Researchers claim to have developed a new artificial intelligence tool that can help interpret and assess how well treatments are working for patients with multiple sclerosis. The results from the study show it is possible to use an AI tool to accurately identify and measure important brain tissues and lesions even with limited MRI data.

AI uses mathematical models to train computers with the use of massive amounts of data to learn and solve problems in ways that can seem human, including the ability to perform complex tasks such as image recognition.

Magnetic resonance imaging markers are crucial for studying and testing treatments for MS. However, measuring these markers needs different types of specialised MRI scans, limiting the effectiveness of many routine hospital scans.

MindGlide is a deep learning model, developed by University College London researchers, to assess MRI images of the brain and identify damage and changes caused by MS. MindGlide, can extract key information from MRI scans acquired during the care of MS patients, such as measuring damaged areas of the brain and highlighting subtle changes such as brain shrinkage and plaques. In developing MindGlide, scientists used an initial dataset of 4,247 brain MRI scans from 2,934 MS patients across 592 MRI scanners. During this process, MindGlide trains itself to identify markers of MS. 

As part of a new study, researchers tested the effectiveness of MindGlide on more than 14,000 images from more than 1,000 patients with MS. This task had previously required expert neuro-radiologists to interpret years of complex scans manually – and the turnaround time for reporting these images is often weeks because of the NHS workload. 

However, MindGlide was able to successfully use AI to detect how different treatments affected disease progression in clinical trials and routine care, using images that could not previously be analyzed in routine MRI scan images. The process took five to 10 seconds per image.

MindGlide also performed better than two other AI tools – SAMSEG (a tool used to identify and outline different parts of the brain in MRI scans) and WMH-SynthSeg (a tool that detects and measures bright spots seen on certain MRI scans, which can be important for diagnosing and monitoring conditions such as MS) – when compared to expert clinical analysis. MindGlide was 60 percent better than SAMSEG and 20 percent better than WMH-SynthSeg for locating brain abnormalities known as plaques (or lesions) and for monitoring treatment effect.

The results from the study suggest it is possible to use MindGlide to accurately identify and measure important brain tissues and lesions even with limited MRI data. Single types of scans aren’t usually used for this purpose – such as T2-weighted MRI without FLAIR (a type of scan that highlights fluids in the body but still contains bright signals – making it harder to see plaques). As well as performing better at detecting changes in the brain’s outer layer, MindGlide also performed well in deeper brain areas.

The findings were valid and reliable both at one point in time and over longer periods (i.e. at annual scans attended by patients). Additionally, MindGlide was able to corroborate previous high-quality research regarding which treatments were most effective.

The researchers now hope that MindGlide can be used to evaluate MS treatments in real-world settings, overcoming previous limitations of relying solely on high-quality clinical trial data, which often did not capture the full diversity of people with MS. The current implementation of MindGlide is limited to brain scans and does not include spinal cord imaging, which is important for assessing disability in people with MS. Future research will need to develop a more comprehensive assessment of the whole neural system to encompass both the brain and the spinal cord.

The findings were published in the journal Nature Communications.