A study published in the August issue of Radiology shows that breast cancer detection was improved by 7.4 percent through the use of a computer aided detection (CAD) system. The study involved 8,682 women and was led by Dr. Robyn Birdwell and her former colleagues at Stanford University Hospital in Palo Alto, Calif. R2 Technology Inc.'s ImageChecker CAD system was used for the study.
This is the first prospective published study of its kind to be conducted in an academic medical setting.
"Breast cancer can be very challenging to detect and subtle clues can be missed by even the most experienced radiologist. This challenge is made even more difficult by the stress radiologists face to increase their efficiency and limit the number of women being recalled unnecessarily for further analysis," said Dr. Birdwell in the study. "Performed in our university hospital setting, our results show that, even among the most highly-trained radiologists, R2's CAD system helps detect cancers that would have otherwise been overlooked."
The study was conducted over an 18-month period on women with a median age of 54 years during routine mammography screening. Each mammogram was initially interpreted by a radiologist, followed immediately by reevaluation of the mammogram with the CAD system. Each recall was categorized in three ways:
- Both the radiologist and CAD agreed on the finding;
- The radiologist alone perceived the finding;
- Or, the CAD system prompted the radiologist to detect and act on the finding. The recalled patients were then tracked to determine the effect of CAD on the cancer detection and recall rates, among other findings.
The study found that the radiologists increased their cancer detection rate by 7.4 percent. The increase in the recall rate for patients was similar to the increase in the cancer detection rate.