Posted on March 8th, 2009 by
The results of a study recently published in the New England Journal of Medicine indicate that using computer-aided detection (computer programs that identify suspicious areas on mammograms) along with a single reader of mammograms could be an alternative to using double readers and could also improve the cancer detection rate from mammograms that are read by a single reader.
Screening mammography has made important contributions to improved breast cancer outcomes. In an attempt to improve the detection of breast cancer on mammographic images, some mammography facilities have implemented computer-aided detection (CAD) systems. CAD involves the use of a computer to evaluate a digital mammographic image. The technology marks areas of the image that appear abnormal and that should be reviewed further by the radiologist. CAD doesn’t replace a radiologist’s review of a mammogram, but it can supplement it.
In the United States, single reading of mammograms is standard practice, whereas double reading is the standard in many European countries. Some researchers have speculated that single reading plus CAD could match the performance of two readers. The prospective, randomized Computer-Aided Detection Evaluation Trial II (CADET II) compared single reading plus CAD with double reading during routine screening mammography in the United Kingdom National Health Service Breast Screening Programme (NHSBSP).
In this study 31,057 women undergoing routine screening mammography at three centers in England were randomly assigned to double reading, single reading with CAD, or both. In terms of cancer detection rates, the two methods appear to be equivalent: double reading detected 199 of 227 cancers (87.7%), and single reading with CAD detected 198 of 227 cancers (87.2%). However, the overall recall rate for single reading with CAD was significantly higher (3.9%) than the recall rate for double reading (3.4%).
The researchers concluded that single reading with CAD could be an alternative to double reading; however, more research is needed in order to determine whether adopting this method is cost-effective. The cost of the CAD equipment in addition to the costs associated with an increase in recall will have to be weighed against the potential savings in reader time.
Because single reading is the standard practice in the United States, CAD may have the potential to improve cancer detection rates to match those achieved by double reading.
Reference: Gilbert F., Astley, S., Gillan, M., et al. Single reading with computer-aided detection for screening mammography. New England Journal of Medicine. 2008: 359;16:1675-1684.
Related News: Mammography Technology Doesn’t Replace Doctors’ Judgment (12/8/2006)
Copyright © 2010 CancerConsultants. All Rights Reserved.
Tags: UNM CC Features
You must be logged-in to the site to post a comment.