All talks & lectures

Workshop ·

Predicting multiple sclerosis progression with conventional MRI using artificial intelligence

What routine MRI can and cannot predict about MS progression, and where AI may add practical value.

41st MAGNIMS Plenary Meeting and Workshop · Van der Valk Hotel Amsterdam-Zuidas, Amsterdam

Opening slide for “Predicting multiple sclerosis progression with conventional MRI using artificial intelligence” at 41st MAGNIMS Plenary Meeting and Workshop
Opening slide from the original presentation
Delivered
Event
41st MAGNIMS Plenary Meeting and Workshop
Place
Van der Valk Hotel Amsterdam-Zuidas, Amsterdam
Format
Workshop
Source deck
14 slides

From the slides

Deck notes

This workshop talk examined the use of conventional MRI to predict progression in multiple sclerosis. It balanced the value of routinely acquired images against their known limits as individual prognostic tools.

The question

Can artificial intelligence recover useful prognostic information from heterogeneous, routinely collected MRI without overstating what those scans can predict?

Deck outline

  • Clinical definitions of disease activity, progression and disability worsening
  • Conventional brain and spinal cord MRI markers
  • AI analysis of heterogeneous clinical scans
  • Evidence, limitations and clinical maturity across imaging measures
  • Barriers to translating prognostic models into practice
  • Priorities for routine brain and spinal cord imaging

Take-away

Conventional MRI is a limited predictor on its own, but it can add value when analysed carefully. Better spinal cord tools and high-quality implementation evidence remain important gaps.

Original deck

Slide by slide

Read the 14-slide presentation in order, or use the index to jump.

  1. Slide 01

    Predicting multiple sclerosis progression with conventional MRI using artificial intelligence

    Slide 1: Predicting multiple sclerosis progression with conventional MRI using artificial intelligenceOpen full-size slide

    Arman Eshaghi, MD, PhD

    Principal Research Fellow

    Queen Square Institute of Neurology

    University College London

    UK

  4. Slide 04

    Slide 4

    Full image of slide 4Open full-size slide
    • MS Heterogeneity
    • Age at onset
    • Genetic complexity
    • Gender effects
    • Ethnicity
    • Geography
    • Symptoms
    • Reserve

  5. Slide 05

    Outcomes

    Slide 5: OutcomesOpen full-size slide

    Phenotypic:

    CIS to RR

    RR to SP

    Disability accrual/worsening

    Confirmed disability progression

    Disease activity

    Progression independent of relapses

    (PIRA)

    Progression

    NEDA-3, 4 and NEPAD*

    Treatment response scores (Rio, etc.)

    Patient reported outcomes

    *No evidence of progression or active disease

    Speaker notes

    https://www.uptodate.com/contents/indications-for-switching-or-stopping-disease-modifying-therapy-for-multiple-sclerosis

  10. Slide 10

    Routine-care MRI for prognosis

    Slide 10: Routine-care MRI for prognosisOpen full-size slide
    • Evidence — Strengths — Weakness — Clinical maturity for AI systems
    • Cerebral Lesions — Proven — Fully automatic — – Infratentorial lesions / – Sensitivity varies across regions — Most mature – Regulatory approval
    • Brain volumes — Proven — Fully automatic — No clinical consensus — Mature – regulatory approval
    • Cord cross-section — Proven — Strong predictor of motor disability — No automatic software — No evidence
    • Cord lesions — Proven — Strong predictor of motor disability — No automatic software — No evidence

  12. Slide 12

    Next steps

    Slide 12: Next stepsOpen full-size slide
    • Technical
    • Clinical
    • Pragmatic trials
    • High quality evidence
    • Implementation
    • Automatic segmentation
    • Infratentorial
    • Spinal cord
    • Cost effectiveness

  13. Slide 13

    Take home

    Slide 13: Take homeOpen full-size slide

    MRI is a poor predictor but adds value

    Emerging evidence for repurposing ”old” brain MRIs

    Limited tools for routine-care spinal cord MRI

    High-quality evidence for implementation is missing

Continue through the archive

Related talks

Nearby ideas from a different year, event or audience.