Breast Cancer :: Computer-aided detection with computed radiography effective in detecting breast cancer

The use of computer-aided detection (CAD) with computed radiography (CR) is effective in the detection of breast cancer, according to a recent study conducted by radiologists at George Washington University Medical Center in Washington, D.C., and iCAD in Nashua, N.H.

“I wanted to undertake this study because we need to further define the performance of CAD with CR,” said Rachel Brem, MD, lead author of the study. “There is no doubt that CR will be an increasingly important technology in breast imaging and multiple studies have unequivocally demonstrated the improved detection of breast cancer with CAD. Therefore, we wanted to investigate these two technologies’ synergies,” she said.

The study included 53 cases with breast cancer that were evaluated using a CAD system. The researchers assessed the sensitivity of cancer detection by CAD, and the mammmographic density as well as cancer sizes.

The study showed that 47 of 53 cancer cases were detected by CAD (30 cancers in non dense breasts and 17 cancers in dense breasts). According to the study results, CAD detected 11 of 12 cancers manifesting as calcifications and 36 out of 41 masses.

“CAD had a high sensitivity of 89% with CR mammography that was maintained even in conditions that may lower the sensitivity of mammography, such as dense breasts and small lesions one millimeter or less,” said Dr. Brem.

“These results demonstrate that CAD’s performance with CR is comparable to that with film screen mammography and will result in the improved detection of breast cancer,” said Dr. Brem. “Our goal is to detect the earliest and smallest breast cancers. Multiple studies have demonstrated that the use of CAD with film screen mammography results in the detection of earlier and smaller breast cancers. Now we have shown similar performance with CR mammography. This is a very exciting finding as we move into the digital world in mammography,” she said.

The full results of the study will be presented on Tuesday, May 8, 2007 during the American Roentgen Ray Society Annual Meeting in Orlando, FL.

Leave a Comment