There are already several products on the market, that read brainwaves to tell whether a vehicle driver is falling asleep. They can be contained in a baseball cap. Similar devices are also used in some new computer games. Now, scientst can use an fmri machine and a trained neural network to pick what picture you are looking at from a list of possibilities.

What's on your mind? Neuroscientists may one day find out

http://news.smh.com.au/whats-on-your-mind-neuroscientists-may-one-day-find-out/20080306-1xer.html

Venturing into the preserve of science fiction and stage magicians, scientists in the United States on Wednesday said they had made extraordinary progress towards reading the brain.

The researchers said they had been able to decode signals in a key part of the brain to identify images seen by a volunteer, according to their study, published by the British journal Nature.

The tool used by the University of California at Berkeley neuroscientists is functional magnetic resonance imaging (fMRI), a non-invasive scanner that detects minute flows of blood within the brain, thus highlighting which cerebral areas are triggered by light, sound and touch.

Their zone of interest was the visual cortex -- a frontal part of the brain that reconstitutes images sent by the retina.

Using two of their number as volunteers, the team built a computational model based on telltale blood-flow patterns in three key areas of the visual cortex.

The signatures were derived from 1,750 images of objects, such as horses, trees, buildings and flowers, that were flashed up in front of the subjects.

Using this model, the programme then scanned a new set of 120 brand new pictures to predict what kind of fMRI patterns these would make in the visual cortex.

After that, the volunteers themselves looked at the 120 new pictures while being scanned. The computer then matched the measured brain activity against the predicted brain activity, and picked an image that it believed was the closest match.

They notched up a 92-percent success rate with one volunteer, and accuracy was 72 percent in the other. The probability of this happening on the basis of chance -- i.e. the computer picking the right image out of the 120 -- is only 0.8 percent.

In an email to AFP, lead author Jack Gallant likened the task to that of a magician who asks a member of the audience to pick a card from a pack, and then figures out which one it was.