A Belgian study assessing relapsing multiple sclerosis activity through automated magnetic resonance imaging volumetry.
Authors
Affiliations (9)
Affiliations (9)
- Center for Neurosciences, Vrije Universiteit Brussel, Brussels, Belgium.
- National MS Center, Melsbroek, Belgium.
- AZ Klina, Brasschaat, Belgium.
- AZ Groeninge, Kortrijk, Belgium.
- Hôpital Universitaire de Bruxelles, Erasme Hospital, Brussels, Belgium.
- Centre Hospitalier Universitaire HELORA, Mons, Belgium.
- Europe Hospitals, Brussels, Belgium.
- icometrix, Leuven, Belgium.
- Medical Department, Novartis Pharma NV/SA, Vilvoorde, Belgium.
Abstract
This study assessed to what extent ico<b>brain ms</b>, a commercially available artificial intelligence (AI)-assisted magnetic resonance imaging (MRI) volumetry software, detected disease activity in patients with clinically and radiologically stable relapsing multiple sclerosis (RMS), and estimated its impact on radiologists' assessments. We retrospectively enrolled 111 RMS patients with two consecutive MRI scans at one year interval, without relapses, progression or radiological changes while remaining on stable therapy. MRI scans were analyzed by four radiologists acting independently, and by ico<b>brain ms</b>. The radiologists performed their assessments both without and with ico<b>brain ms</b> support and categorized patient status based on lesion and brain volume changes. Radiologists' detection of lesion activity non-significantly increased from 6.8% to 8.6% (McNemar <i>p</i> = 0.215; ordinal regression <i>p</i> = 0.06; sign-test <i>p</i> = 0.08) using ico<b>brain ms</b>. Detection of accelerated brain volume loss increased from 2.0% to 7.7% (all <i>p</i> < 0.01). Inter-reader agreement improved from 36% to 56% for lesions, and from 26% to 40% for brain loss (Kendall's W, <i>p</i> < 0.001). Ico<b>brain ms</b> detected new or significantly enlarged lesions in 16.2% and accelerated brain volume loss in 6.3% of participants. AI-assisted MRI volumetry may support radiologists to detect subclinical disease activity in patients characterized as having stable disease.