Download PDF
Klinische Neurophysiologie 2025; 56(02): 87-95
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
Sarah Schlaeger
1   Klinik und Poliklinik für Radiologie, LMU Klinikum, LMU München, München, Deutschland
2   Institut für Diagnostische und Interventionelle Neuroradiologie, Klinikum rechts der Isar der Technischen Universität München, München, Deutschland
,
Benedikt Wiestler
2   Institut für Diagnostische und Interventionelle Neuroradiologie, Klinikum rechts der Isar der Technischen Universität München, München, Deutschland
,
Jan S. Kirschke
2   Institut für Diagnostische und Interventionelle Neuroradiologie, Klinikum rechts der Isar der Technischen Universität München, München, Deutschland
› Author Affiliations
› Further Information
Also available at
   Permissions and Reprints

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.

Schlüsselwörter

Künstliche Intelligenz - Multiple Sklerose - Magnetresonanztomographie

Keywords

Artificial intelligence - Multiple sclerosis - Magnetic resonance imaging


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
    PubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 4 Bonacchi R, Filippi M, Rocca MA. Role of artificial intelligence in MS clinical practice. Neuroimage Clin 2022; 35: 103065
    CrossrefPubMedSearch in Google Scholar
  • 5 Eichinger P, Zimmer C, Wiestler B. AI in Radiology: Where are we today in Multiple Sclerosis Imaging?. Rofo 2020; 192: 847-853
    PubMedSearch in Google Scholar
  • 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
    Search in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 8 Amin M, Martínez-Heras E, Ontaneda D. et al. Artificial Intelligence and Multiple Sclerosis. Curr Neurol Neurosci Rep 2024; 24: 233-243
    PubMedSearch in Google Scholar
  • 9 Shaul R, David I, Shitrit O. et al. Subsampled brain MRI reconstruction by generative adversarial neural networks. Med Image Anal 2020; 65: 101747
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 11 Liu H, Xiang QS, Tam R. et al. Myelin water imaging data analysis in less than one minute. Neuroimage 2020; 210: 116551
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 44 Lublin FD, Reingold SC, Cohen JA. et al. Defining the clinical course of multiple sclerosis: the 2013 revisions. Neurology 2014; 83: 278-286
    CrossrefPubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 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
    PubMedSearch in Google Scholar
  • 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
    CrossrefPubMedSearch in Google Scholar
  • 53 Naji Y, Mahdaoui M, Klevor R. et al. Artificial Intelligence and Multiple Sclerosis: Up-to-Date Review. Cureus 2023; 15: e45412
    PubMedSearch in Google Scholar