How do you improve mammogram accuracy? Add noise

Dec 22, 2009

Members of a Syracuse University research team have shown that an obscure phenomenon called stochastic resonance (SR) can improve the clarity of signals in systems such as radar, sonar and even radiography, used in medical clinics to detect signs of breast cancer. It does this by adding carefully selected noise to the system.

The result has been a distinct improvement in the system's ability to correctly identify precancerous lesions, plus a 36 percent reduction in false positives. The inventors have developed a novel method of calculating precisely the correct type and level of noise to add to existing noise in radiography or a similar system.

"We see a of applications for this technology," says research assistant professor Hao Chen. "If a system's performance is unsatisfactory, we add to the system based on a specific algorithm that can significantly improve system performance."

A patent covering the technology has been issued to Chen, Distinguished Professor Pramod K. Varshney and research professor James Michels. All are associated with SU's L.C. Smith College of Engineering and Computer Science.

In mammography studies carried out by doctoral candidate Renbin Peng, the challenge was to identify clusters of micro-calcifications in . These early signs of precancerous conditions average only 0.3 mm in size and offer only subtle contrast with surrounding tissue. In addition to improving detection of these lesions, the group has reduced false positives by more than a third.

While the current focus of the research group is on medical uses of stochastic resonance, other applications are expected in enhancing audio, video, geophysical, environmental, radar and other signals. The group has been receiving support from the U.S. Air Force Office of Scientific Research.
Ongoing investigations by the Syracuse group are expected to produce further improvements in the efficiency and robustness of the SR-based detection techniques.

A paper by the inventors on theory of stochastic resonance stochastic resonance effect in signal detection was published by IEEE Transactions in Signal Processing in July 2007 and became one of the top 10 downloads of that month. Another paper, covering the mammography studies, co-authored by Peng was published in IEEE Journal of Selected Topics in Signal Processing in February 2009.

Explore further: Using social media for behavioral studies is cheap, fast, but fraught with biases

Provided by Syracuse University

5 /5 (1 vote)
add to favorites email to friend print save as pdf

Related Stories

How our senses combine to give us a better view of the world

Nov 12, 2008

From a young age we are taught about the five senses and how they help us to explore our world. Although each sense seems to be its own entity, recent studies have indicated that there is actually a lot of overlap and blending ...

New mammography technology improves cancer detection

Nov 28, 2007

A new radiological diagnostic tool called stereo mammography allows clinicians to detect more lesions and could significantly reduce the number of women who are recalled for additional tests following routine screening mammography.

Finding a Better Way to Quiet Noisy Environments

Apr 05, 2006

Researchers at UCSD report in the April 4 issue of the Journal of Sound and Vibration a new mathematical algorithm designed to dramatically improve noise-cancellation technologies that are used to quiet everything from a ...

Recommended for you

Forging a photo is easy, but how do you spot a fake?

Nov 21, 2014

Faking photographs is not a new phenomenon. The Cottingley Fairies seemed convincing to some in 1917, just as the images recently broadcast on Russian television, purporting to be satellite images showin ...

Algorithm, not live committee, performs author ranking

Nov 21, 2014

Thousands of authors' works enter the public domain each year, but only a small number of them end up being widely available. So how to choose the ones taking center-stage? And how well can a machine-learning ...

User comments : 0

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.