The researchers found that the AI was able to produce 84 percent of the images that matched the overall theme and attributes of the original photos, such as color and texture.
An AI model then fed the data and reconstructed the images based on participants' thoughts while inside a functional magnetic resonance imaging (fMRI) machine.
The team's work focuses on understanding activity from human brain scans and ultimately using that data to decipher what a person is thinking.
But to create these images, the artificial intelligence model used in the experiment had to undergo hours of training.
The AI model, known as Mind-Vis, was trained on a large pre-existing dataset with more than 160,000 brain scans.
This experiment is just one of several similar brain activity and AI-image experiments that have emerged over the past few years.
In early March, Vice conducted an experiment with similar purposes, with a group of researchers from Osaka University in Japan.
In 2019, Futurism announced an experiment by a team in Russia in which an artificial intelligence sketched what a person wearing an electrode cap would see at that moment.
The technology still has a long way to go before it can be used widely. However, Zijiao Chen, a PhD student at the National University of Singapore and one of the researchers on the study, wrote in an e-mail to Insider that with further development of the technology, it could be used in medicine, psychology and neuroscience.
Chen wrote that treatments for people with neurological disorders could potentially be produced with this technology. For example, people who cannot communicate verbally may instead communicate with their thoughts.
