**6. Conclusion**

12 Will-be-set-by-IN-TECH

type was not separately considered. Moreover, for fatty tissue GLM performs better, while, by contrary, for dense breasts the optimal results are obtained when employing GLMs to select

Figure (4) shows the AUC values for the best subset model combinations, employing GLMs and GAMs, for both fatty and dense tissue. Figure 5 represents the AUCs for the global

It can be observed that, for GLM, results obtained for fatty tissue are higher than those obtained for dense tissue. However, when employing the GAM, differences are lower, and

Sensitivity and false positive rates were also calculated for the best GLM and the best GAM. For linear models, results yielded a sensitivity of 88.31%, at a false positive rate of 3.7 FPs per image. For the same sensitivity, the false positive fraction achieved when reducing false

**GLM**

2 4 6 810

number of covariates

**GAM**

2 4 6 810

number of covariates

Fig. 4. "Optimal" models for both fatty and dense tissue. For each subset size, the AUC is

analysis, and for both fatty and dense tissue, for the best GLM and GAM.

a more reduced number of covariates have to be included in the study.

covariates.

0.60 0.70 0.80 0.90

0.60 0.70 0.80 0.90

shown for each model.

AUC

fatty dense

fatty dense

AUC

In this work, GLMs and GAMs were applied to the reduction of false positives yielded by a CAD system devoted to the detection of clusters of microcalcifications. Results indicate that not all the features extracted from the detected clusters are useful for the discrimination between true and false detections: Moreover, there are features that are relevant when the different type of tissue is considered, and their influence is different depending on the breast parenchyma.

After the reduction of false positives, the system is capable of discriminating and detecting clustered microcalcifications from digital mammograms, this suggesting that this CAD

ii<-F==1; X1=X[ii,];Y1=Y[ii] GLM0results=stepGAM(X0,Y0,"glm") GLM1results=stepGAM(X1,Y1,"glm")

GAM0results=stepGAM(X0,Y0) GAM1results=stepGAM(X1,Y1)
