A Machine Learning Prediction Model for Myelitis and Multiple Sclerosis Based on Fourier Transform Features from MRI Images

Year 2024, , 860 - 870, 26.09.2024

Züleyha Yılmaz Acar

https://doi.org/10.17798/bitlisfen.1516713

Abstract

Myelitis is a neurodegenerative disease positioned in the spinal cord, with multiple sclerosis (MS) being a common subtype. Radiological indicators enable the diagnosis of these diseases. This study proposes a classification framework to detect myelitis, MS, and healthy control (HC) groups using magnetic resonance imaging (MRI) images. The feature extraction step involves applying the fast Fourier transform (FFT) to MRI images. FFT is important because it converts spatial data into the frequency domain, making it easier to identify patterns and abnormalities that indicate these diseases. Then, statistical features (mean, minimum, maximum, standard deviation, skewness, kurtosis, and total energy) are extracted from this frequency information. These features are then used to train support vector machine (SVM), k-nearest neighbor (KNN), and decision tree algorithms. In multi-class classification (myelitis vs. MS vs. HC), the proposed method achieves a classification accuracy of 99.31% with SVM, with average precision, recall, and F1-score values of 99.27%, 99.21%, and 99.24%, respectively, indicating effective classification across all classes. In the binary class classification (HC vs. MS, MS vs. myelitis, HC vs. myelitis), the SVM achieves an outstanding classification accuracy of 99.36%, 99.71%, and 100% respectively. This study highlights the efficiency of FFT-based feature extraction in forming detection patterns for classifying HC, MS, and myelitis classes.

Keywords

Disease detection, Fast Fourier transform, Machine learning, Myelitis, Neurodegenerative

References

• [1] E. Glucksman, C. Medina, J. Phillips, R. Schlussel, and S. Glucksman, "New onset urinary incontinence in a pediatric patient with transverse myelitis," Urol Case Rep, vol. 46, p. 102322, January 2023.
• [2] Y. S. Abuzneid, H. Al-Janazreh, M. Haif, S. T. Idais, B. Asakrah, S. M. Ajwa, et al., "Radiation induced delayed transverse myelitis and neurological deficit at tertiary care center," Ann Med Surg (Lond), vol. 69, p. 102728, September 2021.
• [3] S. Lopez Chiriboga and E. P. Flanagan, "Myelitis and Other Autoimmune Myelopathies," Continuum (Minneap Minn), vol. 27, pp. 62-92, February 2021.
• [4] S. Presas-Rodríguez, L. Grau-López, J. V. Hervás-García, A. Massuet-Vilamajó, and C. Ramo-Tello, "Myelitis: Differences between multiple sclerosis and other aetiologies," Neurología (English Edition), vol. 31, 2016, pp. 71-75.
• [5] Z. Yılmaz Acar, F. Başçiftçi, and A. H. Ekmekci, "Future activity prediction of multiple sclerosis with 3D MRI using 3D discrete wavelet transform," Biomedical Signal Processing and Control, vol. 78, p. 103940, September 2022.
• [6] M. K. Yagnavajjula, K. R. Mittapalle, P. Alku, S. R. K, and P. Mitra, "Automatic classification of neurological voice disorders using wavelet scattering features," Speech Communication, vol. 157, p. 103040, February 2024.
• [7] K. Hackmack, F. Paul, M. Weygandt, C. Allefeld, and J.-D. Haynes, "Multi-scale classification of disease using structural MRI and wavelet transform," NeuroImage, vol. 62, pp. 48-58, August 2012.
• [8] J. Feng, S.-W. Zhang, and L. Chen, "Identification of Alzheimer's disease based on wavelet transformation energy feature of the structural MRI image and NN classifier," Artificial Intelligence in Medicine, vol. 108, p. 101940, August 2020.
• [9] Z. Ding, Y. Liu, X. Tian, W. Lu, Z. Wang, X. Zeng, et al., "Multi-resolution 3D-HOG feature learning method for Alzheimer’s Disease diagnosis," Computer Methods and Programs in Biomedicine, vol. 214, p. 106574, February 2022.
• [10] E. Kaplan, M. Baygin, P. D. Barua, S. Dogan, T. Tuncer, E. Altunisik, et al., "ExHiF: Alzheimer’s disease detection using exemplar histogram-based features with CT and MR images," Medical Engineering & Physics, vol. 115, p. 103971, May 2023.
• [11] S. Abbasi and F. Tajeripour, "Detection of brain tumor in 3D MRI images using local binary patterns and histogram orientation gradient," Neurocomputing, vol. 219, pp. 526-535, January 2017.
• [12] Z. Yılmaz Acar, F. Başçiftçi, and A. H. Ekmekci, "A Convolutional Neural Network model for identifying Multiple Sclerosis on brain FLAIR MRI," Sustainable Computing: Informatics and Systems, vol. 35, p. 100706, September 2022.
• [13] P. Varalakshmi, B. Tharani Priya, B. Anu Rithiga, R. Bhuvaneaswari, and R. Sakthi Jaya Sundar, "Diagnosis of Parkinson's disease from hand drawing utilizing hybrid models," Parkinsonism & Related Disorders, vol. 105, pp. 24-31, December 2022.
• [14] I. K. Veetil, D. E. Chowdary, P. N. Chowdary, V. Sowmya, and E. A. Gopalakrishnan, "An analysis of data leakage and generalizability in MRI based classification of Parkinson's Disease using explainable 2D Convolutional Neural Networks," Digital Signal Processing, vol. 147, p. 104407, April 2024.
• [15] S. E. Sorour, A. A. A. El-Mageed, K. M. Albarrak, A. K. Alnaim, A. A. Wafa, and E. El-Shafeiy, "Classification of Alzheimer’s disease using MRI data based on Deep Learning Techniques," Journal of King Saud University - Computer and Information Sciences, vol. 36, p. 101940, February 2024.
• [16] M. Menagadevi, S. Devaraj, N. Madian, and D. Thiyagarajan, "Machine and deep learning approaches for alzheimer disease detection using magnetic resonance images: An updated review," Measurement, vol. 226, p. 114100, February 2024.
• [17] A. Basher, B. C. Kim, K. H. Lee, and H. Y. Jung, "Volumetric Feature-Based Alzheimer’s Disease Diagnosis From sMRI Data Using a Convolutional Neural Network and a Deep Neural Network," IEEE Access, vol. 9, pp. 29870-29882, 2021.
• [18] A. Ebrahimi, S. Luo, and A. s. D. Neuroimaging Initiative, "Convolutional neural networks for Alzheimer’s disease detection on MRI images," Journal of Medical Imaging, vol. 8, p. 024503, 2021.
• [19] D. Venkatesan, A. Elangovan, H. Winster, M. Y. Pasha, K. S. Abraham, S. J, et al., "Diagnostic and therapeutic approach of artificial intelligence in neuro-oncological diseases," Biosensors and Bioelectronics: X, vol. 11, p. 100188, September 2022.
• [20] S. Tatli, G. Macin, I. Tasci, B. Tasci, P. D. Barua, M. Baygin, et al., "Transfer-transfer model with MSNet: An automated accurate multiple sclerosis and myelitis detection system," Expert Systems with Applications, vol. 236, p. 121314, February 2024.
• [21] J. Kunhoth, S. Al Maadeed, M. Saleh, and Y. Akbari, "CNN feature and classifier fusion on novel transformed image dataset for dysgraphia diagnosis in children," Expert Systems with Applications, vol. 231, p. 120740, November 2023.
• [22] F. Hassan, S. F. Hussain, and S. M. Qaisar, "Fusion of multivariate EEG signals for schizophrenia detection using CNN and machine learning techniques," Information Fusion, vol. 92, pp. 466-478, April 2023.
• [23] Q. Gao, A. H. Omran, Y. Baghersad, O. Mohammadi, M. A. Alkhafaji, A. K. J. Al-Azzawi, et al., "Electroencephalogram signal classification based on Fourier transform and Pattern Recognition Network for epilepsy diagnosis," Engineering Applications of Artificial Intelligence, vol. 123, p. 106479, August 2023.
• [24] M. S. Nixon and A. S. Aguado, "Chapter 2 - Images, sampling, and frequency domain processing," in Feature Extraction & Image Processing for Computer Vision (Third Edition), M. S. Nixon and A. S. Aguado, Eds., ed Oxford: Academic Press, 2012, pp. 37-82.
• [25] P. Han, Feature extraction and descriptor based on Fourier transform of local images, Master Thesis, Department of Computer Science, The University of Regina (Canada), 2022.
• [26] M. Li and W. Chen, "FFT-based deep feature learning method for EEG classification," Biomedical Signal Processing and Control, vol. 66, p. 102492, April 2021.
• [27] G. Macin, B. Tasci, I. Tasci, O. Faust, P. D. Barua, S. Dogan, et al., "An Accurate Multiple Sclerosis Detection Model Based on Exemplar Multiple Parameters Local Phase Quantization: ExMPLPQ," Applied Sciences, vol. 12, p. 4920, 2022.
• [28] T. Ekmekyapar and B. Taşcı, "Exemplar MobileNetV2-Based Artificial Intelligence for Robust and Accurate Diagnosis of Multiple Sclerosis," Diagnostics, vol. 13, p. 3030, 2023.