Study Finds No Improvement in Diagnostic Accuracy of Digital Screening Mammography With Computer-Aided Detection

Study Finds No Improvement in Diagnostic Accuracy of Digital Screening Mammography With Computer-Aided Detection

By Matthew Stenger

ASCO POST

Key Points:
  • Overall, there was no difference in sensitivity or specificity for mammography with vs without computer-aided detection.
  • No differences in detection rates for overall cancer or invasive cancer were observed, but computer-aided detection was associated with a higher detection rate for ductal carcinoma in situ.

In a study reported in JAMA Internal Medicine, Lehman et al found no difference in the diagnostic accuracy of digital screening mammography with vs without computer-aided detection.

Study Details

The study assessed the accuracy of digital screening mammography interpreted with (n = 495,818) vs without (n = 129,807) computer-aided detection in 323,973 women screened between 2003 and 2009. Mammograms were interpreted by 271 radiologists from 66 sites in the Breast Cancer Surveillance Consortium. A total of 3,159 breast cancers were identified within 1 year of screening through linkage with tumor registries.

Comparative Accuracy

Overall, there was no significant difference in the accuracy of mammography with vs without computer-aided detection. Sensitivity of mammography was 85.3% with vs 87.3% without computer-aided detection, and specificity was 91.6% vs 91.4%. Sensitivity was 82.1% vs 85.0% for invasive cancer and 93.2% vs 94.3% for ductal carcinoma in situ.

The overall cancer detection rate was 4.1 per 1,000 women screened both with and without computer-aided detection, and the invasive cancer detection rate was 2.9 vs 3.0 per 1,000 women. The ductal carcinoma in situ detection rate was higher with computer-aided detection (1.2 vs 0.9 per 1,000; P < .03). Computer-aided detection did not improve intraradiologist performance; sensitivity was reduced for interpretation of mammograms with vs without computer-aided detection among 107 radiologists who interpreted mammograms in both ways (odds ratio = 0.53, 95% confidence interval [CI] = 0.29–0.97).

The investigators concluded: “Computer-aided detection does not improve diagnostic accuracy of mammography. These results suggest that insurers pay more for [computer-aided detection] with no established benefit to women.”

The study was supported by the National Cancer Institute (NCI) and the NCI-funded Breast Cancer Surveillance Consortium.

Constance D. Lehman, MD, PhD, of Massachusetts General Hospital, Avon Foundation Comprehensive Breast Evaluation Center, is the corresponding author of the JAMA Internal Medicine article.

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s