Document Type : Original/Review Paper

Authors

1 Computer Engineering Department, Rasht Branch, Islamic Azad University, Rasht, Iran.

2 Computer Engineering Department, Karaj Branch, Islamic Azad University, Karaj, Iran.

Abstract

Multiple Sclerosis (MS) is a disease that destructs the central nervous system cell protection, destroys sheaths of immune cells, and causes lesions. Examination and diagnosis of lesions by specialists is usually done manually on Magnetic Resonance Imaging (MRI) images of the brain. Factors such as small sizes of lesions, their dispersion in the brain, similarity of lesions to some other diseases, and their overlap can lead to the misdiagnosis. Automatic image detection methods as auxiliary tools can increase the diagnosis accuracy. To this end, traditional image processing methods and deep learning approaches have been used. Deep Convolutional Neural Network is a common method of deep learning to detect lesions in images. In this network, the convolution layer extracts the specificities; and the pooling layer decreases the specificity map size. The present research uses the wavelet-transform-based pooling. In addition to decomposing the input image and reducing its size, the wavelet transform highlights sharp changes in the image and better describes local specificities. Therefore, using this transform can improve the diagnosis. The proposed method is based on six convolutional layers, two layers of wavelet pooling, and a completely connected layer that had a better amount of accuracy than the studied methods. The accuracy of 98.92%, precision of 99.20%, and specificity of 98.33% are obtained by testing the image data of 38 patients and 20 healthy individuals.

Keywords

[1] C. H. Polman et al., "Diagnostic criteria for multiple sclerosis: 2010 revisions to the McDonald criteria," (in eng), Annals of neurology, Vol 69, No 2, pp. 292-302, 2011.
[2] D. S. Reich, C. F. Lucchinetti, and P. A. Calabresi, "Multiple Sclerosis",  New England Journal of Medicine, Vol 378, No 2, pp. 169-180, 2018.
[3] E. Erbayat Altay, E. Fisher, S. E. Jones, C. Hara-Cleaver, J. C. Lee, and R. A. Rudick, "Reliability of classifying multiple sclerosis disease activity using magnetic resonance imaging in a multiple sclerosis clinic," (in eng), JAMA Neurol, Vol 70, No 3, pp. 338-44, Mar. 1 2013.
[4] P. Mao and P. H. Reddy, "Is multiple sclerosis a mitochondrial disease?," (in eng), Biochimica et biophysica acta, Vol 1802, No 1, pp. 66-79, 2010.
[5] M. A. Battaglia, P. Zagami, and M. M. Uccelli, "A cost evaluation of multiple sclerosis," (in eng), J Neurovirol, Vol 6 Suppl 2, pp. S191-3, May 2000.
[6] M. Azami, M. H. YektaKooshali, M. Shohani, A. Khorshidi, and L. Mahmudi, "Epidemiology of multiple sclerosis in Iran: A systematic review and meta-analysis," (in eng), PloS one, Vol 14, No 4, pp. e0214738-e0214738, 2019.
[7] C. Miltenburger and G. Kobelt, "Quality of life and cost of multiple sclerosis," Clinical neurology and neurosurgery, Vol 104, pp. 272-5, 08/01 2002.
[8] N. N. Sommer et al., "Multiple Sclerosis: Improved Detection of Active Cerebral Lesions With 3-Dimensional T1 Black-Blood Magnetic Resonance Imaging Compared With Conventional 3-Dimensional T1 GRE Imaging," (in eng), Invest Radiol, Vol 53, No 1, pp. 13-19, Jan 2018.
[9] A. J. Thompson et al., "Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria," (in eng), Lancet Neurol, Vol 17, No 2, pp. 162-173, Feb 2018.
[10] M. Filippi et al., "MRI criteria for the diagnosis of multiple sclerosis: MAGNIMS consensus guidelines," (in eng), Lancet Neurol, Vol 15, No 3, pp. 292-303, Mar 2016.
[11] R. Zivadinov, M. Zorzon, R. De Masi, D. Nasuelli, and G. Cazzato, "Effect of intravenous methylprednisolone on the number, size and confluence of plaques in relapsing-remitting multiple sclerosis," (in eng), J Neurol Sci, Vol 267, No 1-2, pp. 28-35, Apr 15 2008.
[12] S. Jain et al., "Automatic segmentation and volumetry of multiple sclerosis brain lesions from MR images," (in eng), NeuroImage. Clinical, Vol 8, pp. 367-375, 2015.
[13] J. D. Dworkin et al., "An Automated Statistical Technique for Counting Distinct Multiple Sclerosis Lesions," (in eng), AJNR Am J Neuroradiol, Vol 39, No 4, pp. 626-633, Apr 2018.
[14] Y. Zhao et al., "A level set method for multiple sclerosis lesion segmentation," (in eng), Magn Reson Imaging, Vol 49, pp. 94-100, Jun 2018.
[15] F. Chollet, Deep Learning with Python. Manning Publications Co., 2017.
[16] M. D. Zeiler and R. Fergus, "Stochastic Pooling for Regularization of Deep Convolutional Neural Networks," arXiv e-prints, p. arXiv:1301.3557, 2013.
[17] N. Boussion et al., "A multiresolution image based approach for correction of partial volume effects in emission tomography," Physics in Medicine and Biology, Vol 51, No 7, pp. 1857-1876, 2006.
[18] J. Sun, M. Yao, B. Xu, and P. Bel, "Fabric wrinkle characterization and classification using modified wavelet coefficients and support-vector-machine classifiers," Textile Research Journal, Vol 81, pp. 902-913, 06/01 2011.
[19] M. Stéphane, "CHAPTER 7 - Wavelet Bases," in A Wavelet Tour of Signal Processing (Third Edition), M. Stéphane, Ed. Boston: Academic Press, 2009, pp. 263-376.
[20] W. van Drongelen, Signal processing for neuroscientists: Introduction to the analysis of physiological signals. Academic Press, 2007.
[21] O. Ghribi, L. Sellami, M. Ben Slima, A. Ben Hamida, C. Mhiri, and K. B. Mahfoudh, "An Advanced MRI Multi-Modalities Segmentation Methodology Dedicated to Multiple Sclerosis Lesions Exploration and Differentiation," (in eng), IEEE Trans Nanobioscience, Vol 16, No 8, pp. 656-665, Dec 2017.
[22] Y.-D. Zhang, Y. Zhang, P. Phillips, Z. Dong, and S. Wang, "Synthetic Minority Oversampling Technique and Fractal Dimension for Identifying Multiple Sclerosis," Fractals, Vol 25, January 01, pp. 57-64, 2017.
[23] W. Xueyan and L. Mason, "Multiple Sclerosis Slice Identification by Haar Wavelet Transform and Logistic Regression," in Advances in Materials, Machinery, Electrical Engineering (AMMEE 2017), 2017: Atlantis Press.
[24] C. Wachinger, M. Reuter, and T. Klein, "DeepNAT: Deep convolutional neural network for segmenting neuroanatomy," NeuroImage, Vol 170, pp. 434-445, 2018/04/15/ 2018.
[25] H. Chen, Q. Dou, L. Yu, J. Qin, and P.-A. Heng, "VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images," NeuroImage, Vol 170, pp. 446-455, 2018/04/15/ 2018.
[26] W. Wells, W. E. L. Grimson, R. Kikinis, and F. Jolesz, "Adaptive segmentation of MRI data," Medical Imaging, IEEE Transactions on, Vol 15, pp. 429-442, 09/01 1996.
[27] F. Forbes, S. Doyle, D. García-Lorenzo, C. Barillot, and M. Dojat, Adaptive weighted fusion of multiple MR sequences for brain lesion segmentation. 2010, pp. 69-72.
[28] Y.-D. Zhang, C. Pan, J. Sun, and C. Tang, "Multiple sclerosis identification by convolutional neural network with dropout and parametric ReLU," Journal of Computational Science, Vol 28, pp. 1-10, 2018/09/01/ 2018.
[29] S.-H. Wang et al., "Multiple Sclerosis Identification by 14-Layer Convolutional Neural Network With Batch Normalization, Dropout, and Stochastic Pooling," (in eng), Frontiers in neuroscience, Vol 12, pp. 818-818, 2018.
 
[30] T. Williams and R. Li, "Wavelet Pooling for Convolutional Neural Networks," in International Conference on Learning Representations, Vancouver, BC, Canada, 2018.
[31] A. M. Rossetto and W. Zhou, "Improving Classification with CNNs using Wavelet Pooling with Nesterov-Accelerated Adam," in Proceedings of 11th International Conference on Bioinformatics and Computational Biology Vol 60, ed: EasyChair, 2019, pp. 1-14.
[32] A. A. M. Abadi, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, M. Devin, S. Ghemawat, I. J. Goodfellow, A. Harp, G. Irving, M. Isard, Y. Jia, R. Józefowicz, L. Kaiser, M. Kudlur, J. Levenberg, D. Mane, R. Monga, S. Moore, D. G. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. A. Tucker, V. Vanhoucke, V. Vasudevan, F. B. Viégas, O. Vinyals, P. Warden, M. Wattenberg, M. Wicke, Y. Yu, and X. Zheng. , "TensorFlow: A System for Large-Scale Machine Learning," presented at the 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16), Savannah, GA, 2016.