{"id":11107,"date":"2024-05-08T21:48:22","date_gmt":"2024-05-09T04:48:22","guid":{"rendered":"https:\/\/mattfife.com\/?p=11107"},"modified":"2025-01-01T14:10:42","modified_gmt":"2025-01-01T21:10:42","slug":"more-advances-in-recreating-images-from-brain-scans","status":"publish","type":"post","link":"https:\/\/mattfife.com\/?p=11107","title":{"rendered":"More advances in recreating images from brain scans"},"content":{"rendered":"\n

I wrote about using AI trained models to re-create images from brain scans<\/a> before. Improvements have been rapidly developing.<\/p>\n\n\n\n

In a paper published in Neural Networks<\/em><\/a>, researchers at the National Institutes for Quantum Science and Technology (QST) in Japan were reportedly able to use artificial intelligence (AI) to reconstruct images solely from people\u2019s brain activity with over 75% accuracy.<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

They recorded the brain activity of subjects who viewed 1,200 various images while in a functional magnetic resonance imaging (fMRI) machine. “Score charts” that included 6.13 million factors such as color, shape, and texture were also created by making the AI recognize the images. The subjects were then shown another set of images that were different to the original images. Their brain activity was measured under the fMRI 30-60 minutes later while asked to imagine what kind of image they had seen.<\/p>\n\n\n\n

According to the publication, the scientists\u2019 groundbreaking method allowed them to use AI to reconstruct original images with a 75.6% accuracy rate \u2014 which is a big step from previous efforts with allowed a 50.4% accuracy rate<\/p>\n\n\n\n

Articles:<\/p>\n\n\n\n