Multimodal imaging prediction models for preoperative microvascular invasion in hepatocellular carcinoma: A systematic review and predictive accuracy analysis from biomechanical perspective
Abstract
This meta-analysis aimed to evaluate the accuracy of multimodal imaging prediction models for preoperative microvascular invasion (MVI) in hepatocellular carcinoma (HCC) patients from both radiological and biomechanical perspectives. We systematically searched PubMed, Embase, and Cochrane Library databases, including 42 studies with 10,876 patients. Statistical analysis using a bivariate random-effects model assessed the diagnostic performance of different imaging modalities and prediction model types, with particular emphasis on biomechanical features including tissue elasticity, vascular wall mechanics, and tumor microenvironment properties. Results demonstrated excellent performance of multimodal imaging prediction models incorporating biomechanical parameters in MVI prediction, with a pooled sensitivity of 0.78 (95% CI: 0.73–0.82), specificity of 0.80 (95% CI: 0.76–0.84), and area under the curve (AUC) of 0.86 (95% CI: 0.83–0.89). Deep learning approaches demonstrated particular advantages in feature extraction and biomechanical pattern recognition, achieving superior performance (AUC 0.88) through their ability to automatically learn hierarchical representations from complex imaging data and mechanical data. The integration of multiple imaging modalities with biomechanical parameters further enhanced predictive accuracy (AUC 0.91), offering complementary information that captures different aspects of tumor biology, mechanics and behavior. This enhanced performance of multimodal combinations, particularly when leveraging biomechanical features and deep learning algorithms, suggests significant potential for improving clinical decision-making and treatment planning in HCC patients. Future research should focus on large-scale prospective validation, standardization of biomechanical measurements, and clinical application assessment to further enhance the accuracy and clinical value of MVI prediction.
References
1. Lee, S., Kim, S. H., Lee, J. E., Sinn, D. H., & Park, C. K. (2017). Preoperative gadoxetic acid-enhanced MRI for predicting microvascular invasion in patients with single hepatocellular carcinoma. Journal of Hepatology, 67(3), 526-534.
2. Xu, X., Zhang, H. L., Liu, Q. P., Sun, S. W., Zhang, J., Zhu, F. P., ... & Yan, Z. P. (2019). Radiomic analysis of contrast-enhanced CT predicts microvascular invasion and outcome in hepatocellular carcinoma. Journal of Hepatology, 70(6), 1133-1144.
3. Hu, H. T., Wang, Z., Huang, X. W., Chen, S. L., Zheng, X., Ruan, S. M., ... & Wang, W. (2019). Ultrasound-based radiomics score: a potential biomarker for the prediction of microvascular invasion in hepatocellular carcinoma. European Radiology, 29(6), 2890-2901.
4. Zhao, H., Hua, Y., Dai, T., He, J., Tang, M., Fu, X., ... & Jiang, Y. (2020). Development and validation of a novel predictive scoring model for microvascular invasion in patients with hepatocellular carcinoma. European Journal of Radiology, 122, 108766.
5. Yang, L., Gu, D., Wei, J., Yang, C., Rao, S., Wang, W., ... & Zhang, B. (2019). A radiomics nomogram for preoperative prediction of microvascular invasion in hepatocellular carcinoma. Liver Cancer, 8(5), 373-386.
6. Feng, S. T., Jia, Y., Liao, B., Huang, B., Zhou, Q., Li, X., ... & Lu, X. (2019). Preoperative prediction of microvascular invasion in hepatocellular cancer: a radiomics model using Gd-EOB-DTPA-enhanced MRI. European Radiology, 29(9), 4648-4659.
7. Zhu, Y. J., Feng, B., Wang, S., Wang, L. M., Wu, J. F., Ma, X., ... & Chen, Z. Q. (2019). Model-based three-dimensional texture analysis of contrast-enhanced CT as a potential marker for preoperative prediction of microvascular invasion in hepatocellular carcinoma. European Radiology, 29(9), 4499-4511.
8. Wang, W. T., Yang, L., Yang, Z. X., Hu, X. X., Ding, Y., Yan, X., ... & Wang, W. X. (2018). Assessment of microvascular invasion of hepatocellular carcinoma with diffusion kurtosis imaging. Radiology, 286(2), 571-580.
9. Zhang, R., Xu, L., Wen, X., Zhang, J., Yang, P., Zhang, L., ... & Xiao, X. (2019). A nomogram based on bi-regional radiomics features from multimodal magnetic resonance imaging for preoperative prediction of microvascular invasion in hepatocellular carcinoma. Quantitative Imaging in Medicine and Surgery, 9(9), 1503-1515.
10. Ahn, S. J., Kim, J. H., Park, S. J., Kim, S. T., Han, J. K. (2019). Prediction of microvascular invasion of hepatocellular carcinoma using gadoxetic acid-enhanced MR and 18F-FDG PET/CT. Abdominal Radiology, 44(1), 129-136.
11. Ryu, T., Takami, Y., Wada, Y., Tateishi, M., Matsushima, H., Yoshitomi, M., & Aishima, S. (2019). A clinical scoring system for predicting microvascular invasion in patients with hepatocellular carcinoma within the Milan criteria. Journal of Gastrointestinal Surgery, 23(4), 779-787.
12. Ma, X., Wei, J., Gu, D., Zhu, Y., Feng, B., Liang, M., ... & Zhang, Z. (2019). Preoperative radiomics nomogram for microvascular invasion prediction in hepatocellular carcinoma using contrast-enhanced CT. European Radiology, 29(7), 3595-3605.
13. Zhou, Y., He, L., Huang, Y., Chen, S., Wu, P., Ye, W., ... & Lu, L. (2017). CT-based radiomics signature: a potential biomarker for preoperative prediction of early recurrence in hepatocellular carcinoma. Abdominal Radiology, 42(6), 1695-1704.
14. Peng, J., Zhang, J., Zhang, Q., Xu, Y., Zhou, J., & Liu, L. (2018). A radiomics nomogram for preoperative prediction of microvascular invasion risk in hepatitis B virus-related hepatocellular carcinoma. Diagnostic and Interventional Radiology, 24(3), 121-127.
15. Chen, J., Zhou, J., Kuang, S., Zhang, Y., Xie, S., He, B., ... & Zheng, J. (2020). Predicting microvascular invasion of hepatocellular carcinoma based on contrast-enhanced ultrasound and large-scale gene expression profiles. Frontiers in Oncology, 10, 565489.
16. Kim, S., Shin, J., Kim, D. Y., Choi, G. H., Kim, M. J., & Choi, J. Y. (2019). Radiomics on gadoxetic acid-enhanced magnetic resonance imaging for prediction of postoperative early and late recurrence of single hepatocellular carcinoma. Clinical Cancer Research, 25(13), 3847-3855.
17. Wei, Y., Huang, Z., Tang, H., Deng, L., Yuan, Y., Li, J., ... & Wu, F. (2019). IVIM-DWI and DCE-MRI in assessment of hepatocellular carcinoma invasion: a comparative study using histopathology as the reference standard. European Journal of Radiology, 117, 149-156.
18. Yao, Z., Dong, Y., Wu, G., Zhang, Q., Yang, D., Yu, J. H., & Wang, W. P. (2019). Preoperative diagnosis and prediction of hepatocellular carcinoma: Radiomics analysis based on multi-modal ultrasound images. BMC Cancer, 19(1), 1089.
19. Cao, L., Chen, J., Duan, T., Wang, M., Jiang, H., Wei, Y., ... & Zhou, J. (2020). Preoperative prediction of microvascular invasion of hepatocellular carcinoma using quantitative parameters based on contrast-enhanced computed tomography. Journal of Cancer Research and Clinical Oncology, 146(4), 971-980.
20. Xue, L. Y., Jiang, Z. Y., Fu, T. T., Wang, F., Hu, Y., Peng, W. J., ... & Shen, Y. Z. (2020). Radiomics of multiparametric MRI for preoperative prediction of microvascular invasion in hepatocellular carcinoma: a multicenter study. Radiology, 294(3), 695-705.
21. Guo, D., Gu, D., Wang, H., Wei, J., Yang, C., Zheng, X., ... & Zhang, B. (2020). Radiomics analysis enables recurrence prediction for hepatocellular carcinoma after liver transplantation. European Journal of Radiology, 126, 108966.
22. Xu, M., Fang, M., Zou, J., Yang, S., Yu, D., Zhong, L., ... & Wang, L. (2019). Using biparametric MRI radiomics signature to differentiate hepatocellular carcinoma from hepatic haemangioma. Liver International, 39(11), 2117-2126.
23. Ji, G. W., Zhu, F. P., Xu, Q., Wang, K., Wu, M. Y., Tang, W. W., ... & Zhang, Y. D. (2019). Machine-learning analysis of contrast-enhanced CT radiomics predicts recurrence of hepatocellular carcinoma after resection: A multi-institutional study. EBioMedicine, 50, 156-165.
24. Chong, H. H., Yang, L., Sheng, R. F., Yu, Y. W., Wu, D. J., Rao, S. X., ... & Hu, H. J. (2019). Multi-scale and multi-parametric radiomics of gadoxetate disodium-enhanced MRI predicts microvascular invasion and outcome in patients with solitary hepatocellular carcinoma ≤ 5 cm. European Radiology, 29(7), 4037-4044.
25. Li, Y., Yan, C., Weng, S., Shi, Z., Sun, H., Chen, J., ... & Xue, H. (2020). Radiomics analysis of multiphasic contrast-enhanced CT for the prediction of lymph node metastasis in patients with hepatocellular carcinoma. Abdominal Radiology, 45(9), 2699-2708.
26. Jiang, Y. Q., Cao, S. E., Cao, S., Chen, J. N., Wang, G. Y., Shi, W. D., ... & Wang, B. (2020). Preoperative identification of microvascular invasion in hepatocellular carcinoma by XGBoost and deep learning. Journal of Cancer Research and Clinical Oncology, 146(3), 817-827.
27. Song, D., Wang, Y., Wang, W., Wang, Y., Cai, J., Zhu, K., ... & Zhang, Y. (2020). Using deep learning to predict microvascular invasion in hepatocellular carcinoma based on dynamic contrast-enhanced MRI combined with clinical parameters. Journal of Cancer Research and Clinical Oncology, 146(12), 3155-3162.
28. Wu, M., Tan, H., Gao, F., Hai, J., Ning, P., Chen, J., ... & Jiang, Y. (2019). Predicting the grade of hepatocellular carcinoma based on non-contrast-enhanced MRI radiomics signature. European Radiology, 29(6), 2802-2811.
29. Zhang, X., Ruan, S., Xiao, W., Shao, J., Tian, W., Liu, W., ... & Zhang, G. (2020). Contrast-enhanced CT radiomics for preoperative evaluation of microvascular invasion in hepatocellular carcinoma: A two-center study. Clinical and Translational Medicine, 10(2), e111.
30. Lin, S., Zheng, Y., Qin, Z., Xu, J., Hu, Z., Fang, Z., ... & Wu, Z. (2020). Radiomics analysis based on gadoxetic acid-enhanced MRI for prediction of microvascular invasion in hepatocellular carcinoma. Abdominal Radiology, 45(11), 3703-3713.
31. Feng, S. T., Jia, Y., Liao, B., Huang, B., Zhou, Q., Li, X., ... & Lu, X. (2019). Preoperative prediction of microvascular invasion in hepatocellular cancer: a radiomics model using Gd-EOB-DTPA-enhanced MRI. European Radiology, 29(9), 4648-4659.
32. Qiao, M., Li, Y., Bai, R., Chen, T., Du, J., Lu, J., ... & Lu, J. (2020). Predictive radiomics models for microvascular invasion in hepatocellular carcinoma. Clinical and Translational Medicine, 10(8), e269.
33. Chou, C. T., Chen, R. C., Lin, W. C., Ko, C. J., Chen, C. B., & Chen, Y. L. (2019). Prediction of microvascular invasion of hepatocellular carcinoma: preoperative CT and histopathologic correlation. American Journal of Roentgenology, 213(2), W44-W53.
34. Yang, C., Wang, Y., He, S., Xie, S., Chen, Y., Zhang, S., ... & Li, X. (2020). Preoperative prediction of microvascular invasion in hepatocellular carcinoma using radiomics models based on gadoxetic acid-enhanced MR images. European Radiology, 30(11), 6134-6145.
35. Xia, W., Ke, Q., Wang, Y., Wang, W., Zhang, M., Shen, Y., ... & Zheng, S. (2020). Intratumoral and peritumoral radiomics for the preoperative prediction of pathological features in hepatocellular carcinoma. Journal of Surgical Research, 256, 543-552.
36. Ke, S., Zhang, X. Y., Cai, H. T., Xie, Y. J., Chang, H. T., Wang, X. L., ... & Chen, X. L. (2019). Preoperative prediction of microvascular invasion in hepatocellular carcinoma using machine learning: A multi-institutional retrospective study. European Journal of Radiology, 120, 108699.
37. Liu, Z., Zhang, X., Xiao, Y., Zhao, G., Zhang, Y., Li, J., ... & Sun, Y. (2020). Deep learning radiomics model based on contrast-enhanced CT images for predicting microvascular invasion in hepatocellular carcinoma. European Radiology, 30(12), 6698-6709.
38. Choi, S. H., Lee, S. S., Park, S. H., Kim, K. M., Yu, E., Park, Y., ... & Lee, M. G. (2019). LI-RADS classification and prognosis of primary liver cancers at gadoxetic acid-enhanced MRI. Radiology, 290(2), 388-397.
39. Duan, T., Jiang, H., Cao, L., Wei, Y., Wang, M., Xu, C., ... & Chen, J. (2020). Predicting microvascular invasion of hepatocellular carcinoma: a multi-parametric analysis of radiomics features on MRI. European Journal of Radiology, 133, 109360.
40. Wang, X., Shen, S., Shi, Y., Mei, J., Sun, G., Chen, W., ... & Wang, W. (2019). Investigating factors associated with hepatocellular carcinoma differentiation and portal vein tumor thrombus via 11C-acetate PET/CT. Journal of Nuclear Medicine, 60(10), 1428-1434.
41. Tan, Y., Zhang, S. T., Wei, J. W., Yang, C., Xiong, J. F., Pan, Q., ... & Zhang, B. (2020). A radiomics nomogram may improve the prediction of IDH genotype for astrocytoma before surgery. European Radiology, 30(4), 1957-1967.
42. Zhang, L., Hu, J., Du, J., Xu, J., Jiang, X., Tian, H., ... & Zhang, X. (2020). Comparison of DWI, IVIM, and texture
Copyright (c) 2025 Shuangshuang Lu
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright on all articles published in this journal is retained by the author(s), while the author(s) grant the publisher as the original publisher to publish the article.
Articles published in this journal are licensed under a Creative Commons Attribution 4.0 International, which means they can be shared, adapted and distributed provided that the original published version is cited.
Submit a Paper
