The same technology used to help naval experts overcome the challenge of finding mines under the sea is helping medical researchers pinpoint cancer cells in the human body.
Doctors review hundreds of microscopic cells in search for abnormal cancer cells. Using a software toolkit called FARSIGHT (Fluorescence Association Rules for Quantitative Insight), they are able to find abnormal cells faster -- the software uses examples of abnormal cells to scan for others -- but the results can often be wrong.
To overcome this and enhance the cell-sifting software, Dr. Larry Carin, professor at Duke University added active learning software algorithms developed by the Office of Naval Research, resulting in more properly categorized cells.
Science Daily reports this technology is already being put into action:
A medical team at the University of Pennsylvania is applying the ONR algorithms, embedded into FARSIGHT, to examine tumors from kidney cancer patients. Focusing on endothelial cells that form the blood vessels that supply the tumors with oxygen and nutrients, the research could one day improve drug treatments for different types of kidney cancer, also known as renal cell carcinoma.
"With the computer program having learned to pick out an endothelial cell, we have now automated this process, and it seems to be highly accurate," said Dr. William Lee, an associate professor of medicine, hematology and oncology at the university who is leading the research effort. "We can begin to study the endothelial cells of human cancer -- something that is not being done because it's so difficult and time-consuming to do."
It usually takes days, even weeks, for a pathologist to manually pick out all the endothelial cells in 100 images. The enhanced FARSIGHT toolkit can accomplish the same feat in a few hours with human accuracy.
The naval software was originally developed to identify unknown objects in the ocean and, according to Dr. Jason Stack, the program officer at ONR who funded Carin's research, "get the man out of the minefield."