{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T12:46:02Z","timestamp":1793191562806,"version":"4.5.0"},"reference-count":25,"publisher":"Termedia Sp. z.o.o.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Pol J Radiol"],"abstract":"\n Purpose<\/jats:title>\n 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.<\/jats:p>\n <\/jats:sec>\n \n Material and methods<\/jats:title>\n A total of 187 lesions from 31 MS patients (mean age 42.5 \u00b1 11.3 years; 64.5% female) at Amin Hospital (November 2024 \u2013 February 2025) were retrospectively analysed using a 1.5 T MRI scanner. Five sequences \u2013 T1-weighted (T1W), T2-weighted (T2W), fluid-attenuated inversion recovery (FLAIR), diffusion-weighted imaging (DWI), and susceptibility-weighted imaging (SWI) \u2013 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 (<i>n<\/i> = 28 lesions), with performance assessed by area under the receiver operating characteristic curve (AUC-ROC).<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n 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 \u03c3 = 0.1) confirmed robustness (AUC = 0.86).<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n 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 (<i>n<\/i> = 28 lesions), pending external validation. External validation is needed to confirm the genera\u00adlisability, but this approach could reduce gadolinium reliance in clinical practice.<\/jats:p>\n <\/jats:sec>","DOI":"10.5114\/pjr\/206986","type":"journal-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T07:06:21Z","timestamp":1755068781000},"page":"394-403","source":"Crossref","is-referenced-by-count":16,"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"],"prefix":"10.5114","volume":"90","author":[{"given":"Mohammadreza","family":"Elhaie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masoud","family":"Etemadifar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alireza","family":"Rezaei Adariani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir","family":"Khorasani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daryoush","family":"Shahbazi-Gahrouei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"3061","published-online":{"date-parts":[[2025,8,10]]},"reference":[{"key":"ref-1496144","doi-asserted-by":"crossref","unstructured":"Band\u00f4 Y. Mechanism of demyelination and remyelination in multiple sclerosis. Clin Exp Neuroimmunol 2020; 11(S1): 14-21.","DOI":"10.1111\/cen3.12576"},{"key":"ref-1496145","doi-asserted-by":"publisher","DOI":"10.1136\/bmjno-2024-000788"},{"key":"ref-1496146","doi-asserted-by":"publisher","DOI":"10.1016\/j.msard"},{"key":"ref-1496147","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-024-01528-6"},{"key":"ref-1496148","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-48488-4"},{"key":"ref-1496149","doi-asserted-by":"crossref","unstructured":"Liu Q, Sun D, Li N, Kim JM, Feng D, Huang G, et al. Predicting EGFR mutation subtypes in lung adenocarcinoma using 18F-FDG PET\/CT radiomic features. Translat Lung Cancer Res 2020; 9: 549-562.","DOI":"10.21037\/tlcr.2020.04.17"},{"key":"ref-1496150","doi-asserted-by":"publisher","DOI":"10.1186\/s41747-018-0068-z"},{"key":"ref-1496151","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinimag.2025.110456"},{"key":"ref-1496152","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2023.103376"},{"key":"ref-1496153","doi-asserted-by":"publisher","DOI":"10.3390\/ijms231810651"},{"key":"ref-1496154","doi-asserted-by":"publisher","DOI":"10.1016\/j.msard.2024.105761"},{"key":"ref-1496155","doi-asserted-by":"publisher","DOI":"10.1016\/j.jrras.2024.101252"},{"key":"ref-1496156","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-024-01528-6"},{"key":"ref-1496157","doi-asserted-by":"crossref","unstructured":"Caruana G, Pessini LM, Cannella R, Salvaggio G, de Barros A, Salerno A, et al. Texture analysis in susceptibility-weighted imaging may be useful to differentiate acute from chronic multiple sclerosis lesions. Eur Radiol 2020; 30: 6348-6356.","DOI":"10.1007\/s00330-020-06995-3"},{"key":"ref-1496158","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.03820"},{"key":"ref-1496159","doi-asserted-by":"crossref","unstructured":"Bleker J, Roest C, Yakar D, Huisman H, Kwee TC. The effect of image resampling on the performance of radiomics-based artificial intelligence in multicenter prostate MRI. J Magn Res Imaging 2023; 59: 1800-1806.","DOI":"10.1002\/jmri.28935"},{"key":"ref-1496160","doi-asserted-by":"crossref","unstructured":"Jaber HA, Aljobouri HK, \u00c7ankaya \u0130, Ko\u00e7ak OM, Alg\u0131n O. Preparing fMRI data for postprocessing: conversion modalities, preprocessing pipeline, and parametric and nonparametric approaches. IEEE Access 2019; 7: 122864-122877.","DOI":"10.1109\/ACCESS.2019.2937482"},{"key":"ref-1496161","doi-asserted-by":"crossref","unstructured":"Van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. Computational radiomics system to decode the radio\u00adgraphic phenotype. Cancer Res 2017; 77: e104-e107. DOI: 10.1158\/0008-5472.CAN-17-0339.","DOI":"10.1158\/0008-5472.CAN-17-0339"},{"key":"ref-1496163","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-90428-8"},{"key":"ref-1496164","doi-asserted-by":"crossref","unstructured":"Moradmand H, Aghamiri SMR, Ghaderi R. Impact of image preprocessing methods on reproducibility of radiomic features in multimodal magnetic resonance imaging in glioblastoma. J Appl Clin Med Phys 2019; 21: 179-190.","DOI":"10.1002\/acm2.12795"},{"key":"ref-1496165","doi-asserted-by":"crossref","unstructured":"Mohammadi-Sadr M, Cheki M, Moslehi M, Zarasvandnia M, Salamat MR. A novel approach based on integrating radiomics, bone morphometry and hounsfield unit-derived from routine chest CT for bone mineral density assessment. Acad Radiol 2025; 32: 2284-2296.","DOI":"10.1016\/j.acra.2024.10.049"},{"key":"ref-1496166","doi-asserted-by":"crossref","unstructured":"Tripathy RK, Sharma LN, Dandapat S. Diagnostic measure to quantify loss of clinical components in multi-lead electrocardiogram. Healthc Technol Lett 2016; 3: 61-66.","DOI":"10.1049\/htl.2015.0011"},{"key":"ref-1496167","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2022.103065"},{"key":"ref-1496168","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2023.103491"},{"key":"ref-1496169","doi-asserted-by":"publisher","DOI":"10.1088\/2057-1976\/ace261"}],"container-title":["Polish Journal of Radiology"],"original-title":[],"link":[{"URL":"https:\/\/www.polradiol.com\/pdf-209637-127892","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.polradiol.com\/pdf-209637-127892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T10:36:46Z","timestamp":1755513406000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.polradiol.com\/Machine-learning-based-classification-of-multiple-sclerosis-lesion-activity-using,209637,0,2.html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,10]]},"references-count":25,"alternative-id":["209637"],"URL":"https:\/\/doi.org\/10.5114\/pjr\/206986","relation":{},"ISSN":["1899-0967"],"issn-type":[{"value":"1899-0967","type":"print"}],"subject":[],"published":{"date-parts":[[2025,8,10]]}}}