Share：
Share this content in WeChat
X
[Chinese] [PDF] 71 1
• Review •
Progress of MRI-based radiomics in predicting aggressive phenotypes and evaluating individualized treatment decisions for hepatocellular carcinoma
LIU Xing  CAO Xinshan 

DOI:10.12015/issn.1674-8034.2026.07.025.


[Abstract] Hepatocellular carcinoma (HCC) is characterized by insidious onset and high biological heterogeneity. Precise prediction of aggressive tumor phenotypes and the formulation of individualized treatment strategies are essential. MRI, with its advantages of multi-parametric imaging, high soft-tissue contrast, and lack of ionizing radiation, combined with radiomics technology for high-throughput quantitative feature extraction, enables the non-invasive disclosure of underlying histopathological and physiological information. This article systematically reviews the latest research progress of MRI-based radiomics in predicting aggressive phenotypes and evaluating individualized treatment decisions for HCC. In particular, the application value of MRI-based radiomics in quantifying intratumoral heterogeneity, predicting aggressive phenotypes such as vessels encapsulating tumor clusters (VETC) and microvascular invasion (MVI), and identifying histopathological grading is discussed. Furthermore, the clinical significance of this technology in evaluating the prognosis of surgical resection and liver transplantation, as well as the efficacy of locoregional and systemic therapies, is summarized. Although MRI-based radiomics has demonstrated significant potential in predicting aggressive phenotypes and evaluating individualized treatment decisions for HCC, limitations such as retrospective single-center designs, limited sample sizes, lack of standardized feature extraction protocols, and restricted clinical interpretability of deep learning models remain. Future research should focus on multi-center prospective studies, deep integration of multi-modal data, and enhancement of algorithmic interpretability to promote the substantial translation of MRI-based radiomics into robust clinical decision support systems.
[Keywords] hepatocellular carcinoma；magnetic resonance imaging；radiomics；aggressive phenotype；microvascular invasion；vessels that encapsulate tumor clusters；efficacy evaluation；prognostic prediction；deep learning；machine learning

LIU Xing   CAO Xinshan*  

Department of Radiology, Affiliated Hospital of Binzhou Medical College, Binzhou 256603, China

Corresponding author: CAO X S, E-mail: byfycxs@126.com

Conflicts of interest   None.

Received  2026-04-04
Accepted  2026-06-03
DOI: 10.12015/issn.1674-8034.2026.07.025
DOI:10.12015/issn.1674-8034.2026.07.025.

[1]
SUNG H, FERLAY J, SIEGEL R L, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2021, 71(3): 209-249. DOI: 10.3322/caac.21660.
[2]
QI J L, LI M L, WANG L J, et al. National and subnational trends in cancer burden in China, 2005—2020: an analysis of national mortality surveillance data[J/OL]. Lancet Public Health, 2023, 8(12): e943-e955 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/38000889/. DOI: 10.1016/S2468-2667(23)00211-6.
[3]
RUMGAY H, ARNOLD M, FERLAY J, et al. Global burden of primary liver cancer in 2020 and predictions to 2040[J]. J Hepatol, 2022, 77(6): 1598-1606. DOI: 10.1016/j.jhep.2022.08.021.
[4]
SAFRI F, NGUYEN R, ZEREHPOOSHNESFCHI S, et al. Heterogeneity of hepatocellular carcinoma: from mechanisms to clinical implications[J]. Cancer Gene Ther, 2024, 31(8): 1105-1112. DOI: 10.1038/s41417-024-00764-w.
[5]
XIE Y Y, WANG F, WEI J W, et al. Noninvasive prognostic classification of ITH in HCC with multi-omics insights and therapeutic implications[J/OL]. Sci Adv, 2025, 11(18): eads8323 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/40315307/. DOI: 10.1126/sciadv.ads8323.
[6]
XU Y S, LIU H F, XI D L, et al. Whole-lesion histogram analysis metrics of the apparent diffusion coefficient: a correlation study with histological grade of hepatocellular carcinoma[J]. Abdom Radiol, 2019, 44(9): 3089-3098. DOI: 10.1007/s00261-019-02109-w.
[7]
SHI G F, HAN X, WANG Q, et al. Evaluation of multiple prognostic factors of hepatocellular carcinoma with intra-voxel incoherent motions imaging by extracting the histogram metrics[J]. Cancer Manag Res, 2020, 12: 6019-6031. DOI: 10.2147/CMAR.S262973.
[8]
YANG Y, ZHANG S, CUI C, et al. Multiphase MRI-based radiomics for predicting histological grade of hepatocellular carcinoma[J/OL]. Magnetic Resonance Imaging, 2024: jmri.29289 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/38344854/. DOI: 10.1002/jmri.29289.
[9]
MAO Y F, WANG J C, ZHU Y, et al. Gd-EOB-DTPA-enhanced MRI radiomic features for predicting histological grade of hepatocellular carcinoma[J]. Hepatobiliary Surg Nutr, 2022, 11(1): 13-24. DOI: 10.21037/hbsn-19-870.
[10]
LU Y J, GU W H, XU D B, et al. CEMRI-based intratumoral and peritumoral radiomics for predicting the degree of pathological differentiation of hepatocellular carcinoma[J]. Chin J Magn Reson Imaging, 2025, 16(3): 51-57. DOI: 10.12015/issn.1674-8034.2025.03.008.
[11]
HAN X B, ZHANG C Y, PENG W S, et al. A study on the prediction of preoperative risk stratification of hepatocellular carcinoma based on multi-phase MRI radiomics combined with different machine learning models[J]. Chin J Magn Reson Imaging, 2025, 16(8): 80-87. DOI: 10.12015/issn.1674-8034.2025.08.012.
[12]
FANG J H, ZHOU H C, ZHANG C, et al. A novel vascular pattern promotes metastasis of hepatocellular carcinoma in an epithelial-mesenchymal transition-independent manner[J]. Hepatology, 2015, 62(2): 452-465. DOI: 10.1002/hep.27760.
[13]
WANG M M, CAO L, WANG Y Z, et al. The prognostic value of vessels encapsulating tumor clusters (VETC) in patients with hepatocellular carcinoma: a systematic review and meta-analysis[J]. Clin Transl Oncol, 2024, 26(8): 2037-2046. DOI: 10.1007/s12094-024-03427-2.
[14]
YU Y X, FAN Y F, WANG X M, et al. Gd-EOB-DTPA-enhanced MRI radiomics to predict vessels encapsulating tumor clusters (VETC) and patient prognosis in hepatocellular carcinoma[J]. Eur Radiol, 2022, 32(2): 959-970. DOI: 10.1007/s00330-021-08250-9.
[15]
DONG X, YANG J W, ZHANG B H, et al. Deep learning radiomics model of dynamic contrast-enhanced MRI for evaluating vessels encapsulating tumor clusters and prognosis in hepatocellular carcinoma[J]. Magnetic Resonance Imaging, 2024, 59(1): 108-119. DOI: 10.1002/jmri.28745.
[16]
GOUW A S H, BALABAUD C, KUSANO H, et al. Markers for microvascular invasion in hepatocellular carcinoma: Where do we stand [J]. Liver Transplant, 2011, 17(Supplement 2): S72-S80. DOI: 10.1002/lt.22368.
[17]
ZHOU H Y, CHENG J M, CHEN T W, et al. A systematic review and meta-analysis of MRI radiomics for PredictingMicrovascular invasion in patients with hepatocellular carcinoma[J/OL]. Curr Med Imaging Former Curr Med Imaging Rev, 2024, 20: e15734056256824[2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/38389371/. DOI: 10.2174/0115734056256824231204073534.
[18]
LIANG G, YU W, LIU S Q, et al. The diagnostic performance of radiomics-based MRI in predicting microvascular invasion in hepatocellular carcinoma: A meta-analysis[J/OL]. Front Oncol, 2023, 12: 960944 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/36798691/. DOI: 10.3389/fonc.2022.960944.
[19]
PENG Y, WU S X, XIONG B, et al. Multiphase MRI radiomics model for predicting microvascular invasion in HCC: Development and clinical validation[J/OL]. iLIVER, 2025, 4(2): 100165 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/40636460/. DOI: 10.1016/j.iliver.2025.100165.
[20]
ZHANG R, WANG Y, LI Z, et al. Dynamic radiomics based on contrast-enhanced MRI for predicting microvascular invasion in hepatocellular carcinoma[J/OL]. BMC Med Imaging, 2024, 24(1): 80 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/38584254/. DOI: 10.1186/s12880-024-01258-9.
[21]
XU X S, LUO Y, LIANG S Q, et al. Predicting microvascular invasion in hepatocellular carcinoma using Delta radiomics model based on Gd-EOB-DTPA enhanced MRI[J]. Chin J Magn Reson Imaging, 2025, 16(11): 123-128. DOI: 10.12015/issn.1674-8034.2025.11.018.
[22]
WANG S, ZHAO Y, LI J Y, et al. Self-supervised multi-modal feature fusion for predicting early recurrence of hepatocellular carcinoma[J/OL]. Comput Med Imaging Graph, 2024, 118: 102457 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/39571452/. DOI: 10.1016/j.compmedimag.2024.102457.
[23]
YOU H Y, WANG J F, MA R X, et al. Clinical interpretability of deep learning for predicting microvascular invasion in hepatocellular carcinoma by using attention mechanism[J/OL]. Bioengineering (Basel), 2023, 10(8): 948 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/37627833/. DOI: 10.3390/bioengineering10080948.
[24]
REIG M, FORNER A, RIMOLA J, et al. BCLC strategy for prognosis prediction and treatment recommendation: The 2022 update[J]. J Hepatol, 2022, 76(3): 681-693. DOI: 10.1016/j.jhep.2021.11.018.
[25]
ZENG H Q, MA Z C, TAO Y X, et al. Predicting early recurrence in hepatocellular carcinoma after hepatectomy using GD-EOB-DTPA enhanced MRI-based model[J/OL]. Eur J Radiol, 2025, 188: 112130 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/40305886/. DOI: 10.1016/j.ejrad.2025.112130.
[26]
YAN M, ZHANG X, ZHANG B, et al. Deep learning nomogram based on Gd-EOB-DTPA MRI for predicting early recurrence in hepatocellular carcinoma after hepatectomy[J]. Eur Radiol, 2023, 33(7): 4949-4961. DOI: 10.1007/s00330-023-09419-0.
[27]
LIAO Y B, HAN S, LI J, et al. Habitat imaging and peritumoral-containing radiomics models based on dynamic contrast-enhanced MRI for predicting early recurrence after hepatectomy in hepatocellular carcinoma[J]. J Clin Radiol, 2026, 45(4): 614-622. DOI: 10.3969/j.issn.1001-9324.2026.04.007.
[28]
CAO X S, YANG H R, LUO X, et al. A cox nomogram for assessing recurrence free survival in hepatocellular carcinoma following surgical resection using dynamic contrast-enhanced MRI radiomics[J]. J Magn Reson Imaging, 2023, 58(6): 1930-1941. DOI: 10.1002/jmri.28725.
[29]
ZHANG L, HU J M, HOU J Y, et al. Radiomics-based model using gadoxetic acid disodium-enhanced MR images: associations with recurrence-free survival of patients with hepatocellular carcinoma treated by surgical resection[J]. Abdom Radiol (NY), 2021, 46(8): 3845-3854. DOI: 10.1007/s00261-021-03034-7.
[30]
FENG L J, HUANG W Y, PAN X Y, et al. Predicting overall survival in hepatocellular carcinoma patients via a combined MRI radiomics and pathomics signature[J/OL]. Transl Oncol, 2025, 51: 102174 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/39489092/. DOI: 10.1016/j.tranon.2024.102174.
[31]
KUANG F Y, GAO Y, ZHOU Q Y, et al. MRI radiomics combined with clinicopathological factors for predicting 3-year overall survival of hepatocellular carcinoma after hepatectomy[J]. J Hepatocell Carcinoma, 2024, 11: 1445-1457. DOI: 10.2147/JHC.S464916.
[32]
GUO X Y, SONG J J, ZHU L Y, et al. Multiparametric MRI-based radiomics and clinical nomogram predicts the recurrence of hepatocellular carcinoma after postoperative adjuvant transarterial chemoembolization[J/OL]. BMC Cancer, 2025, 25(1): 683 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/40229712/. DOI: 10.1186/s12885-025-14079-y.
[33]
ISEKE S, ZEEVI T, KUCUKKAYA A S, et al. Machine learning models for prediction of posttreatment recurrence in early-stage hepatocellular carcinoma using pretreatment clinical and MRI features: A proof-of-concept study[J]. Am J Roentgenol, 2023, 220(2): 245-255. DOI: 10.2214/ajr.22.28077.
[34]
PATEL K R, MENON H, PATEL R R, et al. Locoregional therapies for hepatocellular carcinoma: A systematic review and meta-analysis[J/OL]. JAMA Netw Open, 2024, 7(11): e2447995[2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/39602117/. DOI: 10.1001/jamanetworkopen.2024.47995.
[35]
WANG Y X, LIU Z H, XU H, et al. MRI-based radiomics model and nomogram for predicting the outcome of locoregional treatment in patients with hepatocellular carcinoma[J/OL]. BMC Med Imaging, 2023, 23(1): 67 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/37254089/. DOI: 10.1186/s12880-023-01030-5.
[36]
HUANG W R, PAN Y F, WANG H F, et al. Delta-radiomics analysis based on multi-phase contrast-enhanced MRI to predict early recurrence in hepatocellular carcinoma after percutaneous thermal ablation[J]. Acad Radiol, 2024, 31(12): 4934-4945. DOI: 10.1016/j.acra.2024.06.002.
[37]
WANG Y D, ZHANG Y, XIAO J C, et al. Multicenter integration of MR radiomics, deep learning, and clinical indicators for predicting hepatocellular carcinoma recurrence after thermal ablation[J]. J Hepatocell Carcinoma, 2024, 11: 1861-1874. DOI: 10.2147/JHC.S482760.
[38]
MANJUNATHA N, GANDURI V, RAJASEKARAN K, et al. Transarterial chemoembolization and unresectable hepatocellular carcinoma: A narrative review[J/OL]. Cureus, 2022, 14(8): e28439[2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/36176866/. DOI: 10.7759/cureus.28439.
[39]
ZHAO Y, ZHANG J, WANG N, et al. Intratumoral and peritumoral radiomics based on contrast-enhanced MRI for preoperatively predicting treatment response of transarterial chemoembolization in hepatocellular carcinoma[J/OL]. BMC Cancer, 2023, 23(1): 1026 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/37875815/. DOI: 10.1186/s12885-023-11491-0.
[40]
WANG W L, ZHANG Q, CUI Y, et al. TRACE model: predicting treatment response to transarterial chemoembolization in unresectable hepatocellular carcinoma[J]. J Hepatocell Carcinoma, 2025, 12: 193-203. DOI: 10.2147/jhc.s490226.
[41]
ZHAO Y, HUANG F, LIU S Y, et al. Prediction of therapeutic response of unresectable hepatocellular carcinoma to hepatic arterial infusion chemotherapy based on pretherapeutic MRI radiomics and Albumin-Bilirubin score[J]. J Cancer Res Clin Oncol, 2023, 149(8): 5181-5192. DOI: 10.1007/s00432-022-04467-3.
[42]
İNCE O, ÖNDER H, GENÇTÜRK M, et al. Prediction of response of hepatocellular carcinoma to radioembolization: machine learning using preprocedural clinical factors and MR imaging radiomics[J]. J Vasc Interv Radiol, 2023, 34(2): 235-243. DOI: 10.1016/j.jvir.2022.11.004.
[43]
AUJAY G, ETCHEGARAY C, BLANC J F, et al. Comparison of MRI-based response criteria and radiomics for the prediction of early response to transarterial radioembolization in patients with hepatocellular carcinoma[J]. Diagn Interv Imaging, 2022, 103(7/8): 360-366. DOI: 10.1016/j.diii.2022.01.009.
[44]
DUDZINSKI S O, NEWMAN N B, MCINTYRE J, et al. Emerging evidence-based role for external-beam radiation therapy in hepatocellular carcinoma[J]. Lancet Gastroenterol Hepatol, 2025, 10(4): 387-398. DOI: 10.1016/S2468-1253(24)00267-X.
[45]
HUANG Y M, WANG T E, CHEN M J, et al. Radiomics-based nomogram as predictive model for prognosis of hepatocellular carcinoma with portal vein tumor thrombosis receiving radiotherapy[J/OL]. Front Oncol, 2022, 12: 906498 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/36203419/. DOI: 10.3389/fonc.2022.906498.
[46]
CHEN J L, CHEN J, YE Y M, et al. Pretreatment multi-sequence contrast-enhanced MRI to predict response to immunotherapy in unresectable hepatocellular carcinoma using transformer: a multicenter study[J]. J Cancer, 2025, 16(8): 2663-2672. DOI: 10.7150/jca.111026.
[47]
HUANG K, MA H Y, LIU H K, et al. MRI-based radiomics signatures for predicting the efficacy of targeted therapy with lenvatinib in hepatocellular carcinoma: a retrospective cohort study[J/OL]. J Cancer Res Clin Oncol, 2025, 151(9): 251 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/40931250/. DOI: 10.1007/s00432-025-06306-7.
[48]
KANG W D, TANG P Y, LUO Y G, et al. Multiparametric MRI-based machine learning radiomics for predicting treatment response to transarterial chemoembolization combined with targeted and immunotherapy in unresectable hepatocellular carcinoma: A multicenter study[J]. Acad Radiol, 2025, 32(4): 2013-2026. DOI: 10.1016/j.acra.2024.10.038.
[49]
XU X N, JIANG X, JIANG H R, et al. Prediction of prognosis of immune checkpoint inhibitors combined with anti-angiogenic agents for unresectable hepatocellular carcinoma by machine learning-based radiomics[J/OL]. BMC Cancer, 2025, 25(1): 888 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/40389888/. DOI: 10.1186/s12885-025-14247-0.
[50]
ZHANG R, PENG W, WANG Y, et al. MRI radiomics model for predicting tumor immune microenvironment types and efficacy of anti-PD-1/PD-L1 therapy in hepatocellular carcinoma[J/OL]. BMC Med Imaging, 2025, 25(1): 211 [2026-04-03]. https://pubmed.ncbi.nlm.nih.gov/40597775/. DOI: 10.1186/s12880-025-01751-9.

PREV The application progress of radiomics in intrahepatic cholangiocarcinoma
NEXT Research progress on radiomics-based precise subtyping and risk stratification of intrahepatic cholangiocarcinoma
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn