{"id":21301,"date":"2026-10-13T12:10:13","date_gmt":"2026-10-13T12:10:13","guid":{"rendered":"https:\/\/news.theck1.no\/?p=21301"},"modified":"2026-10-13T12:10:13","modified_gmt":"2026-10-13T12:10:13","slug":"this-ai-reconstructs-what-youre-looking-at-from-a-brain-scan","status":"publish","type":"post","link":"https:\/\/news.theck1.no\/?p=21301","title":{"rendered":"This AI Reconstructs What You\u2019re Looking at From a Brain Scan"},"content":{"rendered":"

AI-rewritten:<\/strong> This is a summary of an article from Singularity Hub, rewritten by AI (Qwen, running locally) to make it easier to read. The facts come from the original article – read it for the full story.<\/p>\n

Singularity Hub • Edd Gent • October 12, 2026<\/strong><\/div>\n\n

Researchers at the Weizmann Institute of Science in Israel have developed an AI system called Brain-IT that reconstructs images from brain scans with high accuracy. Functional MRI scans track blood flow to reveal neural activity linked to what a person is seeing, but previous attempts often produced blurry results or invented details. This new method uses two separate neural networks to predict an image’s layout and contents before generating a detailed picture.<\/p>\n

<\/p>\n

The team trained the system on data from eight volunteers who viewed approximately 9,000 photographs in a high-resolution scanner, supplemented by simulations for over 120,000 additional images. When tested, Brain-IT outperformed ten other reconstruction methods on seven of eight standard measures of image similarity. It excelled at capturing the position, colors, and shapes of objects within a scene.<\/p>\n

The system can adapt to new individuals quickly because it relies on groups of brain cells whose functions are shared across people. With just one hour of scan data from a new volunteer, Brain-IT matches the results of methods trained on 40 hours of data. While this could aid paralyzed people in communicating, experts like Tommy Sprague note concerns regarding mental privacy as technology moves toward simpler devices like EEG headsets.<\/p>\n

\n

Source:<\/strong> Singularity Hub • Edd Gent • October 12, 2026<\/p>\n

Read the original article at Singularity Hub →<\/a><\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

AI-rewritten: This is a summary of an article from Singularity Hub, rewritten by AI (Qwen, running locally) to make it easier to read. The facts come from the original article – read it for the full story. Singularity Hub • Edd Gent • October 12, 2026 Researchers at the Weizmann Institute of Science in Israel<\/p>\n

READ MORE<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[8],"tags":[],"class_list":["post-21301","post","type-post","status-publish","format-standard","hentry","category-positive-news"],"_links":{"self":[{"href":"https:\/\/news.theck1.no\/index.php?rest_route=\/wp\/v2\/posts\/21301","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/news.theck1.no\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/news.theck1.no\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/news.theck1.no\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/news.theck1.no\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=21301"}],"version-history":[{"count":0,"href":"https:\/\/news.theck1.no\/index.php?rest_route=\/wp\/v2\/posts\/21301\/revisions"}],"wp:attachment":[{"href":"https:\/\/news.theck1.no\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=21301"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/news.theck1.no\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=21301"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/news.theck1.no\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=21301"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}