Computer aided detection could help breast cancer screening
September 2006
A novel approach to reading mammograms with the help of a computer could free up hundreds of medical man-hours, as well as speeding-up the breast screening process and potentially increasing accuracy.
Scientists in the Division of Imaging Science, working with The University of Aberdeen and Cancer Research UK, have found that the workload of radiologists could be halved by using a new computer-aided detection (CAD) system to help read breast x-rays and detect cancer.
With CAD only one expert is needed to look at each mammogram, rather than the usual two. Using the system could enable more face-to-face consultations, and all women to be screened as often as recommended.
CAD searches mammograms for suspicious features or irregularities that could be caused by cancer and, if it finds anything unusual, indicates it on a screen for a radiologist to look at. The team’s findings from a trial on mammograms taken in 1996 showed that this approach can be as successful as readings by two expert radiologists, and in some cases even more so.
The team has now started a new study, to confirm that the results of using CAD are still as good when used in real-life decision-making in the breast screening programme. It will involve 30,000 women in the Harpurhey, Eccles, Royton, Stalybridge and Withington areas of Greater Manchester, most of whom will have the single reading with CAD in addition to their routine double-reading.
Dr Caroline Boggis said: “The results of the first trial are very encouraging, and we really hope that local women will take part in the new study. It is an opportunity for women to have their mammograms read using the latest CAD technology, which is already available in America and some European countries.
Dr Sue Astley added: “The workload associated with mammography is extremely high, with double-reading taking place on around 1000 mammograms each week in Manchester. If we are able to confirm the promising results of the first study, using CAD could significantly help manpower problems in the breast screening service.”
- R2 Computer Aided Detection (CAD)
Details on the R2 website
The University of Manchester is not responsible for the content of external internet sites.
