Purpose
The aim of our work is to evaluate the correlation of two-dimensional (2D) and three-dimensional (3D) radiomics and metabolic features of hepatocellular carcinoma (HCC) with tumour diameter, staging, and metabolic tumour volume (MTV).
Material and methods
Thirty-three patients with HCC were studied using
18
F-fluorodeoxyglucose positron-emission tomography with computed tomography (
18
F [FDG] PET/CT). The tumours were segmented from the PET images after CT correction. Metabolic parameters and 35 radiomics features were compared using 2D and 3D modes. The metabolic parameters and tumour morphology were compared using 2 different types of software. Tumour heterogeneity was studied in both metabolic parameters and radiomics features. Finally, the correlation between the metabolic and radiomics features in 3D mode, as well as tumour morphology and staging according to the American Joint Committee on Cancer (AJCC) staging were studied.
Results
Most of the metabolic parameters and radiomics features are statically stable through the 2D and 3D modes. Most of the 3D mode features show a correlation with metabolic parameters; the total lesion glycolysis (TLG) shows the highest correlation, with a Spearman correlation coefficient (rs) of 0.9776. Also, the grey level run length matrix/run length non-uniformity (GLRLM_RLNU) from radiomics features exhibits a correlation with a Spearman correlation coefficient of 0.9733. Maximum tumour diameter is correlated with TLG and GLRLM_RLNU, with rs equal to 0.7461 and 0.7143, respectively. Regarding AJCC staging, some features show a medium but prognostic correlation. In the case of 2D-mode features, all metabolic and radiomics features show no significant correlation with MTV, AJCC staging, and tumour maximum diameter.
Conclusions
Most of the normal metabolic parameters and radiomics features are statistically stable through the 3D and 2D modes. 3D radiomics features are significantly correlated with tumour volume, maximum diameter, and staging. Conversely, 2D features have negligible correlation with the same parameters. Therefore, 3D mode features are preferable and can accurately evaluate tumour heterogeneity.