CAD scores well in digital mammography

July 1, 2007

An iCAD computer-aided detection software package achieves high sensitivity with both computed radiography and full-field digital mammography, according to two new studies presented at the 2007 American Roentgen Ray Society meeting. In the same session, however, Dr. Edward Sickles warned that such positive studies may reflect optimal use and that radiologists should ensure they apply CAD software properly.

An iCAD computer-aided detection software package achieves high sensitivity with both computed radiography and full-field digital mammography, according to two new studies presented at the 2007 American Roentgen Ray Society meeting. In the same session, however, Dr. Edward Sickles warned that such positive studies may reflect optimal use and that radiologists should ensure they apply CAD software properly. Sickles is breast imaging section chief at the University of California, San Francisco.

Research on breast CAD is bountiful in screen-film mammography but limited in the digital world, said iCAD vice president and medical director Dr. Jeffrey Hoffmeister, who presented the results. The studies are the first published findings to show the iCAD product in action with digital systems. The software is currently approved for FFDM and is being used on an investigational basis with Fujifilm's CR unit.

In one study, researchers evaluated iCAD SecondLook (v7.2) with the GE Senographe FFDM unit at five user sites and compared results with CAD in the screen-film environment. The study included 45 biopsy-proven cancers and 38 normal cases. CAD with FFDM compared favorably with screen-film mammography, achieving 89% sensitivity with 1.6 false positives versus 90% sensitivity with 1.9 false positives, respectively. CAD picked up 100% of calcifications, compared with 95% on screen-film mammography, and 86% of masses, compared with 88% on screen-film.

In the other study, researchers evaluated iCAD in assessing 53 screen-detected cancers and 36 normal cases at two CR sites. CAD detected 47 of 53 cancers, for a sensitivity of 89%, with 2.2 false positives per normal case. Sensitivity reached 92% for calcifications and 88% for masses. In the 18 small cancers, sized 1 mm to 10 mm, sensitivity was good at 83%.

Furthermore, CAD correctly marked 91% of cancers in nondense breasts and 85% in dense tissue. An analysis of CAD sensitivity by histologic type revealed that CAD marked 92% of ductal carcinoma in situ, 89% of invasive ductal carcinoma, and 80% of invasive lobular and other cancers.

During a lecture about outcomes research in the same session, Sickles warned radiologists about proper use of CAD. In particular, radiologists should read a mammogram and make a decision without CAD about whether to recall the patient, he said. If the findings are suspicious, radiologists should not even use CAD but should just recall the patient. If the image appears normal, CAD should be applied.