Skip to main content

Table 5 Misclassification rate of texture analyses from AP, EP, HBP and T2 images among poorly-differentiated, well-differentiated and moderately-differentiated HCC

From: Texture analysis of MR images to identify the differentiated degree in hepatocellular carcinoma: a retrospective study

 

A verse C

B verse C

A verse B

AP

EP

HBP

T2

AP

EP

HBP

T2

AP

EP

HBP

T2

RDA (%)

44.26

34.43

50.82

48.33

55.00

50.50

47.50

46.25

34.33

46.27

44.78

47.76

PCA (%)

42.62

36.07

47.57

50.00

53.75

53.75

48.75

40.00

28.36

37.31

44.78

40.30

LDA (%)

14.75

4.92

9.84

10.00

17.50

33.75

33.75

20.00

26.87

23.88

11.94

26.87

NDA (%)

11.48

4.92

6.56

3.33

10.00

13.75

13.75

12.50

8.96

14.93

4.48

7.46

  1. Note: RDA raw data analysis, PCA principal component analysis, LDA linear discriminant analysis, NDA nonlinear discriminant analysis
  2. A: well-differentiated HCC, B: moderately-differentiated HCC, C: poorly-differentiated HCC; AP arterial phase, EP equilibrium phase images, and HBP hepatobiliary phase