Computer-aided mammography

Computer-aided mammography

April 28, 1995

Computer-aided mammography arrives

Researchers at the University of Chicago Medical Center have brought the first computer-assisted system to read mammograms into clinical use. Since mid-April, screening mammograms taken at the Medical Center have been read by a radiologist specializing in mammography, with additional guidance from the computer system.

Computer-aided diagnosis is expected to reduce--by as much as one-half--the number of breast cancers missed by radiologists.

Like the spell-check program on a word processor, which helps writers avoid typographical errors, the computer provides "an automated second opinion, alerting the radiologist to take a closer look at subtle warning signs that might have been missed on the first pass," said project leader Kunio Doi, PhD, Ralph W. Gerard Professor of biological sciences and director of the Kurt Rossman Laboratories for Radiologic Image Research at the University of Chicago. "We hope this system can significantly reduce the number of undetected breast cancers, even for the best screening programs."

"The world is not like the fictional Lake Wobegone, where all the children are above average," explained mammographer Robert Schmidt, MD, associate professor of radiology at the University and a member of the research team. "Only half of all radiologists are above average. This system should eventually make even the other half comparable to the experts."

Although mammography is currently the best method for the early detection of breast cancer, even skilled mammographers fail to spot between 10 and 30 percent of the cancers present in women who get screening mammograms. In as many as two-thirds of these "false negative" mammograms, the radiologist missed signs of cancer that, when the mammogram was more closely examined months or years later, were present and visible.

Eye fatigue and inattentiveness can explain some of those reading errors, but in other cases the mammographic abnormalities caused by the cancer were subtle enough to escape detection, sometimes even by the experts.

Up to half of early breast cancers contain little clusters of microcalcifications, tiny deposits of calcium that on a mammogram look like a constellation of faint stars. Although these minute specks can be obscured by the wealth of information contained in a typical mammogram, the University of Chicago research team has taught the computer to recognize these stars, even through the "clouds" of normal tissue, and to alert the radiologist to their presence. Another 40 percent of early breast cancers will appear on a mammogram as a mass. The computer can detect such masses by contrasting the architectural symmetry of the right and left breasts.

A series of preliminary studies has demonstrated the power of the computer. In the first study, an earlier version of the current system detected 85 to 90 percent of breast lesions in a set of 200 subtly abnormal mammograms, comparable to an experienced radiologist.

In a second study, the computer correctly identified more than 50 percent of breast cancers that had been missed by radiologists. In a third study, the combination of computer and radiologist outperformed a radiologist alone, increasing sensitivity from a quite respectable 85 percent up to 92 percent.
A fourth pre-clinical study, looking at 1,200 consecutive screening patients who had mammograms at the Medical Center, confirmed the system's usefulness and reliability in the clinical setting.

"The computer makes its own mistakes," admits Robert Nishikawa, PhD, assistant professor of radiology at the University of Chicago and one of the principal investigators in the project. It typically directs the radiologist's scrutiny to one or two benign areas on each mammogram, what physicians call false positives. "But radiologists can distinguish between the computer-selected false positives and malignancy," he says.

The computer's weaknesses are sufficiently different from radiologists' shortcomings that the two complement each other well. "It doesn't make human errors," says Schmidt. "The computer never forgets to look at the edges of the film. It doesn't get distracted by the phone, or by frequent interruptions. It doesn't get tired or cranky, or worry about its career choice."

"Since the computer serves as a second opinion rather than acting alone," notes Maryellen Giger, PhD, associate professor of radiology at the University of Chicago and another principal investigator in the project, "it doesn't have to be perfect to make a substantial difference. Radiologists will continue to make the final diagnostic decisions."

At an estimated cost of $100,000, about the same as a full-featured mammography machine, the system may in the future be available to community radiologists.

This project, which now involves more than 40 researchers, has been underway at the University of Chicago for more than ten years, with support from the National Cancer Institute, the American Cancer Society, the United States Army, the Whitaker Foundation and others.

The American Cancer Society estimates that 207,000 women will be diagnosed with breast cancer in the United States in 1995. Mammography is the only known method that can find small, curable cancers before they can be felt, and has been shown to significantly decrease deaths from breast cancer.