R2 ImageChecker outperforms the iCAD SecondLook in study
The R2 ImageChecker M1000 significantly outperformed the iCAD Second Look in a comparative study of the two computer-assisted detection applications, according to study results published in the October issue of Radiology. Researchers examined the systems on a per study and a per image sensitivity basis in a mammography data set of noncalcified invasive breast malignancies smaller than 16 mm.
After the researchers received a waiver of informed consent granted by the Institutional Review Board that approved the HIPAA-compliant study, mammograms were obtained from two institutions. The Gundersen Lutheran Medical Foundation in La Crosse, Wis., and The Elizabeth Wende Breast Clinic in Rochester, N.Y., provided consecutive invasive carcinomas manifesting as noncalcified masses smaller than 16 mm, which were evaluated by using two commercially available CAD systems – the R2 ImageChecker M1000, version 5.0A and the iCAD Second Look, version 6.0.
To provide statistical power to test for a possible 10 percent difference in the sensitivity performance between the systems, 192 consecutive mammographic studies were collected; 182 unifocal, six multifocal, and four bilateral cancers.
The respective per study sensitivity, per image sensitivity, per study specificity, and mass false-positive marker rates were 81.8 percent, 64.7 percent, 39.2 percent, and 1.08 percent for the R2 system, and 60.9 percent, 42.6 percent, 31.4 percent, and 1.41 percent for the iCAD system.
The overall per study and per image sensitivities were significantly better for R2 than for iCAD, with a nonsignificant higher per study specificity and lower mass false marker rate on normal studies.
After the researchers received a waiver of informed consent granted by the Institutional Review Board that approved the HIPAA-compliant study, mammograms were obtained from two institutions. The Gundersen Lutheran Medical Foundation in La Crosse, Wis., and The Elizabeth Wende Breast Clinic in Rochester, N.Y., provided consecutive invasive carcinomas manifesting as noncalcified masses smaller than 16 mm, which were evaluated by using two commercially available CAD systems – the R2 ImageChecker M1000, version 5.0A and the iCAD Second Look, version 6.0.
To provide statistical power to test for a possible 10 percent difference in the sensitivity performance between the systems, 192 consecutive mammographic studies were collected; 182 unifocal, six multifocal, and four bilateral cancers.
The respective per study sensitivity, per image sensitivity, per study specificity, and mass false-positive marker rates were 81.8 percent, 64.7 percent, 39.2 percent, and 1.08 percent for the R2 system, and 60.9 percent, 42.6 percent, 31.4 percent, and 1.41 percent for the iCAD system.
The overall per study and per image sensitivities were significantly better for R2 than for iCAD, with a nonsignificant higher per study specificity and lower mass false marker rate on normal studies.