Document Type : Original Article
Authors
Department of Electrical Engineering, University of Science and Culture, Tehran, Iran
Abstract
Multiple Sclerosis (MS) disease is immune disorder that destroys myelin in the nervous system and causes many complications including motor and sensory disorders. Nowadays, medical images including Magnetic Resonance Imaging (MRI) and Optical Coherence Tomography (OCT) are recognized as the basic tools in the diagnosis of MS disease. Due to the large amount of image data in this method, the use of machine learning methods, especially Neural Networks (NNs) plays an important role in image processing. This paper presents a comprehensive overview of different methods, which utilize NNs to MS diagnosis. This review presents the classical of NNs and Convolutional NNs (CNNs), which are used in the MS diagnosis. In addition, challenges, and recent developments in this field are presented, which provides directions for future researches in this field.
Keywords
[1]. B. A. C. Cree, J. R. Oksenberg, and S. L. Hauser, “Multiple sclerosis: two decades of progress,” Lancet Neurol, vol. 21, no. 3, pp. 211–214, 2022.
[2]. F. D. Lublin et al, “How patients with multiple sclerosis acquire disability,” Brain, vol. 145, no. 9, pp. 3147–3161, 2022.
[3]. R. Rahmanzadeh et al, “A new advanced MRI biomarker for remyelinated lesions in multiple sclerosis,” Ann. Neurol, vol. 92, no. 3, pp. 486–502, 2022.
[4]. A. Pal and Y. Rathi, “A review and experimental evaluation of deep learning methods for MRI reconstruction,” J. Mach. Learn. Biomed. imaging, vol. 1, 2022.
[5]. G. Goh et al, “Multimodal neurons in artificial neural networks,” Distill, vol. 6, no. 3, p. e30, 2021.
[6]. B. Souid, S. Yahia, T. Bouchrika, and O. Jemai, “Fusion of CNN and feature extraction methods for multiple sclerosis classification,” in Fifteenth International Conference on Machine Vision (ICMV 2022), SPIE, 2023, pp. 353–360.
[7]. L. Coll et al, “Global and Regional Deep Learning Models for Multiple Sclerosis Stratification From MRI,” J. Magn. Reson. Imaging, 2023.
[8]. G. Giovannoni, C. Hawkes, J. Lechner-Scott, M. Levy, E. Waubant, and J. Gold, “The COVID-19 pandemic and the use of MS disease-modifying therapies,” Mult. Scler. Relat. Disord, vol. 39, 2020.
[9]. R. Magliozzi and A. H. Cross, “Can CSF biomarkers predict future MS disease activity and severity?,” Mult. Scler. J, vol. 26, no. 5, pp. 582–590, 2020.
[10]. M. P. Sormani et al, “Disease‐modifying therapies and coronavirus disease 2019 severity in multiple sclerosis,” Ann. Neurol, vol. 89, no. 4, pp. 780–789, 2021.
[11]. R. Reda, A. Zanza, A. Mazzoni, A. Cicconetti, L. Testarelli, and D. Di Nardo, “An update of the possible applications of magnetic resonance imaging (MRI) in dentistry: a literature review,” J. imaging, vol. 7, no. 5, p. 75, 2021.
[12]. A. Tiwari, S. Srivastava, and M. Pant, “Brain tumor segmentation and classification from magnetic resonance images: Review of selected methods from 2014 to 2019,” Pattern Recognit. Lett, vol. 131, pp. 244–260, 2020.
[13]. N. Weiskopf, L. J. Edwards, G. Helms, S. Mohammadi, and E. Kirilina, “Quantitative magnetic resonance imaging of brain anatomy and in vivo histology,” Nat. Rev. Phys, vol. 3, no. 8, pp. 570–588, 2021.
[14]. C. Z. Cooley et al, “A portable scanner for magnetic resonance imaging of the brain,” Nat. Biomed. Eng, vol. 5, no. 3, pp. 229–239, 2021.
[15]. G. R. Yang and X.-J. Wang, “Artificial neural networks for neuroscientists: a primer,” Neuron, vol. 107, no. 6, pp. 1048–1070, 2020.
[16]. N. Talpur, S. J. Abdulkadir, H. Alhussian, M. H. Hasan, N. Aziz, and A. Bamhdi, “Deep Neuro-Fuzzy System application trends, challenges, and future perspectives: a systematic survey,” Artif. Intell. Rev, vol. 56, no. 2, pp. 865–913, 2023, doi: 10.1007/s10462-022-10188-3.
[17]. X. Liu, S. Tian, F. Tao, and W. Yu, “A review of artificial neural networks in the constitutive modeling of composite materials,” Compos. Part B Eng, vol. 224, p. 109152, 2021.
[18]. F.-L. Fan, J. Xiong, M. Li, and G. Wang, “On interpretability of artificial neural networks: A survey,” IEEE Trans. Radiat. Plasma Med. Sci, vol. 5, no. 6, pp. 741–760, 2021.
[19]. S. Chung and L. F. Abbott, “Neural population geometry: An approach for understanding biological and artificial neural networks,” Curr. Opin. Neurobiol, vol. 70, pp. 137–144, 2021.
[20]. J. L. Semmlow and B. Griffel, Biosignal and medical image processing. CRC press, 2021.
[21]. X. Liu, L. Song, S. Liu, and Y. Zhang, “A review of deep-learning-based medical image segmentation methods,” Sustainability, vol. 13, no. 3, p. 1224, 2021.
[22]. Y. Li, J. Zhao, Z. Lv, and J. Li, “Medical image fusion method by deep learning,” Int. J. Cogn. Comput. Eng, vol. 2, pp. 21–29, 2021.
[23]. S. Farabi Maleki et al, “Artificial Intelligence for multiple sclerosis management using retinal images: pearl, peaks, and pitfalls,” in Seminars in Ophthalmology, Taylor & Francis, 2023, pp. 1–18.
[24]. N. Haj Messaoud et al, “Automated segmentation of multiple sclerosis lesions based on convolutional neural networks,” Comput. Methods Biomech. Biomed. Eng. Imaging Vis, vol. 11, no. 4, pp. 1359–1377, 2023.
[25]. M. Ortiz et al, “Diagnosis of multiple sclerosis using optical coherence tomography supported by artificial intelligence,” Mult. Scler. Relat. Disord, vol. 74, p. 104725, 2023.
[26]. F. Nabizadeh, E. Ramezannezhad, A. Kargar, A. M. Sharafi, and A. Ghaderi, “Diagnostic performance of artificial intelligence in multiple sclerosis: a systematic review and meta-analysis,” Neurol. Sci, vol. 44, no. 2, pp. 499–517, 2023.
[27]. J. M. Seok et al, “Differentiation between multiple sclerosis and neuromyelitis optica spectrum disorder using a deep learning model,” Sci. Rep, vol. 13, no. 1, p. 11625, 2023.
[28]. M. Filippi et al, “Present and future of the diagnostic work-up of multiple sclerosis: the imaging perspective,” J. Neurol, vol. 270, no. 3, pp. 1286–1299, 2023.
[29]. A. Montolío, J. Cegoñino, E. Garcia‐Martin, and A. Pérez del Palomar, “The macular retinal ganglion cell layer as a biomarker for diagnosis and prognosis in multiple sclerosis: A deep learning approach,” Acta Ophthalmol, 2023.
[30]. A. Kaur, L. Kaur, and A. Singh, “DeepCONN: patch-wise deep convolutional neural networks for the segmentation of multiple sclerosis brain lesions,” Multimed. Tools Appl, vol. 83, no. 8, pp. 24401–24433, 2024.
)