Skip to main content

AI scan tool improved MS checks and saved reading time

By MS Buddy ·

Summarized from Neuroradiology, Nov 2026 · PubMed · DOI. AI-generated summary. Not medical advice.

Observational study · 59 people with relapsing-remitting MS, a form with flare-ups and recovery periods

Research by Edoardo Masiello, Nicoletta Anzalone and 4 colleagues at IRCCS Ospedale San Raffaele in Italy.

Can a computer tool help doctors read MS brain scans faster and more accurately?

Key Takeaway

A computer tool helped doctors spot new or growing MS lesions (areas of damage) on brain scans more accurately and quickly.

Overlapping blue-gray and lavender layers with small patches, aligned contours and a short, gently curving path.
Credibility
Interest
Share:1 min read

What They Found

Researchers compared doctors reading brain scans alone, a computer tool working alone, and doctors using the tool. The experienced doctor's accuracy rose from about 88% alone to about 95% with the tool. The less experienced doctor's accuracy rose from about 83% alone to about 90% with the tool. The tool alone had about 80% accuracy, lower than either doctor working alone. Using the tool shortened reading time by about a minute for both doctors.

Who Should Care and Why

The study involved people with relapsing-remitting MS, a form with flare-ups followed by periods of recovery. Researchers compared earlier and later brain scans to check for new or growing lesions (areas of damage). These changes help doctors monitor MS activity. The tool was linked to more accurate readings for doctors with different levels of experience. The findings support using the tool to help doctors compare scans, rather than replace their judgment.

Important Considerations

This study looked back at brain scans from 59 people with relapsing-remitting MS. Only two doctors tested the tool, and their results were compared with agreement among doctors who had not seen its output. The study did not report whether using the tool changed treatment decisions or health outcomes.

AI-generated summary — for informational purposes only, not medical advice

Read the original abstract

Published in Neuroradiology by et al.. Reproduced from the PubMed record.

Detection of new and enlarging lesions on longitudinal MRI is essential for monitoring disease activity in multiple sclerosis (MS) but is time-consuming and subject to inter-reader variability. This study evaluated the diagnostic performance and workflow impact of a CE-marked artificial intelligence (AI) platform compared with neuroradiologists of different experience. In this retrospective study, 59 patients with relapsing-remitting MS underwent baseline and follow-up brain MRI including 3D FLAIR sequences. Two neuroradiologists independently assessed examinations for new or enlarging lesions, blinded to AI output. The reference standard was an AI-blinded consensus of the two readers, with discordant cases adjudicated by an independent third neuroradiologist. Patient-level diagnostic performance was evaluated for each reader alone, the AI alone, and each reader assisted by AI. Agreement was assessed with Cohen's kappa and reading times with the Wilcoxon signed-rank test. Among unassisted assessments, the experienced reader achieved the highest accuracy (88.1%), followed by the less experienced reader (83.1%) and the AI alone (79.7%). AI assistance was associated with higher accuracy for both readers (94.9%, κ = 0.90, and 89.8%, κ = 0.80, respectively). AI assistance significantly reduced reading time for both readers (median within-patient reduction 0.9 and 1.0 min; p < 0.001), independently of baseline T2 lesion volume. Against an AI-blinded consensus reference standard, AI assistance was associated with higher diagnostic performance of both readers, irrespective of experience, and significantly reduced reading time, supporting its role as a decision-support tool in the longitudinal MRI assessment of MS.

Categories

The app

Check out the MS Buddy app

It’s free, with no ads. Built by people living with MS.

Download on the App StoreGet it on Google Play

Related MS research

Two soft, overlapping layers sweep across muted dots, with a small cluster clearer through one layer.
Spinal fluid test flagged MS cases another test missed

11/20/2026

In a study of 140 people, a spinal fluid test better separated MS from other nervous system conditio

Read More
A crisp scan slice lines up with parallel strokes, while a fainter slice tilts across them.
Lining up MS brain scans gave stronger scan readings

11/20/2026

In people with MS, brain scan readings were stronger when images lined up with the scanner’s magneti

Read More
Cut-paper eye and ribbon-like nerve with a small overlapping terracotta shape on a warm off-white background.
MS linked to about 9% of eye nerve inflammation in Japan

11/19/2026

A Japanese hospital study linked MS to about 9% of first eye nerve inflammation cases. Other immune

Read More
Two matching brain lesion shapes, with a central vein faint on the left and more clearly visible on the right.
Adjusted MRI spots more veins inside MS brain lesions

11/18/2026

An adjusted MRI scan found more veins within MS brain lesions in 17 people with MS. It improved scan

Read More
Muted branching paths cross translucent layers, revealing a small irregular pattern at their overlap.
Brain scans after a car crash revealed MS in a teen

1/1/2026

After a car crash, brain and spine scans revealed signs of MS in an 18-year-old male. Further tests

Read More
Brain outline with connecting fibers between its halves, some subtly lighter than others.
MS brain scans cannot confirm nerve signal failure

11/14/2026

An opinion paper explains why MS brain scans can show tissue loss without proving nerve signal failu

Read More

Not all studies carry the same weight: sample size, study design and whether results were replicated all matter. The credibility score above reflects the journal, and the original paper is linked under More Details. Read how MS Buddy selects and scores research, and talk to your MS care team before acting on any study.