Share：
Share this content in WeChat
X
[Chinese][PDF]271
• Review •
Research progress of radiomics in the prognosis of hepatocellular carcinoma
ZHENG Xiaojun  HUANG Lihong  NONG Haiyang  HUANG Deyou 

Cite this article as: ZHENG X J, HUANG L H, NONG H Y, et al. Research progress of radiomics in the prognosis of hepatocellular carcinoma[J]. Chin J Magn Reson Imaging, 2025, 16(6): 189-194. DOI:10.12015/issn.1674-8034.2025.06.029.


[Abstract] Hepatocellular carcinoma (HCC) ranks as the second leading cause of cancer-related mortality in China, underscoring the urgent need for precise prognostic tools. While radiomics has demonstrated considerable potential, existing reviews predominantly focus on single-modality approaches or technical methodologies. This article systematically reviews advancements in multimodal radiomics: encompassing ultrasound, computed tomography, magnetic resonance imaging, and positron emission tomography for HCC prognosis, while critically analyzing key bottlenecks such as standardization gaps and limited biological interpretability. We propose that future efforts should prioritize: multimodal fusion algorithms, explainable artificial intelligence models, and prospective validation studies, aiming to translate research findings into clinical practice and improve patient outcomes.
[Keywords] hepatocellular carcinoma；radiomics；ultrasound；computed tomography；magnetic resonance imaging；positron emission tomography；artificial intelligence；prognosis

ZHENG Xiaojun1, 2   HUANG Lihong1, 2   NONG Haiyang2   HUANG Deyou2*  

1 Graduate School, Youjiang Medical University for Nationalities, Baise 533000, China

2 Department of Medical Imaging, Affiliated Hospital of Youjiang Medical for Nationalities, Baise 533000, China

Corresponding author: HUANG D Y, E-mail: FZXYH2012@126.com

Conflicts of interest   None.

Received  2024-12-31
Accepted  2025-05-10
DOI: 10.12015/issn.1674-8034.2025.06.029
Cite this article as: ZHENG X J, HUANG L H, NONG H Y, et al. Research progress of radiomics in the prognosis of hepatocellular carcinoma[J]. Chin J Magn Reson Imaging, 2025, 16(6): 189-194. DOI:10.12015/issn.1674-8034.2025.06.029.

[1]
BRAY F, LAVERSANNE M, SUNG H, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2024, 74(3): 229-263. DOI: 10.3322/caac.21834.
[2]
Department of Medical Administration of the National Health Commission of the People's Republic of China. Guideline for diagnosis and treatment of primary liver cancer (2024 edition)[J]. Chin J Magn Reson Imaging, 2024, 15(6): 1-18. DOI: 10.12015/issn.1674-8034.2024.06.001.
[3]
LAMBIN P, RIOS-VELAZQUEZ E, LEIJENAAR R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446. DOI: 10.1016/j.ejca.2011.11.036.
[4]
GUTIERREZ-CHAKRABORTY E, CHAKRABORTY D, DAS D, et al. Discovering novel prognostic biomarkers of hepatocellular carcinoma using eXplainable Artificial Intelligence[J/OL]. Expert Syst Appl, 2024, 252(Pt B): 124239 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10705238/. DOI: 10.1016/j.eswa.2024.124239.
[5]
MOKRANE F Z, LU L, VAVASSEUR A, et al. Radiomics machine-learning signature for diagnosis of hepatocellular carcinoma in cirrhotic patients with indeterminate liver nodules[J]. Eur Radiol, 2020, 30(1): 558-570. DOI: 10.1007/s00330-019-06347-w.
[6]
JIN J, JIANG Y, ZHAO Y L, et al. Radiomics-based machine learning to predict the recurrence of hepatocellular carcinoma: a systematic review and meta-analysis[J]. Acad Radiol, 2024, 31(2): 467-479. DOI: 10.1016/j.acra.2023.09.008.
[7]
CHEN K, SUI C X, WANG Z Y, et al. Habitat radiomics based on CT images to predict survival and immune status in hepatocellular carcinoma, a multi-cohort validation study[J/OL]. Transl Oncol, 2025, 52: 102260 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11754828/. DOI: 10.1016/j.tranon.2024.102260.
[8]
KOCAK B, KUS E A, KILICKESMEZ O. How to read and review papers on machine learning and artificial intelligence in radiology: a survival guide to key methodological concepts[J]. Eur Radiol, 2021, 31(4): 1819-1830. DOI: 10.1007/s00330-020-07324-4.
[9]
LIN P, QIN Q, GAN X Y, et al. Integrating single-cell and bulk RNA sequencing data to characterize the heterogeneity of glycan-lipid metabolism polarization in hepatocellular carcinoma[J/OL]. J Transl Med, 2025, 23(1): 358 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11929990/. DOI: 10.1186/s12967-025-06347-z.
[10]
BO Z Y, SONG J T, HE Q K, et al. Application of artificial intelligence radiomics in the diagnosis, treatment, and prognosis of hepatocellular carcinoma[J/OL]. Comput Biol Med, 2024, 173: 108337 [2025-04-23]. https://pubmed.ncbi.nlm.nih.gov/38547656/. DOI: 10.1016/j.compbiomed.2024.108337.
[11]
GUO T T, LUO H C, WANG H Z, et al. Predictive value of radiomics based on laparoscopic ultrasound imaging in microvascular invasion of hepatocellular carcinoma[J]. Chin J Ultrason, 2024, 33(9): 807-814. DOI: 10.3760/cma.j.cn131148-20240328-00186.
[12]
WANG Y, TIAN W, JIN Q, et al. Correlation and clinical value of HBO1 and Ki-67 expression in hepatocellular carcinoma[J]. Chin J Clin Exp Pathol, 2018, 34(6): 605-609. DOI: 10.13315/j.cnki.cjcep.2018.06.004.
[13]
ZUO D, DONG Y, WANG H Z, et al. Preoperative prediction of Ki-67 level in hepatocellular carcinoma based on radiomics signatures during Kupffer phase of Sonazoid contrast enhanced ultrasound[J]. Chin J Ultrason, 2023, 32(2): 123-128. DOI: 10.3760/cma.j.cn131148-20220616-00436.
[14]
ZHANG D, ZHANG X Y, LU W W, et al. Predicting Ki-67 expression in hepatocellular carcinoma: nomogram based on clinical factors and contrast-enhanced ultrasound radiomics signatures[J]. Abdom Radiol (NY), 2024, 49(5): 1419-1431. DOI: 10.1007/s00261-024-04191-1.
[15]
XU W X, ZHANG H Y, ZHANG R, et al. Deep learning model based on contrast-enhanced ultrasound for predicting vessels encapsulating tumor clusters in hepatocellular carcinoma[J]. Eur Radiol, 2025, 35(2): 989-1000. DOI: 10.1007/s00330-024-10985-0.
[16]
CAO K P, WANG X Y, XU C L, et al. Ultrasound-based radiomics analysis for assessing risk factors associated with early recurrence following surgical resection of hepatocellular carcinoma[J]. Ultrasound Med Biol, 2024, 50(12): 1964-1972. DOI: 10.1016/j.ultrasmedbio.2024.09.002.
[17]
HUANG Z, SHU Z, ZHU R H, et al. Deep learning-based radiomics based on contrast-enhanced ultrasound predicts early recurrence and survival outcome in hepatocellular carcinoma[J]. World J Gastrointest Oncol, 2022, 14(12): 2380-2392. DOI: 10.4251/wjgo.v14.i12.2380.
[18]
MENDIRATTA-LALA M, FETZER D, KAMAYA A, et al. The future role of abdominal US in hepatocellular carcinoma surveillance[J/OL]. Radiology, 2024, 311(2): e232624 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11140528/. DOI: 10.1148/radiol.232624.
[19]
HU Y W, ZHANG L L, QI Q H, et al. Machine learning-based ultrasomics for predicting response to tyrosine kinase inhibitor in combination with anti-PD-1 antibody immunotherapy in hepatocellular carcinoma: a two-center study[J/OL]. Front Oncol, 2024, 14: 1464735 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11602396/. DOI: 10.3389/fonc.2024.1464735.
[20]
HE J, DUAN P Y, LIU Y, et al. Unveiling the impact of hemodynamics on endothelial inflammation-mediated hepatocellular carcinoma metastasis using a biomimetic vascular flow model[J/OL]. Adv Healthc Mater, 2024, 13(18): e2304439 [2025-04-23]. https://pubmed.ncbi.nlm.nih.gov/38486060/. DOI: 10.1002/adhm.202304439.
[21]
CAI C Y, WANG L C, TAO L Y, et al. Imaging-based prediction of ki-67 expression in hepatocellular carcinoma: A retrospective study[J/OL]. Cancer Med, 2025, 14(4): e70562 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11834164/. DOI: 10.1002/cam4.70562.
[22]
ZHANG Z Y, ZHANG W L, HE C T, et al. Identification of macrotrabecular-massive hepatocellular carcinoma through Multiphasic CT-based representation learning method[J]. Med Phys, 2024, 51(12): 9017-9030. DOI: 10.1002/mp.17401.
[23]
WU X W, YOU J J, ZHANG S X, et al. Pretreatment CT-based machine learning radiomics model predicts response in unresectable hepatocellular carcinoma treated with lenvatinib plus PD-1 inhibitors and interventional therapy[J/OL]. J Immunother Cancer, 2024, 12(9): e010330 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11425937/. DOI: 10.1136/jitc-2024-010330.
[24]
CHEN M Y, CAO J S, HU J H, et al. Clinical-radiomic analysis for pretreatment prediction of objective response to first transarterial chemoembolization in hepatocellular carcinoma[J]. Liver Cancer, 2021, 10(1): 38-51. DOI: 10.1159/000512028.
[25]
LI M S, FAN Y H, YOU H Y, et al. Dual-energy CT deep learning radiomics to predict macrotrabecular-massive hepatocellular carcinoma[J/OL]. Radiology, 2023, 308(2): e230255 [2025-04-23]. https://pubmed.ncbi.nlm.nih.gov/37606573/. DOI: 10.1148/radiol.230255.
[26]
WANG F, CHENG M, DU B B, et al. Predicting microvascular invasion in small (≤ 5 cm) hepatocellular carcinomas using radiomics-based peritumoral analysis[J/OL]. Insights Imaging, 2024, 15(1): 90 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10965872/. DOI: 10.1186/s13244-024-01649-0.
[27]
ZHAO H F, FENG Z C, LI H L, et al. Influence of different region of interest sizes on CT-based radiomics model for microvascular invasion prediction in hepatocellular carcinoma[J]. J Cent South Univ Med Sci, 2022, 47(8): 1049-1057. DOI: 10.11817/j.issn.1672-7347.2022.220027.
[28]
ZHU X Q, DING G R. Establishment of CT radiomics model for predicting microvascular invasion, postoperative outcome and recurrence in patients with liver cancer[J]. Chin J CT MRI, 2024, 22(6): 107-110. DOI: 10.3969/j.issn.1672-5131.2024.06.034.
[29]
WANG D D, ZHANG L H, SUN Z Q, et al. A radiomics signature associated with underlying gene expression pattern for the prediction of prognosis and treatment response in hepatocellular carcinoma[J/OL]. Eur J Radiol, 2023, 167: 111086 [2025-04-23]. https://pubmed.ncbi.nlm.nih.gov/37708675/. DOI: 10.1016/j.ejrad.2023.111086.
[30]
GUO L X, HAO X, CHEN L, et al. Early warning of hepatocellular carcinoma in cirrhotic patients by three-phase CT-based deep learning radiomics model: a retrospective, multicentre, cohort study[J/OL]. EClinicalMedicine, 2024, 74: 102718 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11279308/. DOI: 10.1016/j.eclinm.2024.102718.
[31]
CHE F, XU Q, LI Q, et al. Radiomics signature: A potential biomarker for β-arrestin1 phosphorylation prediction in hepatocellular carcinoma[J]. World J Gastroenterol, 2022, 28(14): 1479-1493. DOI: 10.3748/wjg.v28.i14.1479.
[32]
LIN Z J, WANG W D, YAN Y C, et al. A deep learning-based clinical-radiomics model predicting the treatment response of immune checkpoint inhibitors (ICIs)-based conversion therapy in potentially convertible hepatocelluar carcinoma patients: a tumour marker prognostic study[J/OL]. Int J Surg, 2025 [2025-04-23]. https://pubmed.ncbi.nlm.nih.gov/40085751/. DOI: 10.1097/JS9.0000000000002322.
[33]
HAPAER G, CHE F, XU Q, et al. Radiomics-based biomarker for PD-1 status and prognosis analysis in patients with HCC[J/OL]. Front Immunol, 2025, 16: 1435668 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11813882/. DOI: 10.3389/fimmu.2025.1435668.
[34]
ZHANG S T, METAXAS D. On the challenges and perspectives of foundation models for medical image analysis[J/OL]. Med Image Anal, 2024, 91: 102996 [2025-04-23]. https://pubmed.ncbi.nlm.nih.gov/37857067/. DOI: 10.1016/j.media.2023.102996.
[35]
SHI P L, QIU J N, ABAXI S M D, et al. Generalist vision foundation models for medical imaging: a case study of segment anything model on zero-shot medical segmentation[J/OL]. Diagnostics (Basel), 2023, 13(11): 1947 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10252742/. DOI: 10.3390/diagnostics13111947.
[36]
LI Y X, JING B W, LI Z H, et al. Plug-and-play segment anything model improves nnUNet performance[J]. Med Phys, 2025, 52(2): 899-912. DOI: 10.1002/mp.17481.
[37]
JING M Y, CAO Y T, DENG J, et al. The value of minimum apparent diffusion coefficient in evaluating the invasiveness of hepatocellular carcinoma[J]. Chin J Magn Reson Imag, 2021, 12(5): 16-20. DOI: 10.12015/issn.1674-8034.2021.05.004.
[38]
ZONG X D, LI M K, LI J W, et al. Mean ADC values and arterial phase hyperintensity discriminate small (≤ 3 Cm) well-differentiated hepatocellular carcinoma from dysplastic nodule[J]. Abdom Radiol (NY), 2024, 49(4): 1132-1143. DOI: 10.1007/s00261-023-04171-x.
[39]
GUO Y X, CHEN J J, ZHANG Y F, et al. Differentiating Cytokeratin 19 expression of hepatocellular carcinoma by using multi-b-value diffusion-weighted MR imaging with mono-exponential, stretched exponential, intravoxel incoherent motion, diffusion kurtosis imaging and fractional order Calculus models[J/OL]. Eur J Radiol, 2022, 150: 110237 [2025-04-23]. https://pubmed.ncbi.nlm.nih.gov/35278979/. DOI: 10.1016/j.ejrad.2022.110237.
[40]
ZHOU J, YANG D F, TANG H. Magnetic resonance imaging radiomics based on artificial intelligence is helpful to evaluate the prognosis of single hepatocellular carcinoma[J/OL]. Heliyon, 2025, 11(1): e41735 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11761343/. DOI: 10.1016/j.heliyon.2025.e41735.
[41]
NAPEL S, MU W, JARDIM-PERASSI B V, et al. Quantitative imaging of cancer in the postgenomic era: Radio(geno)mics, deep learning, and habitats[J]. Cancer, 2018, 124(24): 4633-4649. DOI: 10.1002/cncr.31630.
[42]
LOSIC B, CRAIG A J, VILLACORTA-MARTIN C, et al. Intratumoral heterogeneity and clonal evolution in liver cancer[J/OL]. Nat Commun, 2020, 11(1): 291 [2025-04-23]. https://pubmed.ncbi.nlm.nih.gov/31941899/. DOI: 10.1038/s41467-019-14050-z.
[43]
XIAO Y Y, HUANG P, ZHANG Y F, et al. Component prediction in combined hepatocellular carcinoma-cholangiocarcinoma: habitat imaging and its biologic underpinnings[J]. Abdom Radiol (NY), 2024, 49(4): 1063-1073. DOI: 10.1007/s00261-023-04174-8.
[44]
LIU H F, WANG M, LU Y J, et al. CEMRI-based quantification of intratumoral heterogeneity for predicting aggressive characteristics of hepatocellular carcinoma using habitat analysis: comparison and combination of deep learning[J]. Acad Radiol, 2024, 31(6): 2346-2355. DOI: 10.1016/j.acra.2023.11.024.
[45]
MICHELOTTI F C. Editorial for "the association between tumor radiomic analysis and peritumor habitat-derived radiomic analysis on gadoxetate disodium-enhanced MRI with microvascular invasion in hepatocellular carcinoma"[J]. J Magn Reson Imaging, 2025, 61(3): 1440-1441. DOI: 10.1002/jmri.29551.
[46]
WEN G H, KONG W. Efficacy analysis of postoperative MVI risk model in hepatocellular carcinoma patients based on preoperative DCE-MRI features[J]. Med J West China, 2023, 35(9): 1331-1335. DOI: 10.3969/j.issn.1672-3511.2023.09.016.
[47]
WANG W J, HUANG J C, YANG X, et al. Value of enhanced MRI radiomics in preoperative prediction for Ki-67 expression in hepatocellular carcinoma[J]. Chin Imag J Integr Tradit West Med, 2024, 22(3): 245-249, 261. DOI: 10.3969/j.issn.1672-0512.2024.03.001.
[48]
YANG J W, DONG X, JIN S Z, et al. Radiomics model of dynamic contrast-enhanced MRI for evaluating vessels encapsulating tumor clusters and microvascular invasion in hepatocellular carcinoma[J]. Acad Radiol, 2025, 32(1): 146-156. DOI: 10.1016/j.acra.2024.07.007.
[49]
CHONG H H, YANG L, SHENG R F, et al. Multi-scale and multi-parametric radiomics of gadoxetate disodium-enhanced MRI predicts microvascular invasion and outcome in patients with solitary hepatocellular carcinoma≤5 cm[J]. Eur Radiol, 2021, 31(7): 4824-4838. DOI: 10.1007/s00330-020-07601-2.
[50]
AI Z, HAN Q J, HUANG Z W, et al. The value of multiparametric histogram features based on intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) for the differential diagnosis of liver lesions[J/OL]. Ann Transl Med, 2020, 8(18): 1128 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC7576072/. DOI: 10.21037/atm-20-5109.
[51]
MAYIDILI·N, WANG J, MAIHEMITIJIANG·D, et al. Predictive value of IVIM-DWI multi-parameter MRI in microvessel invasion of hepatocellular carcinoma[J]. Chin J Hepatic Surg Electron Ed, 2022, 11(1): 39-43. DOI: 10.3877/cma.j.issn.2095-3232.2022.01.009.
[52]
WEI Y C, YUN L, LIANG Y L, et al. Nomogram based on the neutrophil-to-lymphocyte ratio and MR diffusion quantitative parameters for predicting Ki67 expression in hepatocellular carcinoma from a prospective study[J/OL]. Sci Rep, 2024, 14(1): 31738 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11685758/. DOI: 10.1038/s41598-024-82333-7.
[53]
GUO D, LIU L P, JIN Y. Prediction early recurrence of hepatocellular carcinoma after hepatectomy using gadoxetic acid-enhanced MRI and IVIM[J/OL]. Eur J Radiol Open, 2025, 14: 100643 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11957592/. DOI: 10.1016/j.ejro.2025.100643.
[54]
GU Y, JIN K, GAO S, et al. A preoperative nomogram with MR elastography in identifying cytokeratin 19 status of hepatocellular carcinoma[J]. Br J Radiol, 2025, 98(1166): 210-219. DOI: 10.1093/bjr/tqae193.
[55]
ZHANG L N, CHEN J B, JIANG H, et al. MR elastography as a biomarker for prediction of early and late recurrence in HBV-related hepatocellular carcinoma patients before hepatectomy[J/OL]. Eur J Radiol, 2022, 152: 110340 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC9535659/. DOI: 10.1016/j.ejrad.2022.110340.
[56]
PARK S J, YOON J H, LEE D H, et al. Tumor stiffness measurements on MR elastography for single nodular hepatocellular carcinomas can predict tumor recurrence after hepatic resection[J]. J Magn Reson Imaging, 2021, 53(2): 587-596. DOI: 10.1002/jmri.27359.
[57]
GAO S S, ZHANG Y F, SUN W, et al. Assessment of an MR elastography-based nomogram as a potential imaging biomarker for predicting microvascular invasion of hepatocellular carcinoma[J]. J Magn Reson Imaging, 2023, 58(2): 392-402. DOI: 10.1002/jmri.28553.
[58]
SONG L N, WANG B, CAI J L, et al. Stratifying ICIs-responsive tumor microenvironment in HCC: from parsing out immune-hypoxic crosstalk to clinically applicable MRI-radiomics models[J]. Br J Cancer, 2024, 130(8): 1356-1364. DOI: 10.1038/s41416-023-02463-z.
[59]
FAN R Q, LONG X Q, CHEN X L, et al. The value of machine learning-based radiomics model characterized by PET imaging with 68Ga-FAPI in assessing microvascular invasion of hepatocellular carcinoma[J]. Acad Radiol, 2025, 32(4): 2233-2246. DOI: 10.1016/j.acra.2024.11.034.
[60]
SUI C X, SU Q, CHEN K, et al. 18F-FDG PET/CT-based habitat radiomics combining stacking ensemble learning for predicting prognosis in hepatocellular carcinoma: a multi-center study[J/OL]. BMC Cancer, 2024, 24(1): 1457 [2025-04-23]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11600565/. DOI: 10.1186/s12885-024-13206-5.
[61]
CHALIAN H, TÖRE H G, HOROWITZ J M, et al. Radiologic assessment of response to therapy: comparison of RECIST versions 1.1 and 1.0[J]. Radiographics, 2011, 31(7): 2093-2105. DOI: 10.1148/rg.317115050.
[62]
CHEN J B, KAYA N A, ZHANG Y, et al. A multimodal atlas of hepatocellular carcinoma reveals convergent evolutionary paths and 'bad apple' effect on clinical trajectory[J]. J Hepatol, 2024, 81(4): 667-678. DOI: 10.1016/j.jhep.2024.05.017.
[63]
PARK J, LEE Y T, AGOPIAN V G, et al. Liquid biopsy in hepatocellular carcinoma: challenges, advances, and clinical implications[J]. Clin Mol Hepatol, 2025, 31(Suppl): S255-S284. DOI: 10.3350/cmh.2024.0541.
[64]
VAN DER POL C B, MCINNES M D F, SALAMEH J P, et al. CT/MRI and CEUS LI-RADS major features association with hepatocellular carcinoma: individual patient data meta-analysis[J]. Radiology, 2022, 302(2): 326-335. DOI: 10.1148/radiol.2021211244.

PREV Research progress of magnetic resonance imaging in predicting immunohistochemical markers in hepatocellular carcinoma
NEXT Advances in imaging to assess liver volume
  


LINK


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