Researchers at Weill Cornell Medicine, Cornell Tech and Cornell’s Ithaca campus are using AI-selected natural and synthetic images to study the visual processing areas of the brain. By using functional magnetic resonance imaging (fMRI) to record brain activity, researchers found that the images significantly activated specific target areas of the brain. They also demonstrated that they could use this data to create individualized models for each volunteer.
The goal is to create a data-driven approach to understand how vision is organized and uncover potential biases that may arise when using a limited set of researcher-selected images.
The study, published in Communications Biology, involved an existing dataset of natural images with accompanying fMRI responses from human subjects. Researchers used this data to train an artificial neural network (ANN) to model the human brain’s visual processing system. The researchers found that the predicted maximal activator images, both from natural and synthetic sources, activated the targeted brain regions significantly better than average activators.
The researchers believe that this approach can be useful for individualized visual system modeling and may have therapeutic potential in the future. They are now running similar experiments using a more advanced version of their image generator. Additionally, they hope to use the same approach to study other senses, such as hearing.
>>Join our Facebook Group be part of community. <<