{"id":217325,"date":"2025-12-05T19:36:09","date_gmt":"2025-12-05T19:36:09","guid":{"rendered":"https:\/\/www.europesays.com\/ie\/217325\/"},"modified":"2025-12-05T19:36:09","modified_gmt":"2025-12-05T19:36:09","slug":"ai-model-could-help-radiologists-identify-brain-abnormalities-in-mri-scans","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ie\/217325\/","title":{"rendered":"AI model could help radiologists identify brain abnormalities in MRI scans"},"content":{"rendered":"<p>A new AI model could help radiologists identify brain abnormalities in MRI scans for all conditions including stroke, multiple\u00a0sclerosis\u00a0and brain tumors.<\/p>\n<p>The study, led by researchers at King&#8217;s College London and published in\u00a0<a href=\"https:\/\/www.news-medical.net\/health\/What-is-Radiology.aspx\" class=\"linked-term\" rel=\"nofollow noopener\" target=\"_blank\">Radiology<\/a> AI, shows how AI could address the growing backlogs due to radiologist shortages as well as an increasing demand for MRIs year on year for over a decade.<\/p>\n<p>These backlogs could result in treatment delays and poorer patient outcomes because MRI scans are vital for diagnosing and\u00a0monitoring\u00a0a range of\u00a0brain conditions such as tumors,\u00a0strokes\u00a0and aneurysms.<\/p>\n<p>AI could help ease the pressure on radiology departments\u00a0by triaging scans and increasing reporting speeds.\u00a0<\/p>\n<p>To do this, the model was first asked to distinguish between &#8216;normal&#8217; and &#8216;abnormal&#8217; scans,\u00a0which it did accurately when compared to assessments made by expert radiologists.\u00a0<\/p>\n<p>It was then tested on specific conditions &#8211; using new MRI scans which weren&#8217;t included in the training data &#8211; such as a stroke, multiple\u00a0sclerosis\u00a0and brain tumors,\u00a0and was able to recognise these accurately.<\/p>\n<p>Most AI models are currently built with large\u00a0datasets,\u00a0manually labelled by expert radiologists &#8211; which\u00a0are\u00a0expensive and time-consuming\u00a0to produce.\u00a0<\/p>\n<p>To overcome this,\u00a0the team\u00a0built an AI\u00a0model\u00a0that trained itself \u2013 without the need for expert radiologists &#8211; on\u00a0over\u00a060,000\u00a0existing brain\u00a0MRI\u00a0scans using\u00a0their\u00a0corresponding\u00a0radiology reports simultaneously.\u00a0<\/p>\n<blockquote><p>&#13;<\/p>\n<p>By training the system\u00a0on\u00a0scans and the language radiologists use to describe them, we can teach\u00a0it to\u00a0understand what abnormalities look like.&#8221;<\/p>\n<p>&#13;<br \/>\n&#13;<\/p>\n<p style=\"text-align: right;\">Dr. Thomas\u00a0Booth,\u00a0senior author of the study, Reader in Neuroimaging\u00a0at King&#8217;s College London\u00a0and Consultant Neuroradiologist\u00a0at King&#8217;s College Hospital<\/p>\n<p>&#13;\n<\/p><\/blockquote>\n<p>The researchers also designed the model so showed that\u00a0when given a scan\u00a0or textual query like &#8216;glioma&#8217;, a type of brain tumor,\u00a0the system could\u00a0search and retrieve similar cases, potentially supporting diagnostic review or teaching.\u00a0<\/p>\n<p>The study indicates that the model could\u00a0be used at the time of\u00a0scanning\u00a0to\u00a0flag\u00a0abnormal scans\u00a0and\u00a0support clinical decision-making by suggesting findings to radiologists, detecting potential errors in reports, or retrieving similar cases from past examinations.\u00a0This would speed up diagnoses\u00a0and\u00a0reduce reporting delays,\u00a0helping to improve patient outcomes.\u00a0<\/p>\n<p>&#8220;The next step is to run a randomised multicentre trial across the UK to see how abnormality detection improves workflows in practice. We are pleased to say that this trial will start in hospitals in 2026,&#8221;\u00a0commented Booth.\u00a0<\/p>\n","protected":false},"excerpt":{"rendered":"A new AI model could help radiologists identify brain abnormalities in MRI scans for all conditions including stroke,&hellip;\n","protected":false},"author":2,"featured_media":42213,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[78],"tags":[159,18,135,19,17,5968,11694,6425],"class_list":{"0":"post-217325","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-health","8":"tag-brain","9":"tag-eire","10":"tag-health","11":"tag-ie","12":"tag-ireland","13":"tag-radiology","14":"tag-sclerosis","15":"tag-stroke"},"share_on_mastodon":{"url":"https:\/\/pubeurope.com\/@ie\/115668646998326607","error":""},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/posts\/217325","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/comments?post=217325"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/posts\/217325\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/media\/42213"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/media?parent=217325"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/categories?post=217325"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/tags?post=217325"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}