Comparison of standard and double reading and computer-aided detection (CAD) of interval cancers at prior negative screening mammograms: blind review
2003

Comparing Mammogram Readings with and without Computer Assistance

Sample size: 120 publication Evidence: moderate

Author Information

Author(s): S. Ciatto, M. Del Turco Rosselli, P. Burke, C. Visioli, E. Paci, M. Zappa

Primary Institution: Centro per lo Studio e la Prevenzione Oncologica, Florence, Italy

Hypothesis

Does computer-aided detection (CAD) improve the diagnostic accuracy of mammograms compared to standard readings?

Conclusion

The study found that CAD increased sensitivity in detecting interval cancers but also led to a higher recall rate.

Supporting Evidence

  • CAD marked 340 sites for second review, improving sensitivity for interval cancers.
  • 19 out of 19 radiologists showed increased sensitivity when using CAD.
  • The average increase in sensitivity with CAD was 9.9%.

Takeaway

This study looked at how well computers can help doctors find breast cancer in mammograms. It found that computers can help find more cancers, but they also make doctors call back more patients for extra checks.

Methodology

The study involved 120 mammograms, comparing readings by radiologists with and without CAD assistance.

Potential Biases

The order of readings (CONV followed by CAD) may have influenced radiologists' performance.

Limitations

The study design may not reflect real-world conditions, as it was conducted in a controlled environment with heightened awareness among radiologists.

Participant Demographics

Radiologists from a population-based mammography screening program in Tuscany, Italy.

Statistical Information

P-Value

p<0.01

Statistical Significance

p<0.01

Digital Object Identifier (DOI)

10.1038/sj.bjc.6601356

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication