GLMs and GAMs comparison considering the type of tissue

type='b',pch=1,ylim=c(0.6,0.90),cex=1.25,main="GLM") lines(GLM1results\$aucopt,type='b',pch=2,cex=1.25)

type='b',pch=1,ylim=c(0.6,0.90),cex=1.25,main="GAM") lines(GAM1results\$aucopt,type='b',pch=2,cex=1.25)

legend("bottomleft",c("fatty","dense"),lty=1,pch=c(2,1),

legend("bottomleft",c("fatty","dense"),lty=1,pch=c(2,1),

lines(GAMresults\$aucopt,type='b',pch=2,cex=1.25) legend("bottomleft",c("GLM","GAM"),lty=1,pch=c(1,2),

scheme is competent to complement the radiologists' efforts in their daily clinical practice, to help them as second readers in the interpretation of mammograms, and also to improve their diagnostic performance.

Future work will address the issue of reducing the number of false positives, without decreasing the sensitivity, by applying different statistical models to our dataset. Another way to improve the results yielded by the CAD system would be to deal with a higher quality of the digital images, because subtle clusters can be more easily identified in the detection process if the image is digitized at a greater resolution. Thus, to further improve the sensitivity, high quality of the digitized images is required.
