Table 7 Performance metrics in terms of \(\text{F}_1\) and AUC by the different approaches based on radiomics features and deep CNN features for HCC identification.

From: Wavelet radiomics features from multiphase CT images for screening hepatocellular carcinoma: analysis and comparison

Classification models

\(\varvec{\text{F}_1}\) (95% CI)

AUC (95% CI)

Proposed radiomics-based method

0.80 (0.73–0.86)

0.89 (0.83–0.93)

Deep CNN TL using VGG6\(^{*,+}\)

0.78 (0.73–0.85)

0.84 (0.77–0.90)

Deep CNN TL using ResNet-507,61\(^{*,+}\)

0.78 (0.71–0.84)

0.84 (0.76–0.90)

Deep CNN TL using GoogleNet8\(^{*,+}\)

0.80 (0.74–0.86)

0.86 (0.79–0.92)

Deep CNN using 3D-ResNet-189\(^{*,+}\)

0.80 (0.74–0.87)

0.87 (0.82–0.93)

  1. The methods marked with asterisk (\(*\)) and plus (+) symbols indicate statistical significance compared to the proposed method at a confidence level of 99.99%, as determined by the t-test and DeLong’s test, respectively.
  2. The significant AUC value is in bold.
Back to article page