Clinical Report: Distinguishing Hepatocellular Carcinoma from Hepatic Hemangioma

Overview

This study evaluates the diagnostic performance of radiomics features from diffusion-derived vessel density maps in differentiating hepatocellular carcinoma (HCC) from hepatic hemangioma (HG). The DDVD-based model achieved AUC values of 0.926 and 0.977 in validation and independent test cohorts, respectively.

Background

Hepatocellular carcinoma (HCC) is a highly vascularized tumor requiring prompt intervention, while hepatic hemangioma (HG) is a benign lesion that often does not require treatment. Accurate differentiation between these two conditions is crucial due to their differing management strategies. Traditional methods like needle biopsy carry risks and may yield false negatives.

Data Highlights

Key Findings

• The study included 232 patients, with 104 diagnosed with HCC and 128 with HG.
• A total of 1,197 features were extracted, with 10 most informative features retained from each image type.
• The DDVD model showed comparable performance to other models (b0, b50, ADC) in distinguishing HCC from HG.
• All models (b0, b50, ADC, DDVD) significantly outperformed the b800 model in the test cohort (p < 0.05).
• DDVD-based radiomics effectively quantifies spatial heterogeneity in microvascular characteristics.

Clinical Implications

The DDVD-based approach offers a non-invasive alternative for differentiating between HCC and HG.

Conclusion

The use of DDVD in radiomics presents a tool for the non-invasive differentiation of HCC from HG.

Related Resources & Content

1. European Radiology, 2023 -- Correlation of Apparent Diffusion Coefficient with Various Histopathological Characteristics in Intrahepatic Tumors
2. Frontiers in Oncology, 2026 -- CT-based habitat imaging integrated with radiomics and clinicopathology for noninvasive prediction of microvascular invasion in hepatocellular carcinoma
3. European Radiology, 2024 -- The Relationship Between Apparent Diffusion Coefficient, Tissue Stiffness, and Tumor Microenvironment Characteristics in Hepatocellular Carcinoma
4. European Radiology, 2024 -- Models for Distinguishing Benign and Malignant Liver Lesions Using Multiparametric Dual-Energy Non-Contrast CT
5. EASL Clinical Practice Guidelines on the management of hepatocellular carcinoma - PubMed
6. Diagnostic Performance of Radiomics for Differentiating Intrahepatic Cholangiocarcinoma from Hepatocellular Carcinoma: A Systematic Review and Meta-analysis - ScienceDirect
7. Diagnosis of liver hemangioma using magnetic resonance diffusion-derived vessel density (DDVD) pixelwise map: a preliminary descriptive study - PMC
8. EASL Clinical Practice Guidelines on the management of hepatocellular carcinoma - PubMed
9. Diagnostic Performance of Radiomics for Differentiating Intrahepatic Cholangiocarcinoma from Hepatocellular Carcinoma: A Systematic Review and Meta-analysis - ScienceDirect
10. Diagnosis of liver hemangioma using magnetic resonance diffusion-derived vessel density (DDVD) pixelwise map: a preliminary descriptive study - PMC