Study shows breast CAD enhances single-reader performance
A comprehensive study of 231,221 screening mammograms conducted from 2001-2005 indicates that the utilization of computer-assisted detection (CAD) technology enhances performance of a single reader, yielding increased sensitivity with only a small increase in recall rate.
The study, scheduled to be published in the April 2008 edition of the American Journal of Roentgenology, was conducted by Matthew Gromet, MD, of the breast imaging section of Charlotte Radiology, a private-practice diagnostic radiology group in Charlotte, N.C.
Gromet’s research conducted a review of 231,221 screening mammograms interpreted by experienced mammographers from 2001 through 2005 in his community-based mammography program. In 112,413 (48.6 percent) of the exams, mammographers performed the first of two readings. In 118,808 (51.4 percent) of the exams, they performed a single reading aided by CAD.
The mammograms on which the study were based were screen-film studies obtained on Hologic mammography equipment; CAD technology used in the study was the Hologic R2 ImageChecker CAD system.
Results were based on the performance of nine radiologists at Charlotte Radiology with a mean level of experience in mammography of 15 years.
Gromet’s work compared the recall rate, sensitivity, positive predictive value, and cancer detection rate for single reading with CAD, versus double reading without CAD. Biopsy and pathology data for positive cases were also compared.
He 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 with a single reader without CAD assistance.
Gromet 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 and cost constraints limiting the use of double reading in the United States, CAD appears to be an effective alternative that provides similar, and potentially greater, benefits,” Gromet wrote.
The study, scheduled to be published in the April 2008 edition of the American Journal of Roentgenology, was conducted by Matthew Gromet, MD, of the breast imaging section of Charlotte Radiology, a private-practice diagnostic radiology group in Charlotte, N.C.
Gromet’s research conducted a review of 231,221 screening mammograms interpreted by experienced mammographers from 2001 through 2005 in his community-based mammography program. In 112,413 (48.6 percent) of the exams, mammographers performed the first of two readings. In 118,808 (51.4 percent) of the exams, they performed a single reading aided by CAD.
The mammograms on which the study were based were screen-film studies obtained on Hologic mammography equipment; CAD technology used in the study was the Hologic R2 ImageChecker CAD system.
Results were based on the performance of nine radiologists at Charlotte Radiology with a mean level of experience in mammography of 15 years.
Gromet’s work compared the recall rate, sensitivity, positive predictive value, and cancer detection rate for single reading with CAD, versus double reading without CAD. Biopsy and pathology data for positive cases were also compared.
He 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 with a single reader without CAD assistance.
Gromet 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 and cost constraints limiting the use of double reading in the United States, CAD appears to be an effective alternative that provides similar, and potentially greater, benefits,” Gromet wrote.