Rough Hybrid Scheme: An application of breast cancer imaging - Rough Fuzzy Image Analysis: Foundations and Methodologies - page 92

image4 M-FCMwith3clusters M-FCMwith5clusters

M-FCMwith6clusters M-FCMwith7clusters S-FCMwith7clusters

TABLE 5.2 FCM Segmentation results with different number of clusters

(a)Rulesnumbers (b)Classificationaccuracy

TABLE 5.3 Rules and classification accuracy

Table 5.3 shows the number of generated rules before and after pruning process and
the overall classification accuracy. From Table 5.3(a) we can observe that the number of
generated rules for all algorithms is very large. It is greater than the number of objects and
that makes classification unacceptably slow. Therefore, it is necessary to prune the rules
during their generation. Table 5.3(b) shows that rough hybrid approach accuracy is much
better than the neural networks, rough sets, support vector machine and decision tree.

5.5 Conclusion

In this chapter, an application of breast cancer imaging has been chosen and rough hy-
bridization scheme that combines the advantages of fuzzy sets, rough sets and neural net-
works in conjunction with statistical feature extraction techniques, have been applied to
test their ability and accuracy in detecting and classifying breast cancer images into two