Machine learning-based classification of multiple sclerosis lesion activity using multi-sequence MRI radiomics: a complete analysis of T1, T2, FLAIR, DWI, and SWI features
Polish Journal of Radiology · 10.08.2025 · 90 · 394-403
DOI: 10.5114/pjr/206986 ↗Kurz gefasst
Fachartikel in der Zeitschrift Polish Journal of Radiology, online erschienen am 10.08.2025. Verfasst von Mohammadreza Elhaie und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Physics, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Purpose
Differentiating active from non-active multiple sclerosis (MS) lesions is critical for disease management but often relies on gadolinium-enhanced magnetic resonance imaging (MRI), raising concerns about retention risks and costs. This study introduces a contrast-free, multi-sequence MRI approach using radiomics and machine learning to classify MS lesion activity. Material and methods A total of 187 lesions from 31 MS patients (mean age 42.5 ± 11.3 years; 64.5% female) at Amin Hospital (November 2024 – February 2025) were retrospectively analysed using a 1.5 T MRI scanner. Five sequences – T1-weighted (T1W), T2-weighted (T2W), fluid-attenuated inversion recovery (FLAIR), diffusion-weighted imaging (DWI), and susceptibility-weighted imaging (SWI) – were processed to extract 8905 radiomic features, refined to 127 via correlation and recursive feature elimination. XGBoost classified lesions as active or non-active, validated on an internal test set (n = 28 lesions), with performance assessed by area under the receiver operating characteristic curve (AUC-ROC).
Results
The XGBoost model achieved an AUC-ROC of 0.87 (95% CI: 0.82-0.92), sensitivity of 0.85, and specificity of 0.83, outperforming other classifiers (SVM AUC 0.84). FLAIR (35.4%) and T2W (28.3%) dominated feature contributions, with SWI (12.6%) enhancing accuracy (AUC dropped to 0.84 without SWI). Noise simulation (Gaussian σ = 0.1) confirmed robustness (AUC = 0.86).
Conclusions
This integration of SWI with conventional sequences in a unified radiomic model offers a promising contrast-free alternative for MS lesion classification, achieving promising accuracy comparable to radiologist performance on an internal test set (n = 28 lesions), pending external validation. External validation is needed to confirm the generalisability, but this approach could reduce gadolinium reliance in clinical practice.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medical Physics, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran.
- Department of Neurology, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran.
- Department of Radiology, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran.
- Department of Bioimaging, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, Iran.
Zitieren
APA
Elhaie, M., Etemadifar, M., Adariani, A. R., Khorasani, A., & Shahbazi-Gahrouei, D. (2025). Machine learning-based classification of multiple sclerosis lesion activity using multi-sequence MRI radiomics: a complete analysis of T1, T2, FLAIR, DWI, and SWI features. Polish Journal of Radiology, 90, 394-403. https://doi.org/10.5114/pjr/206986
Vancouver
Elhaie M, Etemadifar M, Adariani AR, Khorasani A, Shahbazi-Gahrouei D. Machine learning-based classification of multiple sclerosis lesion activity using multi-sequence MRI radiomics: a complete analysis of T1, T2, FLAIR, DWI, and SWI features. Polish Journal of Radiology. 2025;90:394-403. doi:10.5114/pjr/206986
BibTeX
@article{Elhaie2025,
author = {Elhaie, Mohammadreza and Etemadifar, Masoud and Adariani, Alireza Rezaei and Khorasani, Amir and Shahbazi-Gahrouei, Daryoush},
title = {Machine learning-based classification of multiple sclerosis lesion activity using multi-sequence MRI radiomics: a complete analysis of T1, T2, FLAIR, DWI, and SWI features},
journal = {Polish Journal of Radiology},
year = {2025},
volume = {90},
pages = {394--403},
doi = {10.5114/pjr/206986}
}
EUVIMED