Dataset and Adaptive Knowledge Based Model Configuration

In this section, the adaptive knowledge-based model is evaluated using the same configuration as described in the previous section and using exactly the same strategy for determining the segmentation operating point from an independent

Table 11.17: Frequency of normal and abnormal images

Type

Abnormal

Normal

1

53

54

2

20

20

3

28

36

4

99

90

Total

200

200

training set. The dataset is extended to include 200 normal images from four different breast types, 50 normal images drawn from each. The use of normal mammograms will demonstrate the specificity levels of the adaptive knowledge-based model. Table 11.17 shows the frequency of predicted breast groupings for normal and abnormal classes following breast type classification. The adaptive knowledge-based model is evaluated in its ability to provide an optimal segmentation for all the normal and abnormal mammograms.

0 0

Post a comment