Evaluation of a deep learning segmentation tool to help detect spinal cord lesions from combined T2 and STIR acquisitions in people with multiple sclerosis - Summary - MDSpire

Evaluation of a deep learning segmentation tool to help detect spinal cord lesions from combined T2 and STIR acquisitions in people with multiple sclerosis

  • By

  • Baptiste Lodé

  • Burhan Rashid Hussein

  • Cédric Meurée

  • Ricky Walsh

  • Malo Gaubert

  • Nicolas Lassalle

  • Guilhem Courbon

  • Agathe Martin

  • Jeanne Le Bars

  • Françoise Durand-Dubief

  • Bertrand Bourre

  • Adil Maarouf

  • Olivier Outteryck

  • Clément Mehier

  • Alexandre Poulin

  • Camille Cathelineau

  • Jeremy Hong

  • Guillaume Criton

  • Sophie Motillon-Alonso

  • Augustin Lecler

  • Frédérique Charbonneau

  • Loïc Duron

  • Alexandre Bani-Sadr

  • Céline Delpierre

  • Jean-Christophe Ferré

  • Gilles Edan

  • François Cotton

  • Romain Casey

  • Francesca Galassi

  • Benoit Combès

  • Anne Kerbrat

  • April 4, 2025

  • 0 min

Share

Objective:

To assess the impact of a deep learning segmentation tool on clinician’s sensitivity and precision in detecting spinal cord lesions in multiple sclerosis patients, specifically measuring lesion-wise sensitivity and precision.

Key Findings:
  • The deep learning tool improved clinician sensitivity in detecting SC lesions.
  • The tool also affected interpretation time and inter-reader variability, with specific metrics to be detailed.
  • Mean sensitivity with the tool was significantly higher than without it.
Interpretation:

The deep learning segmentation tool shows promise in enhancing the detection of spinal cord lesions in pwMS, potentially improving diagnostic accuracy and efficiency in clinical practice.

Limitations:
  • Study limited to a specific cohort from the French MS registry.
  • Results may not be generalizable to all clinical settings or populations.
  • Potential biases from the selection of expert readers.
  • Retrospective design may introduce selection bias.
Conclusion:

The study indicates that a deep learning tool can significantly aid in the detection of spinal cord lesions in multiple sclerosis, warranting further exploration in clinical applications and validation in diverse clinical settings.

Original Source(s)

Evaluation of a deep learning segmentation tool to help detect spinal cord lesions from combined T2 and STIR acquisitions in people with multiple sclerosis

  • by Baptiste Lodé, Burhan Rashid Hussein, Cédric Meurée, Ricky Walsh, Malo Gaubert, Nicolas Lassalle, Guilhem Courbon, Agathe Martin, Jeanne Le Bars, Françoise Durand-Dubief, Bertrand Bourre, Adil Maarouf, Olivier Outteryck, Clément Mehier, Alexandre Poulin, Camille Cathelineau, Jeremy Hong, Guillaume Criton, Sophie Motillon-Alonso, Augustin Lecler, Frédérique Charbonneau, Loïc Duron, Alexandre Bani-Sadr, Céline Delpierre, Jean-Christophe Ferré, Gilles Edan, François Cotton, Romain Casey, Francesca Galassi, Benoit Combès, Anne Kerbrat

  • April 4, 2025

Related Content

Multiple sclerosis as a biological and clinical continuum: from risk factors to the early stages of disease

Redefining Neuro-Ophthalmology

The eye-brain connection and the future of imaging

Mandatory Training Modules Deserve a Harder Look

A JAMA Viewpoint argues that 4 million physician-hours spent on compliance modules each year warrants institutional reassessment.