Computer-Aided Detection in Screening Mammography Enhances Performance of a Single Reader

Thursday, February 14, 2008 General News
Email Print This Page Comment bookmark
Font : A-A+

BEDFORD, Mass., Feb. 13 Hologic, Inc.(Nasdaq: HOLX), a diversified medical technologies company specializing inimaging systems, diagnostics, and interventional devices dedicated to servingthe healthcare needs of women, today announced the publication of a largescale breast screening trial comparing a single radiologist using computer-aided detection (CAD) to double reading without CAD. The author of the studyis Dr. Matthew Gromet of the Breast Imaging Section of Charlotte Radiology, alarge imaging practice (approximately 66,000 screening mammograms a year) inCharlotte, North Carolina. The study(1), published in the on-line version ofthe American Journal of Roentgenology, the scientific journal of the AmericanRoentgen Ray Society, will appear in the April 2008 issue of the researchjournal. The study compared the recall rate, sensitivity, positive predictivevalue, and cancer detection rate for single reading with CAD, versus doublereading without CAD. Biopsy and pathology data for positive cases were alsocompared.

Dr. Gromet found that a single reader with CAD had a statisticallysignificant increase in sensitivity (11%) and a smaller increase in recallrate (4%), when compared a single reader without CAD assistance. He also foundthat single reading with CAD review, when compared with independent doublereading, resulted in a not statistically significant increase in sensitivitybut with a statistically significant lower recall rate. With manpowerconstraints limiting the use of double reading, Dr. Gromet concludes that "CADappears to be an effective alternative that provides similar, and potentiallygreater, benefits."

The results were based on the performance of nine radiologists atCharlotte Radiology with a mean level of experience in mammography of 15years. The mammograms in the study were screen-film studies obtained onHologic mammography equipment. The CAD technology used in the study was theHologic R2 ImageChecker(R) CAD system. A total of 231,221 exams were includedin the study; 49% of the exams were double read without CAD and 51% weresingle read with CAD.

"The Gromet study is a valuable addition to the body of knowledge on theperformance of radiologists reading screening mammograms with CAD assistance,"says Ronald A. Castellino, MD, FACR, Chief Medical Officer for Hologic. "Astrength of this study is the large number of malignancies as well as thelarge number of cases in both arms of the study (double reading without CADvs. single reading with CAD). The number of CAD cases is nearly four timesgreater than that reported in the Fenton paper(2) published in the New EnglandJournal of Medicine last year. An additional strength is the use of data fromthe same pool of experienced radiologists with considerable CAD experience."

Note on Sensitivity, Double Reading and CAD

The efficacy of screening mammography is enhanced when sensitivity is highand the recall rate is low. Double reading, though used by few practices inthe United States, is a method for increasing sensitivity commonly used inEuropean screening programs. CAD has become increasingly popular as analternative way to increase sensitivity, since double reading is time-consuming and because of a shortage of radiologists.

CAD has the potential to increase sensitivity of screening mammography bymarking areas of interest that might otherwise be overlooked by interpretingradiologists. However, CAD also may place false marks, identifying areas ofsuspicion that are not cancer. A small fraction of false marks may result inunnecessary patient recalls for further evaluation. The major goal for CAD isto reduce oversights when screening mammograms are read; the radiologist isstill responsible for lesion analysis and final interpretation of anexamination.

About Hologic, Inc.

Hologic, Inc. is a leading developer, manufacturer and supplier of premiumdiagnostics

Post your Comments

Comments should be on the topic and should not be abusive. The editorial team reserves the right to review and moderate the comments posted on the site.
* Your comment can be maximum of 2500 characters
I agree to the terms and conditions

News A - Z


News Search

Medindia Newsletters

Subscribe to our Free Newsletters!

Terms & Conditions and Privacy Policy.

Find a Doctor

Press Release Category

Press Release Archive

Stay Connected

  • Available on the Android Market
  • Available on the App Store