Navigation Links
Brain Scans Let Computer 'Read' Visual Activity
Date:3/5/2008

Researchers suggest finding could lead to ways to decode the mind for therapeutic purposes

WEDNESDAY, March 5 (HealthDay News) -- Using brain scans and computer models, researchers report they have found a way to "read" visual activity in the brain.

The process relies on functional MRI to scan the brain for activity information related to the viewing of a chosen set of images. A computer database of brain activity-image links is then created, so that future viewings can be deduced based solely on an analysis of fresh fMRI patterns.

"We're not mind-reading," explained study co-author Jack L. Gallant, an associate professor in the department of psychology at the Helen Wills Neuroscience Institute at the University of California, Berkeley. "We're not reconstructing images of what people see or think. We can't do that yet, although it should be possible in principle."

"But already," he added, "this research makes clear that there's a huge amount of information -- way more than we have expected -- that we can dig out of fMRI signals to get a better understanding of brain function. And that is very important, both in terms of pure science and in terms of how this information might eventually lead to all kinds of applications in the future."

Gallant and his colleagues reported their findings in the March 5 online issue of Nature.

To probe the possibilities of brain imaging, Gallant enlisted two of his study co-authors -- Kendrick N. Kay and Thomas Naselaris -- to serve as healthy volunteers with good eyesight.

As a first step, both were shown 1,750 photographic images of animals, buildings, food, indoor scenes, outdoor scenes and people, during which fMRIs recorded activity in the primary visual cortex region of their brains.

The authors noted that fMRIs measure blood flow related to neural activity in the brain, and that the particular region observed is the brain's largest processing module.

The brain activity was then put into a computer program. During a second round, Kay and Naselaris were then shown 120 different photos. The computer model sifted through its previous store of brain activity-to-image patterns to "decode" the second round of fMRI data and find a correct match.

The authors stressed that their decoder program was not attempting image reconstruction, but rather image identification.

The results: When given a set of 120 photo options, the computer successfully identified the viewed images between 72 percent and 92 percent of the time. Broadened to 1,000 images, the success rate was 80 percent. With a pool of 1 billion images (as many, they noted, as are cataloged online by Google), the authors estimated that the decoding model would work about 20 percent of the time.

Gallant discussed a number of ways in which a fully developed method for decoding brain imagery might ultimately be applied as a practical medical tool.

"In theory, this could be used to help doctors evaluate the effectiveness of drugs designed to improve brain function," he noted. "Or it could, perhaps, be used to help fit neuro-prostheses for the blind, or to assist with psychotherapy, the interpretation of dreams or biofeedback. But all this is a long way down the road."

Dr. Joe Verghese, an associate professor of neurology at the Albert Einstein College of Medicine in New York City, agreed that the study has interesting implications but described it as "just a first step" in a complex effort to decode the brain.

"This kind of pattern recognition -- while consistent with previous work -- is still very targeted, very defined and very crude," he said. "They're using the noninvasive beauty of the MRI to look at the part of the brain that deals with vision, rather than trying to read thoughts. But I can see how, if they can carry it forward, there could eventually be medical applications that might be useful, and theoretically very positive."

"But trying to measure and image much more complex cognitive tasks will be much more challenging," Verghese cautioned. "And, of course, when applying recognition application to the real world, you will not want accuracy rates ranging from 20 to 90 percent. That would be a pretty scary endeavor. You will want to be very, very precise."

More information

For more on brain imaging, visit the The New York Academy of Sciences.



SOURCES: Jack L. Gallant, associate professor, department of psychology, Helen Wills Neuroscience Institute, University of California, Berkeley; Joe Verghese, M.D., associate professor, neurology, Albert Einstein College of Medicine, New York City; March 5, 2008, Nature, online


'/>"/>
Copyright©2008 ScoutNews,LLC.
All rights reserved  

Related medicine news :

1. Draining away brains toxic protein to stop Alzheimers
2. Vision restoration therapy shown to improve brain activity in brain injured patients
3. Clinical depression linked to abnormal emotional brain circuits
4. Brain imaging reveals breakdown of normal emotional processing
5. Brain cells work differently than previously thought
6. Vaccine Stops Alzheimers Brain Tangles
7. Research may unlock mystery of autisms origin in the brain
8. Scientists Spot Brains Free Will Center
9. Free will takes flight: how our brains respond to an approaching menace
10. Alcoholics With Cirrhosis Have More Brain Damage
11. Brain Lesions Predict MS Progression
Post Your Comments:
*Name:
*Comment:
*Email:
Related Image:
Brain Scans Let Computer 'Read' Visual  Activity 
(Date:3/29/2017)... CT (PRWEB) , ... March 29, 2017 , ... HealthCareMandA.com ... —on Thursday, April 20, 2017, at 1:00 PM ET. A recording of the webinar ... the Interactive Webinar Series. , Home health and hospice companies are still popular targets ...
(Date:3/29/2017)... ... March 29, 2017 , ... Immunotherapy has emerged as one ... cancers and is touted to be the next revolution in our fight against this ... in the form of immune checkpoint inhibitors such as PD-1 and PD-L1 inhibitors. , ...
(Date:3/29/2017)... PA (PRWEB) , ... March ... ... eastern suburbs and South Hills of Pittsburgh now have easier access to ... Pennsylvania only by Allegheny Health Network (AHN). Orthopaedic surgeons at Forbes Hospital ...
(Date:3/29/2017)... ... ... The Wharton School of the University of Pennsylvania is pleased to announce that ... gift to establish the Ken Moelis and Julie Taffet Moelis Advance Access Program ... for highly-qualified Penn undergraduates whose academic and career interests expand traditional notions of business ...
(Date:3/29/2017)... ... March 29, 2017 , ... VisualSP has helped over 1.5 million SharePoint ... option for on-premises installation of its Help System for SharePoint was at the farm ... into the entire tenant. , The company recently released a modified version of ...
Breaking Medicine News(10 mins):
(Date:3/29/2017)... Wound care devices and products are used ... The industry mainly consists of establishments engaged in manufacturing ... wounds caused by mechanical, chemical, thermal, and radiogenic trauma; ... diabetes, skin related diseases, immunological diseases, and other chronic ... the largest region in the wound care devices market ...
(Date:3/29/2017)... YORK , March 29, 2017 Global intravenous ... US$ 3 billion by 2021, growing at a CAGR of ... iron prescribed by a doctor to treat anemia or other ... iron level in the body. However, in some cases, oral ... the body and intravenous (IV) iron therapy comes into the ...
(Date:3/29/2017)... 2017  Novartis announced today that the US ... company,s Biologics License Application (BLA) filing and granted ... antigen receptor T cell (CAR-T) therapy, in relapsed ... with B-cell acute lymphoblastic leukemia (ALL). This is ... CAR-T. The priority review designation is expected to ...
Breaking Medicine Technology: