Computer-aided mammograms no better for detecting cancer

CAD software serves as a "second read" for
screening mammography, marking image pat-
terns for the radiologist to review. (Image
courtesy, of Hologic, Inc.)

Adding computerized detection to screening mammography adds to the cost, but not the effectiveness in terms of catching potentially dangerous lesions, a new study finds.

In what may be the largest study yet to look at the real-world value of the widely used add-on for mammography, Dr. Joshua Fenton, an assistant professor in the UC Davis Department of Family and Community Medicine, and colleagues with the Breast Cancer Surveillance Consortium analyzed screening results of 1.6 million mammograms from 684,956 women in seven states.

They looked at how effective computer-aided detection technology, or CAD mammography, as used in clinical practice is in detecting serious lesions and whether it reduced false positives.

What they found was that in clinical practice there was virtually no increase in the detection of serious lesions, but there was a slight increase in the number women recalled unnecessarily for further testing.

“After installation of CAD the number of (false-positives) detected increased by about 0.5 percent,” Fenton said by phone. “Another way to say that is that for every 200 women who get a screening mammogram, CAD would cause one additional woman to be recalled unnecessarily for further testing to exclude breast cancer.”

Fenton told Cancer Digest that theoretically, the way CAD mammography is supposed to work is the radiologist reads the patient’s mammogram and notes his or her findings. Then the radiologist runs the film, or if a digital machine is used, the image file, through the CAD machine. This is essentially a computer with specialized software programmed to recognize specific image patterns. The computer marks up certain areas of the image that may be cancer. The radiologist then evaluates those marked areas on the CAD-read image and decides whether to call the woman back for further evaluation.

And that is how it has worked in the clinical trials that led the FDA to approve the technology in 1998. One of those studies involving 12,860 patients in a community breast center was published in the journal Radiology in 2001, (220:781-786). That study showed 26.2 percent of cancers missed by a radiologist would be detected with the use of CAD.

Fenton pointed out that in the United Kingdom every mammogram is double-read, meaning two radiologists independently read the mammograms and then compare their findings. That practice has been shown in studies to increase the number of cancers captured and decrease the number of false positives. In this study, however, the use of computer-aided detection technology for the “second read” produced the opposite result.

In an editorial accompanying the current study, Dr. Donald A. Berry, of the Department of Biostatistics at M.D. Anderson Cancer Center, wrote that the significance of Fenton’s study is that it reflects real-world results where the daily pressures on radiologists to perform, likely has an impact on quality, while financial incentives also may play a role in the use of CAD.

“Why is CAD so popular?” Berry asked. “An obvious reason is that it is built into digital mammography equipment, which is increasingly common in the United States. Another is financial: In 2008, Medicare’s global reimbursement for CAD was $16.50. Still another is that CAD marks are comforting to the reader, even though the comfort may be misplaced.”

While an added $12 to $16 to the cost of a $80 mammogram may not seem like much, Fenton says the additional cost to the healthcare system is substantial. He said he has seen startup and capital equipment costs for CAD range from $75,000 to $200,000 for installation. After that there are additional fees for the interpretation. The $12 to $16 dollars cost is for Medicare recipients, but it may range from $25 to $45 for those covered by private health insurance. And finally there is the cost incurred by additional diagnostic testing for women who receive false positive tests.

“Our study raises important questions about how CAD is being used in practice right now,” Fenton said. “This is a study of real-world utilization and the effects in real-world practice. And our study suggests that the benefits of CAD are not being realized in practice right now. It is important for us to figure out why. Is it a limitation of the technology, or is not being used as it was designed, or is it a combination of both of these factors?”