Differentiation of the Follicular Neoplasm on the Gray-Scale US by Image Selection Subsampling along with the Marginal Outline Using Convolutional Neural Network

Figure 5

Plots of differentiation in percentage (%) versus α for false benignancy of carcinoma and true benignancy of adenoma for each of the test data sets.

(a) True benignancy in percentage (%) for range [−1.5, 1.5] defined in (2), for Set_° denoted in Table 4

(b) True benignancy in percentage (%) for range [−1.5, 1.5] defined in (2), for Set_° denoted in Table 4

(c) True benignancy in percentage (%) for range [−1.5, 1.5] defined in (2), for Set_° denoted in Table 4

(d) True benignancy in percentage (%) for range [−1.5, 1.5] defined in (2), for Set_° denoted in Table 4

(e) False benignancy in percentage (%) for range [−1.5, 1.5] defined in (2), for Set_° denoted in Table 4

(f) True benignancy in percentage (%) for range [−1.5, 1.5] defined in (2), for Set_° denoted in Table 4

(g) False benignancy in percentage (%) for range [−1.5, 1.5] defined in (2), for Set_° denoted in Table 4