Computer-Aided Breast Cancer Detection in Women Undergoing Screening Mammography

A Prospective Evaluation of Computer Aided Detection (CAD) in the NHS Breast Screening Programme [CADET II]

RATIONALE: A computer-aided detection program may help doctors find breast cancer sooner, when it may be easier to treat, in women undergoing screening mammography.

PURPOSE: This randomized clinical trial is studying how well computer-aided breast cancer detection works in women undergoing screening mammography.

OBJECTIVES:

• Compare, prospectively, the breast cancer detection rate and recall rate of single reading using computer-aided detection vs standard double reading in women undergoing screening mammography.

OUTLINE: This is a prospective, randomized, multicenter study. Participants are randomized to 1 of 3 screening arms.

• Arm I (double reading): Screening mammograms are independently reviewed by two readers (i.e., radiologist or radiographer), each of whom reports on any abnormalities and decides whether a participant is recalled for further assessment or returned home to routine screening. In the event there is disagreement between the readers' findings, a third reader acts as an arbitrator by rendering an interpretation of the mammogram and making the final decision to recall the participant or return to routine screening.
• Arm II (single reading with computer-aided detection [CAD]): Screening mammograms are reviewed initially by a single reader who reports on any abnormalities. The reader then re-examines the mammogram with the aid of CAD, a system that uses computer prompts to recall suspicious features or abnormalities that may have been overlooked or previously dismissed as being normal. Based on these evaluations, a recommendation is made by the reader to either recall the participant for further assessment or return home to routine screening. If there is a discrepancy between the reader's interpretation and the CAD findings, another reader may be consulted to review the mammogram.
• Arm III (double reading followed by single reading with CAD): Screening mammograms are reviewed by double reading as in arm I followed by single reading with CAD as in arm II.

Peer Reviewed and Funded or Endorsed by Cancer Research UK

PROJECTED ACCRUAL: A total of 30,000 participants will be accrued for this study.

DISEASE CHARACTERISTICS:

• Currently undergoing 2-view mammography for routine breast cancer screening at any of the following participating National Health Services Breast Cancer Screening Program centers:

  • Manchester
  • Coventry
  • Nottingham

• Hormone receptor status not specified

PATIENT CHARACTERISTICS:

• Female
• Menopausal status not specified

PRIOR CONCURRENT THERAPY:

• Not specified