CT-Based Radiomics for Non-Invasive Prediction of Ki-67 Expression in Hepatocellular Carcinoma.
Meilong Wu1, Zhiyong Du1, Ying Xiao2
1Division of Hepatobiliary and Pancreas Surgery, Department of General Surgery, Shenzhen People's Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen, Guangdong, People's Republic of China.
Journal of Hepatocellular Carcinoma
|March 23, 2026
Summary
Non-invasive radiomics analysis using contrast-enhanced CT effectively predicts Ki-67 expression in hepatocellular carcinoma (HCC). This approach enhances clinical decision-making for HCC patients.
Area of Science:
- Oncology
- Radiology
- Medical Imaging
Background:
- Assessing Ki-67 expression in hepatocellular carcinoma (HCC) is crucial for treatment planning.
- Non-invasive methods for Ki-67 assessment in HCC are limited, necessitating advanced imaging techniques.
Purpose of the Study:
- To evaluate the capability of radiomics analysis based on contrast-enhanced computed tomography (CECT) in predicting Ki-67 expression in HCC.
- To develop and compare models for predicting Ki-67 expression using radiomics, clinical factors, and a combination of both.
Main Methods:
- Patients with HCC undergoing curative hepatectomy were included.
- Radiomics features were extracted from CECT images and selected using Least Absolute Shrinkage and Selection Operator (LASSO) regression.
- Clinical, radiomics, and combined models were constructed to predict Ki-67 expression, with performance evaluated using C-index and validated with DeLong tests and decision curves.
Main Results:
- Four stable radiomics features, along with alpha-fetoprotein and intratumoral necrosis, were identified as independent predictors of Ki-67 expression.
- The combined model demonstrated the highest predictive performance with a C-index of 0.88, outperforming the clinical model (0.75) and radiomics model (0.82).
- Validation confirmed that incorporating radiomics features significantly improved predictive efficacy.
Conclusions:
- Contrast-enhanced CT-based radiomics provides a non-invasive and effective method for predicting Ki-67 expression in HCC.
- The developed radiomics model holds significant potential for clinical decision-making in HCC management.
