Added value of CE-CT radiomics to predict high Ki-67 expression in hepatocellular carcinoma

Abstract

Background: This study aimed to develop a computed tomography (CT) model to predict Ki-67 expression in hepatocellular carcinoma (HCC) and to examine the added value of radiomics to clinico-radiological features.

Methods: A total of 208 patients (training set, n = 120; internal test set, n = 51; external validation set, n = 37) with pathologically confirmed HCC who underwent contrast-enhanced CT (CE-CT) within 1 month before surgery were retrospectively included from January 2014 to September 2021. Radiomics features were extracted and selected from three phases of CE-CT images, least absolute shrinkage and selection operator regression (LASSO) was used to select features, and the rad-score was calculated. CE-CT imaging and clinical features were selected using univariate and multivariate analyses, respectively. Three prediction models, including clinic-radiologic (CR) model, rad-score (R) model, and clinic-radiologic-radiomic (CRR) model, were developed and validated using logistic regression analysis. The performance of different models for predicting Ki-67 expression was evaluated using the area under the receiver operating characteristic curve (AUROC) and decision curve analysis (DCA).

Results: HCCs with high Ki-67 expression were more likely to have high serum α-fetoprotein levels (P = 0.041, odds ratio [OR] 2.54, 95% confidence interval [CI]: 1.04-6.21), non-rim arterial phase hyperenhancement (P = 0.001, OR 15.13, 95% CI 2.87-79.76), portal vein tumor thrombus (P = 0.035, OR 3.19, 95% CI: 1.08-9.37), and two-trait predictor of venous invasion (P = 0.026, OR 14.04, 95% CI: 1.39-144.32). The CR model achieved relatively good and stable performance compared with the R model (AUC, 0.805 [95% CI: 0.683-0.926] vs. 0.678 [95% CI: 0.536-0.839], P = 0.211; and 0.805 [95% CI: 0.657-0.953] vs. 0.667 [95% CI: 0.495-0.839], P = 0.135) in the internal and external validation sets. After combining the CR model with the R model, the AUC of the CRR model increased to 0.903 (95% CI: 0.849-0.956) in the training set, which was significantly higher than that of the CR model (P = 0.0148). However, no significant differences were found between the CRR and CR models in the internal and external validation sets (P = 0.264 and P = 0.084, respectively).

Conclusions: Preoperative models based on clinical and CE-CT imaging features can be used to predict HCC with high Ki-67 expression accurately. However, radiomics cannot provide added value.

Keywords: Contrast-enhanced computed tomography; Hepatocellular carcinoma; Ki-67 expression; Radiomics.

Fig. 1

Flowchart of study inclusion. HCC, hepatocellular carcinoma

Fig. 2

Flowchart of tumor segmentation, feature extraction, and model building. Manual segmentation was performed in the multi-phase images, and radiomics features were extracted. Then, LASSO was used for radiomics feature selection and finally, a model was establishment. Receiver operating characteristic (ROC) curve and the DCA curve for predicting Ki-67 status were then developed. LASSO, least absolute shrinkage and selection operator; DCA, Decision curve analysis

Fig. 3

Representative images of multiphase contrast enhanced CT (CE-CT). A-E high Ki-67 HCC lession (black arrow), A, non-rim APHE and internal arteries (white arrow) on AP, B-C, hypodense halo and PVTT on PP, wash out and enhancing capsule on DP; consisting of “internal arteries” and “hypodense halos” defined as TTPVI, E, High and low Ki67 expression (70.5%), the brown regions represent positive Ki67 expression; And F-J show low Ki-67 expression HCC lesion (black arrow), F, no internal arteries on AP, G-I, no hypodense halos and PVTT on PP, non-enhancing capsule on DP, no TTPVI present. J, low Ki67 expression (8.2%); AP, arterial phase; PP, portal venous phase; DP, delayed phase; PVTT, portal vein tumor thrombus; TTPVI, two-trait predictor of venous invasion

Fig. 4

Three models predict ROC curves and DCA for KI-67-high expression. Figure A, D: training set; Figure B, E: internal test set; Figure C, F: external validation set. CR, clinico-radiologic; CRR, clinic-radiologic-radiomic