OHSU receives grant to study evolutionary computing for biomedical image analysis
PORTLAND, Ore. -- A new OGI School of Science & Engineering grant to study evolutionary computing for biomedical image analysis exemplifies the sort of new research opportunities the graduate school has capitalized on since its 2001 merger with Oregon Health & Science University.
"Whether it's computer science, environmental science or biomedical engineering, our goal is to be collaborative and work between disciplines to solve tough societal problems like people's health and well-being," said OGI Dean Ed Thompson, Ph.D.
Grants like this -- A $225,000, three-year grant from Intel to test a new biomedical image analysis technique -- are how OGI is using its traditional science and engineering expertise to branch into new, less traditional areas of study. The emphasis on interdisciplinary research, particularly in the health care arena, also will take advantage of many grantors' -- including the National Institutes of Health -- recent decision to give higher priority to interdisciplinary research.
Intel, for example, "has a strong interest in adaptive computing methods," said Melanie Mitchell, Ph.D., an OGI associate professor of computer science and engineering and principal investigator for the new grant. "Adaptive computing uses many ideas from evolution and biology to solve problems in computing."
Mitchell, an expert in genetic algorithms, and OGI assistant professor Xubo Song, Ph.D., who specializes in image processing and machine learning, will look at ways computer programs can be developed to more quickly and accurately analyze images and classify abnormalities in the prostate.
The prostate is part of the male reproductive system. Currently men of a certain age are given yearly PSA (prostate specific antigen) tests to determine whether their prostate is healthy. But because PSA levels can fluctuate, even in men with a healthy prostate, the test isn't always a good indicator. When PSA tests are inconclusive, physicians often do a biopsy, which can be painful and time-consuming.
"We are going to explore whether evolutionary computer programs can learn how to very accurately pinpoint on a CT (computed tomography) scan abnormalities in the prostate," said Mitchell. Relying on such an imaging technique to test the prostate would be far less invasive to men with high PSA levels, noted Mitchell.
About 190,000 new cases of prostate cancer are diagnosed in the United States every year, and about 30,000 men died from the disease in 2002, according to the American Cancer Society.
Evolutionary computing mimics the idea behind biological evolution. In a so-called "genetic algorithm," a population of computer programs evolve over time. Each computer program is an "organism," and each has a fitness value which measures how well it performs tasks. When computer programs have "offspring," the children are copies of their parents, though with mutations, and the process keeps repeating itself generation after generation.
The idea is that after many computations, the genetic algorithm will by natural selection produce a computer program that solves a given problem, rather than the programmer having to design it.
"You evolve the computer program, rather than build it," explained Mitchell. "This is what we'll try to do to design more advanced image processing programs."
For their study, Mitchell and Song will start with an initial population of random image processing programs. Each program is executed on an image and produces an analysis of that image by highlighting certain pixels (points in the image). Its fitness corresponds to how many pixels are highlighted correctly, compared with a "training" image that is highlighted correctly.
"When the program is finished running, you ask, How close is this to what I asked it to do? How many pixels did it get right?" said Mitchell. "Most of the offspring do horribly, but there are ones that do better than others," she said. "The ones that do better get to have more children, and some of their children will do even better."
A complete run of tens to hundreds of generations can take several hours or more, said Mitchell. "You definitely have to be patient and then you try it on another set of images." Mitchell is the author of the textbook An Introduction to Genetic Algorithms. Her research centers on intelligent systems, machine learning, evolutionary computation and complex systems. She joined OGI's Department of Computer Science and Engineering in 2002.
Source: Eurekalert & othersLast reviewed: By John M. Grohol, Psy.D. on 21 Feb 2009
Published on PsychCentral.com. All rights reserved.