Using computer-aided detection (CAD) to assess mammograms increases diagnosis of early stage cancers, but also increases diagnostic testing for women without breast cancer. Researchers suggest these findings are likely fuel breast cancer screening debates.
With CAD, radiologists use computer algorithms to mark and reassess potentially suspicious lesions that may have been missed on initial mammogram review. Despite limited evidence of its clinical effectiveness, the use of CAD in screening mammography has been broadly adopted.
Researchers reviewed health records for 163,099 women aged 67 to 89 years receiving 409,459 mammograms to determine the associations between CAD use during screening mammography and the incidence of ductal carcinoma in situ (DCIS) and invasive breast cancer, invasive cancer stage, and diagnostic testing. The researchers found that use of CAD was associated with greater DCIS incidence, but found no difference in invasive breast cancer incidence.
Among women with invasive cancer, use of CAD was associated with greater likelihood of detecting it in earlier stages (stages I and II vs II and IV). Use of CAD also increased diagnostic mammography, breast ultrasonography, and breast biopsy in women without cancer.
doi:10.7326/0003-4819-158-8-201304160-00002