Advanced Imaging


Advanced Imaging Magazine

Updated: January 12th, 2011 10:01 AM CDT

Improving Results in Screening Mammograms

New study reviews more than 231,000 mammograms to show benefits of CAD compared to double-reading without it
The PeerView feature of the Hologic R2 CAD system
© Hologic
The PeerView feature of the Hologic R2 CAD system outlines the central density of a detected mass or distortion so the radiologist can evaluate the margin, shape and interior characteristics. Detected microcalcifications are highlighted so the radiologist can determine the number, shape and distribution.
The R2 system
© Hologic
The R2 system is designed to pinpoint regions of interest, efficiently drawing the radiologist’s eye to important image features. Calcification clusters are marked with the familiar R2 triangle and masses with the R2 asterisk. A special EmphaSize variable size feature displays marks in variable sizes correlating to the prominence of a mass or calcification features.
The R2 DMax™ platform
© Hologic
The R2 DMax™ platform, including ImageChecker™ CAD and DigitalNow™ film digitizing software can scan each film in just 22 seconds.
A Selenia direct digital image with R2 PeerView® CAD
© Hologic
A Selenia direct digital image with R2 PeerView® CAD outlines a density and highlights a cluster of microcalcifications to help visualize and analyze the specific features that may indicate malignancy.
The R2 CAD system
© Hologic
The R2 CAD system pinpoints the region of interest marking the mass with the traditional R2 asterisk and calcifications with the traditional R2 triangle.

By Barry Hochfelder

The author of the study (Comparison of Computer-Aided Detection to Double Reading of Screening Mammograms: Review of 231,221 Mammograms) is Dr. Matthew Gromet of the Breast Imaging Section of Charlotte Radiology, a Charlotte, N.C., imaging practice that does about 66,000 screening mammograms each year.

Dr. Gromet found that a single reader with CAD had a statistically significant increase in sensitivity (11 percent) and a smaller increase in recall rate (4 percent), when compared to a single reader without CAD assistance. He also found that single reading with CAD review, when compared with independent double reading, resulted in a not statistically significant increase in sensitivity but with a statistically significant lower recall rate. With manpower constraints limiting the use of double reading, Dr. Gromet concludes that "CAD appears to be an effective alternative that provides similar, and potentially greater, benefits."

The results were based on the performance of nine radiologists at Charlotte Radiology with a mean level of experience in mammography of 15 years. The mammograms in the study were screen-film studies obtained on the Hologic (Bedford, Mass.) R2 ImageChecker® CAD system. A total of 231,221 exams were included in the study; 49 percent of the exams were double-read without CAD and 51 percent were single-read with CAD. All mammograms in the study were obtained on Lorad M-IV equipment with Kodak Min-R and Kodak Min-R EV film.

The latest Hologic algorithm contains a range of software options, including breast geometry and lesion metrics. Breast geometry detects a breast outline for advanced sizing logic; lesion metrics creates advanced measures such as size, number of calcifications and distance to nipple. The system provides nine operating combinations, allowing the software to be adapted to the radiologists' reading preferences. Three separate operating points (sensitivity/false marker rate settings) can be selected for microcalcifications and masses.

For example, a site can choose to set the highest sensitivity for microcalcifications while selecting a balanced operating point for masses. This results in a lower overall false marker rate.

Subscribe to our RSS Feeds