{"slug": "ai-could-help-spare-brain-tumour-patients-mri-dye-injections", "title": "AI could help spare brain tumour patients MRI dye injections", "summary": "Researchers at UCL developed an AI tool that predicted from 11,089 MRI scans of more than 8,500 patients across the UK, US, Netherlands and Nigeria whether brain tumours would brighten on contrast-enhanced scans, correctly predicting enhancement on more than 1,100 non-contrast images 83% of the time, identifying 92% of tumours that did brighten and 74% that did not. The study, which the researchers say could reduce gadolinium dependence in neuro-oncology imaging, was most accurate for meningioma and less accurate in children, and the team cautioned the model is \"currently insufficient to replace contrast-enhanced MRI\" entirely. Dr Karen Noble, director of research and policy at Brain Tumour Research, called AI innovation that could reduce the need for contrast dye injections for some patients \"welcome.", "body_md": "# AI could help spare brain tumour patients MRI dye injections\n\n## The technology could help predict which tumours will light up on scans without the need for gadolinium, according to researchers.\n\n- Bookmark\n\nBrain tumour patients could be spared contrast dye injections during MRI scans with the help of artificial intelligence (AI).\n\nThe technology could help predict which tumours will light up on scans without the need for gadolinium, according to researchers.\n\nGadolinium is a clear, colourless fluid injected into a patient’s bloodstream to make images clearer during an MRI scan and help with diagnosis.\n\nHowever, the long-term effects of exposure on the body “remain unknown”, experts said.\n\nThere are also “broader environmental implications” linked to its use, they added, with gadolinium detected in sewage, surface and drinking water, water sources distant from MRI facilities, and fast-food soft drinks.\n\nExperts at [UCL](https://www.independent.co.uk/topic/ucl) developed an AI tool to predict exactly which parts of the brain would be enhanced if contrast fluid had been injected into the bloodstream using 11,089 MRI scans from more than 8,500 patients in the UK, US, the [Netherlands](https://www.independent.co.uk/topic/netherlands) and Nigeria.\n\nOn more than 1,100 non-contrast images, AI correctly predicted whether a tumour would brighten 83% of the time.\n\nThe study found the technology correctly identified 92% of tumours that did brighten and 74% that did not.\n\nIt was most accurate in scans of meningioma – a common brain tumour – but less accurate in cases involving children.\n\nResearchers said: “These models show promise as a triage or decision-support aid – for example, flagging studies in which post-contrast enhancement is likely so that contrast can be added to a non-contrast-only protocol – and could reduce gadolinium dependence in neuro-oncology imaging.\n\n“Future studies should optimise these models through close collaboration with expert radiologists.”\n\nThey added that the model’s performance is “currently insufficient to replace contrast-enhanced MRI” entirely, particularly in children, where is showed “reduced accuracy”.\n\nHowever, it could be used as “a triage or decision-support aid” to flag where enhancement is likely, which would help “patients avoid a second hospital visit and minimise delays to patient care”, researchers suggest.\n\nDr Karen Noble, director of research and policy at Brain Tumour Research, said: “More than 100,000 people in the UK are estimated to be living with a brain tumour or the long-term impact of their diagnosis, with many of them undergoing regular MRI scans to monitor tumour growth.\n\n“AI innovation that could reduce the need for contrast dye injections during MRI scans for some patients is welcome.\n\n“We look forward to understanding how this model could be used in future to improve care, minimise side effects and help inform treatment decisions for brain tumour patients.”", "url": "https://wpnews.pro/news/ai-could-help-spare-brain-tumour-patients-mri-dye-injections", "canonical_source": "https://www.independent.co.uk/news/health/netherlands-ucl-b3050851.html", "published_at": "2026-09-15 22:30:00+00:00", "updated_at": "2026-09-15 23:08:07.477363+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-research", "computer-vision"], "entities": ["UCL", "Dr Karen Noble", "Brain Tumour Research", "gadolinium", "meningioma"], "alternates": {"html": "https://wpnews.pro/news/ai-could-help-spare-brain-tumour-patients-mri-dye-injections", "markdown": "https://wpnews.pro/news/ai-could-help-spare-brain-tumour-patients-mri-dye-injections.md", "text": "https://wpnews.pro/news/ai-could-help-spare-brain-tumour-patients-mri-dye-injections.txt", "jsonld": "https://wpnews.pro/news/ai-could-help-spare-brain-tumour-patients-mri-dye-injections.jsonld"}}