Subscribe to RSS
Please copy the URL and add it into your RSS Feed Reader.
https://www.thieme-connect.de/rss/thieme/en/10.1055-s-00000032.xml
Download PDF
Klinische Neurophysiologie 2025; 56(02): 87-95
DOI: 10.1055/a-2530-1105
DOI: 10.1055/a-2530-1105
Übersicht
Intelligente Bildgebung: Künstliche Intelligenz in der MRT-Diagnostik der Multiplen Sklerose
Intelligent Imaging: Artificial Intelligence in MRI Diagnostics of Multiple Sclerosis
Zusammenfassung
Die Magnetresonanztomographie (MRT) ist zentral für Diagnose und Verlaufsbeurteilung der Multiplen Sklerose (MS). Die Künstliche Intelligenz (KI) hält zunehmend Einzug in den radiologischen Alltag. Diese narrative Übersichtsarbeit gibt einen Überblick über aktuelle KI-Anwendungen in der MRT bei MS. So wird KI in der Bilderzeugung zur Akquisitionsbeschleunigung sowie zur Generierung synthetischer und hochaufgelöster Kontraste genutzt. In der Bildinterpretation kommen Modelle zur Läsionsdetektion, Atrophiequantifizierung sowie Hirnalterbestimmung zum Einsatz. KI kann bei der Diagnosestellung, MS-Phänotyp-Differenzierung und Prognoseabschätzung unterstützen. Der klinische Einsatz der KI-Modell ist derzeit noch hauptsächlich auf die Läsionsdetektion begrenzt. Für eine zunehmende Verbreitung sind eine weitere MRT-Protokollstandardisierung, Generalisierbarkeit, Validierung der klinischen Relevanz und Integration multimodaler Daten essentiell. KI könnte so zum Schlüsselwerkzeug der personalisierten MS-Diagnostik und -Therapie werden.
Abstract
Magnetic resonance imaging (MRI) plays a central role in the diagnosis and monitoring of multiple sclerosis (MS). Artificial intelligence (AI) is increasingly being integrated into routine radiological practice. This narrative review provides an overview of current AI applications in MRI for MS. AI is used in image acquisition to accelerate data acquisition and to generate synthetic and high-resolution contrasts. In image interpretation, models are employed for lesion detection, atrophy quantification, and brain age estimation. AI can support diagnosis, differentiation of MS phenotypes, and prognosis assessment. Currently, the clinical application of AI models is primarily limited to lesion detection. For broader clinical adoption, further MRI protocol standardization, generalizability, validation of clinical relevance, and integration of multimodal data are essential. AI could thus become a key tool in personalized MS diagnostics and therapy.
Publication History
Article published online:
04 June 2025
© 2025. Thieme. All rights reserved.
Georg Thieme Verlag KG
Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany
-
Literatur
- 1 Global, regional, and national burden of multiple sclerosis 1990-2016: a systematic analysis for the Global Burden of Disease Study 2016. Lancet Neurol. 2019 18. 269-285
- 2 Wattjes MP, Ciccarelli O, Reich DS. et al. 2021 MAGNIMS-CMSC-NAIMS consensus recommendations on the use of MRI in patients with multiple sclerosis. Lancet Neurol 2021; 20: 653-670
- 3 Rocca MA, Preziosa P, Barkhof F. et al. Current and future role of MRI in the diagnosis and prognosis of multiple sclerosis. Lancet Reg Health Eur 2024; 44: 100978
- 4 Bonacchi R, Filippi M, Rocca MA. Role of artificial intelligence in MS clinical practice. Neuroimage Clin 2022; 35: 103065
- 5 Eichinger P, Zimmer C, Wiestler B. AI in Radiology: Where are we today in Multiple Sclerosis Imaging?. Rofo 2020; 192: 847-853
- 6 Jasperse B, Barkhof F. Machine Learning in Multiple Sclerosis. In: Colliot O, editor. Machine Learning for Brain Disorders. New York, NY: Humana; Copyright 2023, The Author(s) 2023: 899-919
- 7 Collorone S, Coll L, Lorenzi M. et al. Artificial intelligence applied to MRI data to tackle key challenges in multiple sclerosis. Mult Scler 2024; 30: 767-784
- 8 Amin M, Martínez-Heras E, Ontaneda D. et al. Artificial Intelligence and Multiple Sclerosis. Curr Neurol Neurosci Rep 2024; 24: 233-243
- 9 Shaul R, David I, Shitrit O. et al. Subsampled brain MRI reconstruction by generative adversarial neural networks. Med Image Anal 2020; 65: 101747
- 10 Mani A, Santini T, Puppala R. et al. Applying Deep Learning to Accelerated Clinical Brain Magnetic Resonance Imaging for Multiple Sclerosis. Front Neurol 2021; 12: 685276
- 11 Liu H, Xiang QS, Tam R. et al. Myelin water imaging data analysis in less than one minute. Neuroimage 2020; 210: 116551
- 12 Finck T, Li H, Grundl L. et al. Deep-Learning Generated Synthetic Double Inversion Recovery Images Improve Multiple Sclerosis Lesion Detection. Investigative radiology 2020; 55: 318-323
- 13 Bouman PM, Strijbis VI, Jonkman LE. et al. Artificial double inversion recovery images for (juxta)cortical lesion visualization in multiple sclerosis. Mult Scler 2022; 28: 541-549
- 14 Bouman PM, Steenwijk MD, Geurts JJG. et al. Artificial double inversion recovery images can substitute conventionally acquired images: an MRI-histology study. Sci Rep 2022; 12: 2620
- 15 Schlaeger S, Li HB, Baum T. et al. Longitudinal Assessment of Multiple Sclerosis Lesion Load With Synthetic Magnetic Resonance Imaging – A Multicenter Validation Study. Investigative radiology 2023; 58: 320-326
- 16 Finck T, Li H, Schlaeger S. et al. Uncertainty-Aware and Lesion-Specific Image Synthesis in Multiple Sclerosis Magnetic Resonance Imaging: A Multicentric Validation Study. Front Neurosci 2022; 16: 889808
- 17 Wei W, Poirion E, Bodini B. et al. Fluid-attenuated inversion recovery MRI synthesis from multisequence MRI using three-dimensional fully convolutional networks for multiple sclerosis. J Med Imaging (Bellingham) 2019; 6: 014005
- 18 Bahrami K, Shi F, Zong X. et al. Reconstruction of 7T-Like Images From 3T MRI. IEEE Trans Med Imaging 2016; 35: 2085-2097
- 19 Qu L, Zhang Y, Wang S. et al. Synthesized 7T MRI from 3T MRI via deep learning in spatial and wavelet domains. Med Image Anal 2020; 62: 101663
- 20 Zhao C, Shao M, Carass A. et al. Applications of a deep learning method for anti-aliasing and super-resolution in MRI. Magn Reson Imaging 2019; 64: 132-141
- 21 Spagnolo F, Depeursinge A, Schädelin S. et al. How far MS lesion detection and segmentation are integrated into the clinical workflow? A systematic review. Neuroimage Clin 2023; 39: 103491
- 22 Wiltgen T, McGinnis J, Schlaeger S, Kofler F, Voon C, Berthele A. et al. LST-AI: A deep learning ensemble for accurate MS lesion segmentation. Neuroimage Clin.. 2024 42. 103611
- 23 Valverde S, Cabezas M, Roura E. et al. Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach. Neuroimage 2017; 155: 159-168
- 24 Weeda MM, Brouwer I, de Vos ML. et al. Comparing lesion segmentation methods in multiple sclerosis: Input from one manually delineated subject is sufficient for accurate lesion segmentation. Neuroimage Clin 2019; 24: 102074
- 25 Bendfeldt K, Taschler B, Gaetano L. et al. MRI-based prediction of conversion from clinically isolated syndrome to clinically definite multiple sclerosis using SVM and lesion geometry. Brain Imaging Behav 2019; 13: 1361-1374
- 26 Gaj S, Ontaneda D, Nakamura K. Automatic segmentation of gadolinium-enhancing lesions in multiple sclerosis using deep learning from clinical MRI. PloS one 2021; 16: e0255939
- 27 Schlaeger S, Shit S, Eichinger P. et al. AI-based detection of contrast-enhancing MRI lesions in patients with multiple sclerosis. Insights Imaging 2023; 14: 123
- 28 Narayana PA, Coronado I, Sujit SJ. et al. Deep Learning for Predicting Enhancing Lesions in Multiple Sclerosis from Noncontrast MRI. Radiology 2020; 294: 398-404
- 29 Eichinger P, Schön S, Pongratz V. et al. Accuracy of Unenhanced MRI in the Detection of New Brain Lesions in Multiple Sclerosis. Radiology 2019; 291: 429-435
- 30 Rovira A, Corral JF, Auger C. et al. Assessment of automatic decision-support systems for detecting active T2 lesions in multiple sclerosis patients. Mult Scler 2022; 28: 1209-1218
- 31 Eshaghi A, Prados F, Brownlee WJ. et al. Deep gray matter volume loss drives disability worsening in multiple sclerosis. Ann Neurol 2018; 83: 210-222
- 32 Battaglini M, Jenkinson M, De Stefano N. Evaluating and reducing the impact of white matter lesions on brain volume measurements. Hum Brain Mapp 2012; 33: 2062-2071
- 33 Sastre-Garriga J, Pareto D, Battaglini M. et al. MAGNIMS consensus recommendations on the use of brain and spinal cord atrophy measures in clinical practice. Nat Rev Neurol 2020; 16: 171-182
- 34 Thompson AJ, Banwell BL, Barkhof F. et al. Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria. Lancet Neurol 2018; 17: 162-173
- 35 Nabizadeh F, Ramezannezhad E, Kargar A. et al. Diagnostic performance of artificial intelligence in multiple sclerosis: a systematic review and meta-analysis. Neurol Sci 2023; 44: 499-517
- 36 Yoo Y, Tang LYW, Brosch T. et al. Deep learning of joint myelin and T1w MRI features in normal-appearing brain tissue to distinguish between multiple sclerosis patients and healthy controls. Neuroimage Clin 2018; 17: 169-178
- 37 Eshaghi A, Wottschel V, Cortese R. et al. Gray matter MRI differentiates neuromyelitis optica from multiple sclerosis using random forest. Neurology 2016; 87: 2463-2470
- 38 Cacciaguerra L, Meani A, Mesaros S, Radaelli M, Palace J, Dujmovic-Basuroski I. et al. Brain and cord imaging features in neuromyelitis optica spectrum disorders. Ann Neurol 2019; 85: 371-84
- 39 Kim H, Lee Y, Kim YH. et al. Deep Learning-Based Method to Differentiate Neuromyelitis Optica Spectrum Disorder From Multiple Sclerosis. Front Neurol 2020; 11: 599042
- 40 Rocca MA, Anzalone N, Storelli L. et al. Deep Learning on Conventional Magnetic Resonance Imaging Improves the Diagnosis of Multiple Sclerosis Mimics. Investigative radiology 2021; 56: 252-260
- 41 Theocharakis P, Glotsos D, Kalatzis I. et al. Pattern recognition system for the discrimination of multiple sclerosis from cerebral microangiopathy lesions based on texture analysis of magnetic resonance images. Magn Reson Imaging 2009; 27: 417-422
- 42 Luo X, Piao S, Li H. et al. Multi-lesion radiomics model for discrimination of relapsing-remitting multiple sclerosis and neuropsychiatric systemic lupus erythematosus. European radiology 2022; 32: 5700-5710
- 43 Ekşi Z, Özcan ME, Çakıroğlu M. et al. Differentiation of multiple sclerosis lesions and low-grade brain tumors on MRS data: machine learning approaches. Neurol Sci 2021; 42: 3389-3395
- 44 Lublin FD, Reingold SC, Cohen JA. et al. Defining the clinical course of multiple sclerosis: the 2013 revisions. Neurology 2014; 83: 278-286
- 45 Marzullo A, Kocevar G, Stamile C. et al. Classification of Multiple Sclerosis Clinical Profiles via Graph Convolutional Neural Networks. Front Neurosci 2019; 13: 594
- 46 EkŞİ Z, ÇakiroĞlu M, Öz C. et al. Differentiation of relapsing-remitting and secondary progressive multiple sclerosis: a magnetic resonance spectroscopy study based on machine learning. Arq Neuropsiquiatr 2020; 78: 789-796
- 47 Eshaghi A, Young AL, Wijeratne PA. et al. Identifying multiple sclerosis subtypes using unsupervised machine learning and MRI data. Nat Commun 2021; 12: 2078
- 48 Pontillo G, Penna S, Cocozza S. et al. Stratification of multiple sclerosis patients using unsupervised machine learning: a single-visit MRI-driven approach. European radiology 2022; 32: 5382-5391
- 49 Roca P, Attye A, Colas L. et al. Artificial intelligence to predict clinical disability in patients with multiple sclerosis using FLAIR MRI. Diagn Interv Imaging 2020; 101: 795-802
- 50 Zhao Y, Wang T, Bove R. et al. Ensemble learning predicts multiple sclerosis disease course in the SUMMIT study. NPJ Digit Med 2020; 3: 135
- 51 Tommasin S, Cocozza S, Taloni A. et al. Machine learning classifier to identify clinical and radiological features relevant to disability progression in multiple sclerosis. Journal of neurology 2021; 268: 4834-4845
- 52 Mendelsohn Z, Pemberton HG, Gray J. et al. Commercial volumetric MRI reporting tools in multiple sclerosis: a systematic review of the evidence. Neuroradiology 2023; 65: 5-24
- 53 Naji Y, Mahdaoui M, Klevor R. et al. Artificial Intelligence and Multiple Sclerosis: Up-to-Date Review. Cureus 2023; 15: e45412