It has been suggested that computer aided detection (CAD), a system of bringing a mammography reader's attention to suspicious features, can help save time, manpower, and might help detect abnormalities that might otherwise be missed.
An initial study (CADET I) carried out in 2004, used CAD to re-read 10,000 mammograms which had previously been read by two radiologists. This study showed that the accuracy of the single reader using CAD was the same as double reading of mammograms.
CADET II was a follow up study aimed at testing CAD in the day to day environment of the breast screening programme. 31,293 women were recruited into the trial between September 2006 and August 2007. The cancer detection rates of the two reading regimes were comparable (86.5 per cent for single reading with CAD and 87.8 per cent for double reading). Recall rates were 3.9 per cent for single reading with CAD and 3.3 per cent for double reading, a small but significant, absolute difference of 0.6 per cent (a relative difference of 18%). The trial concluded that the cancer detection rate of single reading with CAD was comparable to that achieved by double reading with only a small increase in recall rate.
Single Reading with Computer-Aided Detection for Screening Mammography.
Back to key research in breast screening.
- NHSBSP home page
- Programme publications
- About breast screening
- What is breast screening?
- What does the NHS Breast Screening Programme do?
- When was the NHS Breast Screening Programme set up?
- What happens at a breast screening unit?
- Why are women under 50 not routinely invited?
- Are women screened over the age of 70?
- Does breast screening save lives?
- Does breast screening have any risks?
- What is Digital Mammography?
- Research in breast screening
- About breast cancer
- Programme logistics
- Frequently asked questions
- Programme statistics
- Mammography equipment reports
- Programme news index
- Useful links