The University of MichiganNews Services
The University Record Online
search
Updated 11:30 AM December 6, 2004
 

front

accolades

briefs

view events

submit events

UM employment


obituaries
police beat
regents round-up
research reporter
letters


archives

Advertise with Record

contact us
meet the staff
contact us
contact us
 
  Research
Computer program helps doctors diagnose lung cancer

Not all masses are cancer. When a person undergoes a scan to identify a lump or nodule, the radiologist looks at the texture, borders and shape to determine if it is malignant or just a benign growth.

Researchers at the Comprehensive Cancer Center are developing computer-aided diagnosis (CAD) methods to make that assessment easier. A computer program reads the same scans the radiologist views, and the combined judgment of the computer and radiologist helps detect more cancers, the researchers found.

"Our system is designed to help the radiologist. From our experiences in evaluating CAD for breast cancer, using computer aids significantly improves the performance of the radiologist in predicting malignancies of the masses. Radiologists with computers are able to detect more cancers than radiologists by themselves. We expect that CAD for lung cancer can achieve similar results," says Lubomir Hadjiyski, research assistant professor of radiology at the Medical School.

Hadjiyski presented results of the lung cancer study last week at the Radiological Society of North America's annual meeting in Chicago.

In the study, researchers looked at 41 CT scans that showed nodules in the lungs. Current scans and previous scans were fed through a computer program specially designed by the researchers to evaluate the size, texture, density and change over time of the nodules. Based on that information, the computer determines how likely the nodule is cancerous.

A CAD system is designed to provide a second opinion to radiologists. The computer analyzes the images with computer-vision techniques specially designed for a given type of cancer or disease. At the same time, the radiologist examines the images and evaluates the likelihood of cancer. The radiologist then compares the two results and makes a final decision.
"Radiologists with
computers are able to detect more cancers than radiologists by themselves."
—Lubomir Hadjiyski, research
assistant professor of radiology

"The radiologist is not perfect and the computer is not perfect, but working together they detect more cancers," Hadjiyski says.

Hadjiyski and his team have developed a similar program to detect breast cancer, and initial testing there is promising.

The computer program for both lung and breast cancer needs Food and Drug Administration approval before it can be offered clinically. Hadjiyski stresses that computers never will replace the radiologist entirely but that the technology is meant to complement the radiologist's judgment.

The one flaw with the computer-aided system is it may return false positive results, identifying masses as cancerous when they are benign. Hadjiyski notes, though, that overall the system detects more cancers.

As the researchers fine-tune the technology, they hope to see fewer false positives, and may actually help radiologists identify benign lesions and reduce the number of people undergoing biopsies. Researchers hope next to develop a system that will both detect a lesion and identify it as malignant or benign.

In addition to Hadjiyski, researchers were Berkman Sahiner, associate professor of radiology; Heang-Ping Chan, professor of radiology; Dr. Naama Bogot, clinical lecturer in radiology; Dr. Philip Cascade, professor of cardiology and radiology; and Dr. Ella Kazerooni, professor of radiology.

For more information about lung cancer, visit http://www.cancer.med.umich.edu/learn/lung.htm or call the Cancer AnswerLine at (800) 865-1125.

More Stories