Early Detection of Multiple Sclerosis Using Combining Descriptors and Feature Subset Selection Based on Differential Evolutionary Algorithm

Zamani Boroujeni, Farsad; Davami, Fatemeh; Derakhshan-Barjoei, Pouya; Changani, Fahimeh

doi:10.22034/apj.2025.725725

Early Detection of Multiple Sclerosis Using Combining Descriptors and Feature Subset Selection Based on Differential Evolutionary Algorithm

Document Type : Original Research Article

Authors

Farsad Zamani Boroujeni ¹

Fatemeh Davami ²

Pouya Derakhshan-Barjoei ³

Fahimeh Changani ⁴

¹ Department of Computer Engineering, SR.C, Islamic Azad University, Tehran, Iran

² Department of Computer Engineering, Firoozabad Branch, Islamic Azad University, Firoozabad, Iran

³ Department of Electrical Engineering, SR.C, Islamic Azad University, Tehran, Iran

⁴ Department of Electrical and Computer Engineering, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran

10.22034/apj.2025.725725

Abstract

Background and Objectives: Multiple sclerosis is a brain disease where early diagnosis is crucial for treatment. One of the ways to diagnose this disease is by observing lesions caused by it in MRI scans. Most previous approaches have issues such as low diagnostic accuracy, a high number of features, time-consuming analysis, and a lack of certainty in achieving optimal answers.
Methods: In this article, for the first time, a feature vector set is formed by aggregating results from image MRI texture descriptors such as wavelet transform, chaotic features (fractal), and local binary patterns. The presentation of a selected feature set using a differential evolutionary algorithm has not been utilized in this area of identification before, so our proposed technique is based on this approach. Additionally, the proposed classifier will be an improved model combining three types of neural networks. Moreover, improvements in accuracy, sensitivity, and the ability to verify the correctness of the classification results are also considered innovative aspects.
Findings: The data used in this article was obtained from two datasets. After K-fold cross-validation, the experimental accuracy for both image datasets were found to be 95% and 97%, respectively, which represents a 2% improvement over a method that used wavelet transform along with principal component analysis and support vector machines, while also addressing the uncertainty issue.
Conclusion: Our integrated algorithm introduced greater diagnostic accuracy compared to previous methods and takes into account the accuracy factor that was not considered in past approaches. This algorithm not only reduces processing time but also enables simultaneous processing from different channels, aligning better with the opinions of specialized doctors. Despite the lack of a simultaneous separation-processing technique, the rates of false positives and negatives in identifying MS disease are very low. For future work, recommendations include noise removal in the preprocessing stage, combining feature selection techniques to increase accuracy, and using parallel processing as the primary tool in separation software.

Keywords

MS disease

Feature extraction

Evolutionary-differential algorithm

[1] R. E. Boeschoten et al., "Prevalence of depression and anxiety in multiple sclerosis: a systematic review and meta-analysis," Journal of the neurological sciences, vol. 372, pp. 331-341, 2017.

[2] T. Olsson, L. F. Barcellos, and L. Alfredsson, "Interactions between genetic, lifestyle and environmental risk factors for multiple sclerosis," Nature Reviews Neurology, vol. 13, no. 1, pp. 25-36, 2017.

[3] و. امینی‌آذر, ر. فرحی, and ا. خوانچه سپهرالدین, "مروری بر روش‌های هوشمند در تشخیص و پیش‌بینی بیمارهای کبد با استفاده از تکنیک‌های یادگیری ماشین و الگوریتم‌های فراابتکاری," فصلنامه تخصصی آرمان پردازش, vol. 4, no. 2, pp. -, 2023. [Online]. Available: https://www.armanprocessjournal.ir/article_708841_cf94c99c44ee36fa708b221107724893.pdf.

[4] م. دهقانی محمودآبادی, "بررسی کارایی سیستم دسته‌بند یادگیر برای شناسایی بیماران قلبی," فصلنامه تخصصی آرمان پردازش, vol. 4, no. 4, pp. 19-29, 2024. [Online]. Available: https://www.armanprocessjournal.ir/article_712664_0a3582cfe3711dea4a4f495519fcef56.pdf.

[5] B. K. Tsang and R. Macdonell, "Multiple sclerosis: diagnosis, management and prognosis," Australian family physician, vol. 40, no. 12, pp. 948-955, 2011.

[6] E. Roura et al., "A toolbox for multiple sclerosis lesion segmentation," Neuroradiology, vol. 57, pp. 1031-1043, 2015.

[7] Y. Karpate, O. Commowick, and C. Barillot, "Probabilistic one class learning for automatic detection of multiple sclerosis lesions," in 2015 IEEE 12th International Symposium on biomedical imaging (ISBI), 2015: IEEE, pp. 486-489.

[8] T. Brosch, L. Y. Tang, Y. Yoo, D. K. Li, A. Traboulsee, and R. Tam, "Deep 3D convolutional encoder networks with shortcuts for multiscale feature integration applied to multiple sclerosis lesion segmentation," IEEE transactions on medical imaging, vol. 35, no. 5, pp. 1229-1239, 2016.

[9] I. De Falco, "Classification of Potential Multiple Sclerosis Lesions Through Automatic Knowledge Extraction by Means of Differential Evolution," in Applications of Evolutionary Computation: 17th European Conference, EvoApplications 2014, Granada, Spain, April 23-25, 2014, Revised Selected Papers 17, 2014: Springer, pp. 538-549.

[10] A. Rezaee, K. Rezaee, J. Haddadnia, and H. T. Gorji, "Supervised meta-heuristic extreme learning machine for multiple sclerosis detection based on multiple feature descriptors in MR images," SN Applied Sciences, vol. 2, no. 5, p. 866, 2020.

[11] L. Bai, J. Wu, L. Chen, X. Jiang, and Z. Song, "A density-based MS disease diagnosis model using the capuchin search algorithm and an ensemble of deep neural networks," Scientific Reports, vol. 14, no. 1, p. 31721, 2024.

[12] C. Dachraoui et al., "A machine learning approach for multiple sclerosis diagnosis through Detecron Architecture," Multimedia Tools and Applications, vol. 83, no. 14, pp. 42837-42859, 2024.

[13] C. P. Loizou et al., "Brain white matter lesion classification in multiple sclerosis subjects for the prognosis of future disability," Intelligent Decision Technologies, vol. 7, no. 1, pp. 3-10, 2013.

[14] C. P. Loizou, V. Murray, M. S. Pattichis, I. Seimenis, M. Pantziaris, and C. S. Pattichis, "Multiscale amplitude-modulation frequency-modulation (AM–FM) texture analysis of multiple sclerosis in brain MRI images," IEEE Transactions on Information Technology in Biomedicine, vol. 15, no. 1, pp. 119-129, 2010.

[15] P. DerakhshanBarjoei, M. Bahadorzadeh, and A. Arabzadeh, "Early Detection of Diabetic Foot Ulcers by Thermal Images of Foot Soles Using Nearest Neighbor Algorithm," Medical Journal of Mashhad University of Medical Sciences, vol. 66, no. 2, pp. 150-156, 2023.

[16] E. Foroozandeh, P. Derakhshan-Barjoei, and M. Bahadorzadeh, "Investigation the effect of emotional control and extroversion on severity of central serous retinopathy in patients using fuzzy logic algorithm," Journal of Health and Biomedical Informatics, vol. 5, no. 3, pp. 337-347, 2018.