOTPE,Vol.4,Issue 13,No. 4,pp 54-59.
    11. Perona, P. and Malik, J., (1990), “Scale-space and edge detection using anisotropic diffusion”, IEEE Transactions on pattern analysis and machine intelligence, 12(7), pp.629-639.
    12. Jaffar, M. A., Zia, S., Latif, G., Mirza, A. M., Mehmood, I., Ejaz, N., & Baik, S. W. (2012), “Anisotropic diffusion based brain MRI segmentation and 3D reconstruction”, International Journal of Computational Intelligence Systems, 5(3), 494-504.
    13. Luisier, F. and Wolfe, P.J., (2011), “Chi-square unbiased risk esti-mate for denoising magnitude MR images”, In Image Processing (ICIP), 2011 18th IEEE International Conference on (pp. 1561-1564). IEEE.
    14. Buades, A., Coll, B. and Morel, J.M., (2005), “A non-local algo-rithm for image denoising”, In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Confer-ence on (Vol. 2, pp. 60-65). IEEE.
    15. Tomasi C, Manduchi R (1998), “Bilateral filtering for gray and col-or images”, In Proceedings of the sixth international conference on computer vision, pp 839–846.
    16. Prima, S. and Commowick, O., (2013), “Using bilateral symmetry to improve non-local means denoising of MR brain images”, In Bi-omedical Imaging (ISBI), 2013 IEEE 10th International Symposi-um on (pp. 1231-1234). IEEE.
    17. Golshan, H.M. and Hasanzadeh, R.P., (2013), “A modified Rician LMMSE estimator for the restoration of magnitude MR images”, Optik-International Journal for Light and Electron Optics, 124(16), pp.2387-2392.
    18. Manjón, J.V., Coupé, P., Buades, A., Collins, D.L. and Robles, M., (2012), “New methods for MRI denoising based on sparseness and self-similarity”, Medical image analysis, 16(1), pp.18-27.
    19. Zhang, C., Hu, W., Jin, T. and Mei, Z., (2016), “Nonlocal image denoising via adaptive tensor nuclear norm minimization”, Neural Computing and Applications, pp.1-17.
    20. Sharif, M., Hussain, A., Jaffar, M.A. and Choi, T.S., (2015), “Fuzzy similarity based non local means filter for rician noise removal”, Multimedia tools and applications, 74(15), pp.5533-5556.
    21. Pinheiro, P. and Collobert, R., (2014), “Recurrent convolutional neural networks for scene labeling”, In International Conference on Machine Learning, pp. 82-90.
    22. Farabet, C., Couprie, C., Najman, L. and LeCun, Y., (2013), “Learning hierarchical features for scene labeling”, IEEE transac-tions on pattern analysis and machine intelligence, 35(8), pp.1915-1929.
    23. Long, J., Shelhamer, E. and Darrell, T., (2015)), “Fully convolution-al networks for semantic segmentation”, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431-3440.
    24. Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., Pal, C., Jodoin, P.M. and Larochelle, H., (2017), “Brain tumor segmentation with deep neural networks”, Medical image analysis, 35, pp.18-31.
    25. Gauch, J.M., (1999), “Image segmentation and analysis via mul-tiscale gradient watershed hierarchies”, IEEE transactions on image processing, 8(1), pp.69-79.
    26. Pal, C., Das, P., Chakrabarti, A., & Ghosh, R., (2017), “Rician noise removal in magnitude MRI images using efficient anisotropic diffu-sion filtering”, International Journal of Imaging Systems and Tech-nology, 27(3), 248-264.
    27. Zhang, K., Zuo, W., Chen, Y., Meng, D., & Zhang, L., (2017), “Beyond a gaussian denoiser: Residual learning of deep cnn for im-age denoising”, IEEE Transactions on Image Processing.
    28. Gao, W., Zhang, X., Yang, L., & Liu, H., (2010), “An improved Sobel edge detection”, In 3rd International Conference on Comput-er Science and Information Technology (ICCSIT), Vol. 5, pp. 67-71, IEEE.
    29. Latif, G., Iskandar, D. A., Jaffar, A., & Butt, M. M. (2017). Multi-modal Brain Tumor Segmentation using Neighboring Image Fea-tures. Journal of Telecommunication, Electronic and Computer En-gineering (JTEC), 9(2-9), 37-42.
    30. Wiest-Daesslé, N., Prima, S., Coupé, P., Morrissey, S. P., & Barillot, C., (2008), “Rician noise removal by non-local means filtering for low signal-to-noise ratio MRI: applications to DT-MRI”, In International Conference on Medical Image Computing and Computer-assisted Intervention, pp. 171-179. Springer, Berlin, Hei-delberg.
    31. Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., ... & Larochelle, H, (2017), “Brain tumor segmentation with deep neural networks”, Medical image analysis, 35, pp. 18-31.
    32. Pereira, S., Pinto, A., Alves, V., & Silva, C. A. (2016), “Brain tumor segmentation using convolutional neural networks in MRI imag-es”, IEEE transactions on medical imaging, 35(5), pp. 1240-1251.
    33. Kwon, D., Shinohara, R. T., Akbari, H., & Davatzikos, C., (2014), “Combining generative models for multifocal glioma segmentation and registration”, In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 763-770). Springer, Cham.
    34. Bauer, S., Nolte, L. P., & Reyes, M., (2011), “Fully automatic seg-mentation of brain tumor images using support vector machine clas-sification in combination with hierarchical conditional random field regularization”, In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 354-361). Springer, Berlin, Heidelberg.

  • Downloads

  • How to Cite

    Latif, G., N.F. Awang Iskandar, D., Alghazo, J., Butt, M., & H. Khan, A. (2018). Deep CNN based MR image denoising for tumor segmentation using watershed transform. International Journal of Engineering and Technology, 7(2.3), 37-42. https://doi.org/10.14419/ijet.v7i2.3.9964