Dec. 18 (UPI) -- A new computerized model for lung cancer detection could replace the old method of using surgical biopsies, a new study says.
New findings published Tuesday in the journal Radiology show how researchers used computer imaging to probe in and around a lung image on a CAT scan to distinguish a malignant and benign tumor with 80 percent accuracy. The radiologist only had 60 percent accuracy.
"The number-one reason I'm excited about these papers is that we are in truly uncharted territory," Anant Madabhushi, a researcher at Case Western Reserve University and study author, said in a news release. "We've all been trained that 'the money is in the tumor,' but what these papers demonstrate unequivocally is that there is a lot of signal outside the tumor, too."
Specifically, the method uses deep learning diagnostic computers to analyze the CAT scan of an image of blood vessels pumping into a potentially cancerous tumor on a lung.
More promising research performed earlier this year showed computer-extracted patterns of "vessel tortuosity"-- or twisted blood vessels -- that could tell between malignant and benign tumors with 85 percent accuracy.
"We're now doing something that radiologists do not typically tend to do," Madabhushi said. "Radiologists have been looking at CAT scans for 40 or 50 years, but they have never looked in these locations or found what we've found."
The computer model gives scientists the capability to take CAT scan results one step further.
"So there's the economics of it, but also the anxiety for the patient," Madabhushi said. "We don't really do a great job of lung cancer screening because we don't have better tools. This would be a far, far better tool."