{"id":34306,"date":"2026-01-07T07:00:00","date_gmt":"2026-01-07T01:15:00","guid":{"rendered":"https:\/\/www.revoscience.com\/en\/?p=34306"},"modified":"2026-01-06T23:46:58","modified_gmt":"2026-01-06T18:01:58","slug":"artificial-intelligence-gives-a-clearer-picture-of-functional-mri-brain-data","status":"publish","type":"post","link":"https:\/\/www.revoscience.com\/en\/artificial-intelligence-gives-a-clearer-picture-of-functional-mri-brain-data\/","title":{"rendered":"Artificial intelligence gives a clearer picture of functional MRI brain data"},"content":{"rendered":"\n<p><strong><em>Chestnut Hill, Mass<\/em><\/strong> \u2013 Obtaining clearer functional MRI data about the brain and its disorders is possible using artificial intelligence, according to Boston College researchers who reported recently in\u00a0<em>Nature Methods<\/em>\u00a0that they developed an AI-assisted method to remove \u201cnoise\u201d, or image distortions, caused by movement, heartbeat, and other factors.<\/p>\n\n\n\n<p>Functional neuroimaging, also known as fMRI, is one of the most widely used noninvasive methods in neuroscience, with tens of thousands of studies published just in 2024. A major obstacle for fMRI research is that MRI data about brain responses is mixed with noise from movements and other sources.&nbsp;<\/p>\n\n\n\n<p>Removing noise more effectively could pave the way to new discoveries about the brain and its disorders, according to Boston College Associate Professor of Psychology Stefano Anzellotti, the paper\u2019s senior author. The new method developed by Anzellotti and two other researchers used generative AI to&nbsp;triple the performance of previous approaches.<\/p>\n\n\n\n<p>The findings could open new doors for brain research, Anzellotti said.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"700\" height=\"245\" src=\"https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods.webp\" alt=\"\" class=\"wp-image-34307\" style=\"width:840px;height:auto\" title=\"\" srcset=\"https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods.webp 700w, https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods-675x236.webp 675w, https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods-150x53.webp 150w\" sizes=\"auto, (max-width: 700px) 100vw, 700px\" \/><figcaption class=\"wp-element-caption\"><em><sup>For three decades, functional neuroimaging (fMRI) has been shaping the understanding of the human brain. A major obstacle for fMRI research is that information about brain responses is mixed with \u201cnoise\u201d: distortions in the measurements caused by head movements of the participants, heart rate, and perturbations in fMRI machines. Removing noise more effectively could pave the way to new discoveries about the brain and its disorders. Boston College researchers have developed a new method to remove noise from fMRI data using generative AI. Their study found that the method can improve by 200 percent\u00a0over previous approaches, offering the opportunity to measure brain responses more accurately in basic science as well as medical research.<\/sup><\/em><\/figcaption><\/figure>\n\n\n\n<p>\u201cWe wanted to improve the removal of noise from fMRI data,\u201d said Anzellotti. \u201cOther work had attempted to do this before. What is new about our work is that thanks to the use of generative AI we were able to improve by more than 200 percent over previous methods.\u201d<\/p>\n\n\n\n<p>The method developed by the researchers, known as DeepCor, outperforms other state-of-the-art denoising approaches on a variety of simulated datasets. In real fMRI data, DeepCor outperforms another widely-used method, known as CompCor, by 215 percent in removing noise from face responses, and by 339 percent in clarifying realistic synthetic data, generated to imitate the properties of a real fMRI dataset, according to Anzellotti.<\/p>\n\n\n\n<p>The AI learns which patterns are unique to brain regions that contain neurons and the unique patterns within regions of the brain that do not contain neurons. like the ventricles, said Anzellotti.<\/p>\n\n\n\n<p>\u201cNoise typically affects both sets of regions, therefore removing the patterns they have in common makes the unique patterns of the regions that contain neurons stand out,\u201d Anzellotti said.<\/p>\n\n\n\n<p>The team, including post-doctoral researcher Aidas Aglinskas and Yu Zhu, then an undergraduate student, studied the human brain with functional magnetic resonance imaging.<\/p>\n\n\n\n<p>Anzellotti said the scope of improvement was not expected.<\/p>\n\n\n\n<p>\u201cWe were surprised by how big the improvement was,\u201d he said. \u201cWe expected the method to do better, but we anticipated an improvement in the range of 10 percent to 50 percent. Improving by 200 percent was beyond our most optimistic expectations.\u201d<\/p>\n\n\n\n<p>Anzellotti\u2019s research will continue to explore improvements in fMRI readings.<\/p>\n\n\n\n<p>\u201cWe are looking at two key next steps: making the method as easy to access for as many other researchers as possible, and using it to denoise large public datasets so that the field can start benefiting from cleaner data as soon as possible,\u201d he said.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Chestnut Hill, Mass \u2013 Obtaining clearer functional MRI data about the brain and its disorders is possible using artificial intelligence, according to Boston College researchers who reported recently in\u00a0Nature Methods<\/p>\n","protected":false},"author":2,"featured_media":34307,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[],"class_list":["post-34306","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"featured_image_urls":{"full":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods.webp",700,245,false],"thumbnail":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods-200x200.webp",200,200,true],"medium":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods-675x236.webp",675,236,true],"medium_large":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods.webp",700,245,false],"large":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods.webp",700,245,false],"1536x1536":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods.webp",700,245,false],"2048x2048":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods.webp",700,245,false],"ultp_layout_landscape_large":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods.webp",700,245,false],"ultp_layout_landscape":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods.webp",700,245,false],"ultp_layout_portrait":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods-600x245.webp",600,245,true],"ultp_layout_square":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods-600x245.webp",600,245,true],"newspaper-x-single-post":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods.webp",700,245,false],"newspaper-x-recent-post-big":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods-550x245.webp",550,245,true],"newspaper-x-recent-post-list-image":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods-95x65.webp",95,65,true],"web-stories-poster-portrait":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods-640x245.webp",640,245,true],"web-stories-publisher-logo":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods-96x96.webp",96,96,true],"web-stories-thumbnail":["https:\/\/www.revoscience.com\/en\/wp-content\/uploads\/2026\/01\/anzellotti.nature.methods-150x53.webp",150,53,true]},"author_info":{"info":["RevoScience"]},"category_info":"<a href=\"https:\/\/www.revoscience.com\/en\/category\/news\/\" rel=\"category tag\">News<\/a>","tag_info":"News","comment_count":"0","_links":{"self":[{"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/posts\/34306","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/comments?post=34306"}],"version-history":[{"count":1,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/posts\/34306\/revisions"}],"predecessor-version":[{"id":34308,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/posts\/34306\/revisions\/34308"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/media\/34307"}],"wp:attachment":[{"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/media?parent=34306"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/categories?post=34306"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.revoscience.com\/en\/wp-json\/wp\/v2\/tags?post=34306"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}