Health insurer ODS Companies of Portland will curtail reimbursements for computer-aided detection (CAD) used in diagnostic medical imaging procedures. "The decision could have major ramifications for the CAD industry should it ripple to other third-party payors," reports AuntMinnie.com.

The policy decision appears to be the result of a study, which found that CAD did not clearly improve the detection of breast cancer. The research was sponsored by the National Cancer Institute (NCI), and published in the New England Journal of Medicine (4/5/07). The study was also reported in DOTmed News at the time.

In response to the NEJM publication, the American College of Radiology (ACR) stated that the decreased accuracy of mammography when using CAD was due to increased false positives, not to fewer cancers being detected. The study was designed in such a way that it was impossible to determine how many cancers would have been missed without the use of CAD, according to ACR.
DOTmed Business News recently interviewed a leading radiologist and CAD expert for an Industry Sector Report on mammography in our July 2007 issue. "CAD is a technology that helps radiologists read mammograms, improving the sensitivity for detecting cancer by about 25 percent," said Richard Cooper, MD, President and CEO of Imaging Centers of America, Inc. He explained that CAD uses sophisticated software that performs billions of calculations to recognize different presentations of cancer on mammograms. "The way a radiologist is supposed to [use CAD] is [to] look at the mammogram as he always did, formulate an opinion, and then pick up the CAD sheet as a second opinion and see if there is something on there that didn't catch his eye."

Dr. Cooper said that not all CAD technologies are created equal. "There are a lot of levels of CAD out there. There's good CAD and bad CAD," he said, stressing the high quality of equipment and training of radiologists at his facility in Valdosta, Ga. He noted that the better the radiologist, the less helpful CAD will be in spotting discrepancies.

ACR noted: "Clearly, CAD is not a substitute for human interpretation, and those using this tool must use it properly, as an adjunct to, rather than a replacement for, careful mammographic evaluation. Vendors also should strive to continue to improve the performance of CAD systems. Meanwhile, there is a fair amount of evidence outside the current study to suggest that, when properly used, CAD may indeed be worthwhile and it seems unwarranted to consider abandoning this potentially valuable tool at this time."

Watch for further coverage of this issue in DOTmed News.

More Industry Headlines