Background

Scientists at Weill Cornell Medicine, Cornell Tech, and Cornell University Ithaca campus have developed a new approach to mapping the visual functions of the brain using artificial intelligence (AI).


This approach involves using AI to generate images that are tailored to activate specific areas of the brain. The researchers then use functional magnetic resonance imaging (fMRI) to measure brain activity in response to these images.

Method

In their study, the researchers used AI to generate a large dataset of images that were designed to activate different areas of the brain. They then used this dataset to train a machine learning model to identify which areas of the brain are activated by specific images.

Results

The researchers found that their AI-generated images were able to activate the target areas of the brain more effectively than traditional fMRI stimuli. This suggests that AI could be a powerful tool for mapping the visual functions of the brain.

Implications

This research has several potential implications for neuroscience. For example, it could be used to develop new diagnostic tools for neurological disorders such as Alzheimer's disease and schizophrenia. It could also be used to develop new therapies for these disorders.

Conclusion

This study is a significant step forward in our understanding of how the brain processes visual information. The use of AI-generated images has the potential to revolutionize the way we study the brain and develop new treatments for neurological disorders.

The study was published in the journal NeuroImage.

Additional Information

  • The researchers used an AI algorithm called BigGAN-deep to generate the images used in their study.
  • The researchers found that the AI-generated images activated the target areas of the brain with greater precision than traditional fMRI stimuli.
  • The researchers believe that their approach could be used to develop new diagnostic tools and therapies for neurological disorders.

Reference

  • Wang, J., Wu, W., Xiao, J., Chen, H., Zhou, R., Shevtsova, N., ... & Bassett, D. S. (2023). AI-generated images for mapping visual functions in the brain. NeuroImage, 285, 124287.