Share:
Share this content in WeChat
X
• Review •
Research progress of CT and MRI radiomics in predicting postoperative recurrence of hepatocellular carcinoma
HUANG Mengjie  HUANG Deyou 

DOI:10.12015/issn.1674-8034.2026.11.022.


[Abstract] Hepatocellular carcinoma (HCC) continues to face persistently high postoperative recurrence rates, which critically compromise long-term patient survival. Traditional prediction methods based on clinicopathological indicators are constrained by invasiveness, temporal lag, and inherent subjectivity. As a non-invasive quantitative image analysis technique, radiomics enables in-depth mining of tumor heterogeneity information and offers a novel avenue for preoperative, non-invasive prediction of post-surgical recurrence. However, existing reviews predominantly focus on unimodal or single-technology approaches, lacking a systematic synthesis of the evolutionary trajectory from conventional radiomics to deep learning and habitat analysis across both CT and MRI modalities. This review systematically summarizes the research progress of CT- and MRI-based radiomics in predicting HCC recurrence after resection, covering the current applications of intratumoral, peritumoral, multiphasic, and deep learning models. We contend that this field is transitioning from a "performance-driven" paradigm toward a "clinically problem-oriented" one. Future efforts should prioritize multicenter prospective validation, elucidation of imaging–biology mechanistic associations, development of fully automated end-to-end platforms, and assessment of decision impact, so as to facilitate the substantive translation of radiomics from laboratory research into individualized clinical practice.
[Keywords] hepatocellular carcinoma;postoperative recurrence;radiomics;computed tomography;magnetic resonance imaging;machine learning;deep learning

HUANG Mengjie1, 2   HUANG Deyou2*  

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

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

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

Conflicts of interest   None.

Received  2026-07-23
Accepted  2026-10-21
DOI: 10.12015/issn.1674-8034.2026.11.022
DOI:10.12015/issn.1674-8034.2026.11.022.

[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]
CHIDAMBARANATHAN-REGHUPATY S, FISHER P B, SARKAR D. Hepatocellular carcinoma (HCC): Epidemiology, etiology and molecular classification[J]. Adv Cancer Res, 2021, 149: 1-61. DOI: 10.1016/bs.acr.2020.10.001.
[3]
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.
[4]
Expert Group of the State Key Project on Infectious Diseases on "Novel Strategies of Comprehensive and Individualizd Surgical Treatment of Viral Hepatitisrelated Liver Cancer" from the Ministry of Science. Chinese expert consensus on the preventation and management of recurrent hepatocellular carcinoma after hepatic resection(2020 edition)[J]. Chin J Pract Surg, 2021, 41(01): 20-30. DOI: 10.19538/j.cjps.issn1005-2208.2021.01.03.
[5]
NEVOLA R, RUOCCO R, CRISCUOLO L, et al. Predictors of early and late hepatocellular carcinoma recurrence[J]. World J Gastroenterol, 2023, 29(8): 1243-1260. DOI: 10.3748/wjg.v29.i8.1243.
[6]
CANALE M, ULIVI P, FOSCHI F G, et al. Clinical and circulating biomarkers of survival and recurrence after radiofrequency ablation in patients with hepatocellular carcinoma[J]. Crit Rev Oncol Hematol, 2018, 129: 44-53. DOI: 10.1016/j.critrevonc.2018.06.017.
[7]
STRAŚ W A, WASIAK D, ŁĄGIEWSKA B, et al. Recurrence of hepatocellular carcinoma after liver transplantation: risk factors and predictive models[J/OL]. Ann Transplant, 2022, 27: e934924 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/35078965/. DOI: 10.12659/aot.934924.
[8]
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.
[9]
YIP S S F, AERTS H J W L. Applications and limitations of radiomics[J]. Phys Med Biol, 2016, 61(13): R150-R166. DOI: 10.1088/0031-9155/61/13/R150.
[10]
NING P G, GAO F, HAI J J, et al. Application of CT radiomics in prediction of early recurrence in hepatocellular carcinoma[J]. Abdom Radiol (NY), 2020, 45(1): 64-72. DOI: 10.1007/s00261-019-02198-7.
[11]
LI Z Y, YU J L, LI Y H, et al. Radiomics model based on CT predicts early recurrence after surgical resection of CNLC stage Ⅰ-Ⅱ hepatocellular carcinoma[J]. J Clin Radiol, 2023, 42(10): 1590-1596. DOI: 10.13437/j.cnki.jcr.2023.10.027.
[12]
CAI Z D, XU J Q, CHEN Z P, et al. Research progress of endothelial cell encapsulation of tumor clusters in hepatocellular carcinoma[J]. J Guangdong Med Univ, 2025, 43(3): 311-317. DOI: 10.20227/j.cnki.2096-3610.2025.03.013.
[13]
LEI Y, BAI Y W, SU Y, et al. CT-based radiomics-clinical model for predicting recurrence in VETC-positive HCC patients after hepatectomy[J]. J Hepatocell Carcinoma, 2025, 12: 2585-2598. DOI: 10.2147/JHC.S549825.
[14]
NONG H Y, CEN Y Y, PAN Z L, et al. Ki-67 expression correlates with hepatocellular carcinoma recurrence and is predictable using radiomics features[J]. Abdom Radiol, 2026, 51(4): 1895-1906. DOI: 10.1007/s00261-025-05191-5.
[15]
CUI J F, LIN Z K, HUANG X J, et al. Predictive radiomics-based model for recurrence-free survival after curative resection in patients with hepatocellular carcinoma[J]. J Hepatocell Carcinoma, 2025, 12: 1755-1766. DOI: 10.2147/JHC.S535492.
[16]
DAI T, GU Q B, PENG Y J, et al. Preoperative noninvasive prediction of recurrence-free survival in hepatocellular carcinoma using CT-based radiomics model[J]. J Hepatocell Carcinoma, 2024, 11: 2211-2222. DOI: 10.2147/JHC.S493044.
[17]
SHAN Q Y, HU H T, FENG S T, et al. CT-based peritumoral radiomics signatures to predict early recurrence in hepatocellular carcinoma after curative tumor resection or ablation[J/OL]. Cancer Imaging, 2019, 19(1): 11 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/30813956/. DOI: 10.1186/s40644-019-0197-5.
[18]
LI N, WAN X T, ZHANG H, et al. Tumor and peritumor radiomics analysis based on contrast-enhanced CT for predicting early and late recurrence of hepatocellular carcinoma after liver resection[J/OL]. BMC Cancer, 2022, 22(1): 664 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/35715783/. DOI: 10.1186/s12885-022-09743-6.
[19]
LI Y H, QIAN G X, YAO L, et al. Preoperative model for predicting early recurrence in hepatocellular carcinoma patients using radiomics and deep learning: a multicenter study[J]. World J Gastrointest Oncol, 2025, 17(6): 106608 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/40547169/. DOI: 10.4251/wjgo.v17.i6.106608.
[20]
XIONG L X, FANG Q M, LI S H, et al. Value of radiomics of contrast-enhanced CT inprediction of early postoperative recurrence in hepatocellular carcinoma[J]. Radiol Pract, 2022, 37(4): 432-436. DOI: 10.13609/j.cnki.1000-0313.2022.04.004.
[21]
LI S Q, SU L L, XU T F, et al. Radiomics model based on contrast-enhanced computed tomography to predict early recurrence in patients with hepatocellular carcinoma after radical resection[J]. World J Gastroenterol, 2023, 29(26): 4186-4199. DOI: 10.3748/wjg.v29.i26.4186.
[22]
YAN X Z, LI Y C, QIN W Y, et al. Radiomics model based on contrast-enhanced computed tomography imaging for early recurrence monitoring after radical resection of AFP-negative hepatocellular carcinoma[J/OL]. BMC Cancer, 2024, 24(1): 700 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/38849749/. DOI: 10.1186/s12885-024-12436-x.
[23]
LI J Y, CHEN Z J, WANG Q Q, et al. Radiomics model based on preoperative contrast-enhanced CT and clinical features for predicting early recurrence of hepatocellular carcinoma[J/OL]. Ann Ital Chir, 2025, 96(6): 771-782. DOI: 10.62713/aic.3902.
[24]
YANG C Y, WEI X Q, YANG Q, et al. Multiphase enhanced CT-based radiomics for predicting recurrence in patient with hepatocellular carcinoma after tumor resection[J]. Chin J Med Imaging, 2025, 33(3): 245-251.
[25]
HUANG C, TIAN Y, ZHANG Q, et al. Prediction of recurrence after resection in hepatocellular carcinoma via whole liver deep learning on preoperative contrast-enhanced CT[J/OL]. Sci Rep, 2025, 15(1): 42975 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/41331271/. DOI: 10.1038/s41598-025-26933-x.
[26]
KINOSHITA M, UEDA D, MATSUMOTO T, et al. Deep learning model based on contrast-enhanced computed tomography imaging to predict postoperative early recurrence after the curative resection of a solitary hepatocellular carcinoma[J/OL]. Cancers, 2023, 15(7): 2140 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/37046801/. DOI: 10.3390/cancers15072140.
[27]
LV C, HE N, YANG J J, et al. Prediction of 3-year recurrence rate of hepatocellular carcinoma after resection based on contrast-enhanced CT: a single-centre study[J/OL]. Br J Radiol, 2023, 96(1145): 20220702 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/36745047/. DOI: 10.1259/bjr.20220702.
[28]
ZHANG Y B, CHEN Z Q, BU Y, et al. Construction of a 2.5D deep learning model for predicting early postoperative recurrence of hepatocellular carcinoma using multi-view and multi-phase CT images[J]. J Hepatocell Carcinoma, 2024, 11: 2223-2239. DOI: 10.2147/JHC.S493478.
[29]
MAO B, REN Y J, YU X, et al. Preoperative prediction for early recurrence of hepatocellular carcinoma using machine learning-based radiomics[J/OL]. Front Oncol, 2024, 14: 1346124 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/38559563/. DOI: 10.3389/fonc.2024.1346124.
[30]
LI X, CHEN J M, LI Z X, et al. Contrast-CT-based deep learning for predicting early postoperative recurrence in patients with hepatocellular carcinoma[J]. Radiol Pract, 2025, 40(8): 1002-1010. DOI: 10.13609/j.cnki.1000-0313.2025.08.009.
[31]
ZHAO Y F, LIU Z, WEI X Q, et al. Prediction of early recurrence after thermal ablation for hepatocellular carcinoma using contrast-enhanced CT and habitat analysis[J]. Chin J Med Imaging, 2025, 33(9): 929-935, 947.
[32]
ZHANG Y B, MA H Y, LEI P, et al. Prediction of early postoperative recurrence of hepatocellular carcinoma by habitat analysis based on different sequence of contrast-enhanced CT[J/OL]. Front Oncol, 2024, 14: 1522501 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/39830646/. DOI: 10.3389/fonc.2024.1522501.
[33]
WU Z Q, LIU D Y, OUYANG S Y, et al. Augmenting conventional criteria: a CT-based deep learning radiomics nomogram for early recurrence risk stratification in hepatocellular carcinoma after liver transplantation[J/OL]. Insights Imaging, 2025, 16(1): 194 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/40962936/. DOI: 10.1186/s13244-025-02082-7.
[34]
CHENG Z P, CHEN X L, ZHANG H, et al. Study on the radiomics model to predict early recurrence after hepatocellular carcinoma ablation[J]. Mod Interv Diagn Treat Gastroenterol, 2024, 29(8): 923-931, 942.
[35]
LI W C, SHEN H R, HAN L Z, et al. A multiparametric fusion radiomics signature based on contrast-enhanced MRI for predicting early recurrence of hepatocellular carcinoma[J/OL]. J Oncol, 2022, 2022: 3704987 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/36213823/. DOI: 10.1155/2022/3704987.
[36]
WANG L Y, MA X H, FENG B, et al. Multi-sequence MR-based radiomics signature for predicting early recurrence in solitary hepatocellular carcinoma ≤5 cm[J/OL]. Front Oncol, 2022, 12: 899404 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/35756618/. DOI: 10.3389/fonc.2022.899404.
[37]
ZHANG J Y, ZHANG T, ZHANG X Q, et al. Preoperative gadoxetic acid-enhanced MRI combine with vessels encapsulating tumor clusters in predicting early recurrence of hepatocellular carcinoma[J]. Radiol Pract, 2024, 39(10): 1367-1373. DOI: 10.13609/j.cnki.1000-0313.2024.10.014.
[38]
LIN Y Y, WANG J F, CHEN Y Y, et al. Predicting one-year recurrence of HCC based on gadoxetic acid-enhancedMRI by machine learning models[J/OL]. Curr Med Imaging Former Curr Med Imaging Rev, 2024, 20: e15734056293489 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/38462826/. DOI: 10.2174/0115734056293489240226064955.
[39]
WANG K D, GUAN M J, BAO Z Y, et al. Radiomics analysis based on dynamic contrast-enhanced MRI for predicting early recurrence after hepatectomy in hepatocellular carcinoma patients[J/OL]. Sci Rep, 2025, 15: 22240 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/40595796/. DOI: 10.1038/s41598-025-02291-6.
[40]
DONG Z C, ZHANG J B, XING M Y, et al. Predictive value of MRI radiomics for postoperative recurrence of liver cancer[J]. China Med Equip, 2025, 22(5): 57-61.
[41]
CHEN J P, ZHANG T H, YANG R H, et al. The value of Gd-EOB-DTPA-enhanced MRI combined with clinical features. in predicting early recurrence of hepatocellular carcinoma after resection[J]. Chin J CT MRI, 2023, 21(9): 121-124. DOI: 10.3969/j.issn.1672-5131.2023.09.040.
[42]
WEI H, ZHENG T Y, ZHANG X L, et al. MRI radiomics based on deep learning automated segmentation to predict early recurrence of hepatocellular carcinoma[J/OL]. Insights Imaging, 2024, 15(1): 120 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/38763975/. DOI: 10.1186/s13244-024-01679-8.
[43]
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: 10.13437/j.cnki.jcr.2026.04.015.
[44]
SONG W L, LIU H, XU Y, et al. Contrast-enhanced MRI–based multi-parameter habitats radiomics models to predict early recurrence in early-stage hepatocellular carcinoma following curative resection[J/OL]. Eur J Radiol, 2026, 195: 112560 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/41289727/. DOI: 10.1016/j.ejrad.2025.112560.
[45]
QIN Y J, ZHANG L G, ZHOU X Q, et al. Explainable fusion model for predicting postoperative early recurrence in hepatocellular carcinoma using gadoxetic acid-enhanced MRI habitat imaging[J]. Acad Radiol, 2025, 32(9): 5162-5172. DOI: 10.1016/j.acra.2025.04.018.
[46]
GAO W Y, WANG W T, SONG D J, et al. A predictive model integrating deep and radiomics features based on gadobenate dimeglumine-enhanced MRI for postoperative early recurrence of hepatocellular carcinoma[J]. Radiol Med, 2022, 127(3): 259-271. DOI: 10.1007/s11547-021-01445-6.
[47]
KUCUKKAYA A S, ZEEVI T, CHAI N X, et al. Predicting tumor recurrence on baseline MR imaging in patients with early-stage hepatocellular carcinoma using deep machine learning[J/OL]. Sci Rep, 2023, 13(1): 7579 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/37165035/. DOI: 10.1038/s41598-023-34439-7.
[48]
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.
[49]
ZHAO Y, WANG S, WANG Y, et al. Deep learning radiomics based on contrast enhanced MRI for preoperatively predicting early recurrence in hepatocellular carcinoma after curative resection[J/OL]. Front Oncol, 2024, 14: 1446386 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/39582540/. DOI: 10.3389/fonc.2024.1446386.
[50]
QU H, ZHANG S R, GUO M R, et al. Deep learning model for predicting proliferative hepatocellular carcinoma using dynamic contrast-enhanced MRI: implications for early recurrence prediction following radical resection[J]. Acad Radiol, 2024, 31(11): 4445-4455. DOI: 10.1016/j.acra.2024.04.028.
[51]
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 [2026-07-22]. https://pubmed.ncbi.nlm.nih.gov/40305886/. DOI: 10.1016/j.ejrad.2025.112130.

PREV Research progress on the Kaiser score in breast MRI diagnosis
NEXT Research progress of radiomics and deep learning in efficacy evaluation and prognosis prediction of liver malignant tumors
  



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