Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Advertisement

Scientific Reports
  • View all journals
  • Search
  • My Account Login
  • Content Explore content
  • About the journal
  • Publish with us
  • Sign up for alerts
  • RSS feed
  1. nature
  2. scientific reports
  3. articles
  4. article
Machine learning integrating MRI and clinical features predicts early recurrence of hepatocellular carcinoma after resection
Download PDF
Download PDF
  • Article
  • Open access
  • Published: 18 January 2026

Machine learning integrating MRI and clinical features predicts early recurrence of hepatocellular carcinoma after resection

  • Lijuan Feng1 na1,
  • Ningbin Luo2 na1,
  • Fengqiu Ruan1,
  • Xihuan Zheng2,
  • Xiaoyu Pan1,
  • Xuan Li1,
  • Liang Fu1 &
  • …
  • Liling Long  ORCID: orcid.org/0000-0003-3369-85321,3,4 

Scientific Reports , Article number:  (2026) Cite this article

  • 1369 Accesses

  • 2 Altmetric

  • Metrics details

We are providing an unedited version of this manuscript to give early access to its findings. Before final publication, the manuscript will undergo further editing. Please note there may be errors present which affect the content, and all legal disclaimers apply.

Subjects

  • Biomarkers
  • Biotechnology
  • Oncology

Abstract

This study aims to construct a robust artificial intelligence (AI) model to predict early recurrence of hepatocellular carcinoma (HCC) following surgical resection, leveraging clinical blood biomarkers, pathological parameters, and MRI-derived features. We included 240 hepatectomy patients from two medical centers, collecting clinical blood biomarkers, MRI features, and postoperative pathological data. Feature reduction was conducted using Spearman correlation and the least absolute shrinkage and selection operator (LASSO) regression. Predictive models were constructed using five machine learning algorithms and validated on an external dataset. The models were subsequently compared. The ExtraTrees, XGBoost, and LightGBM models exhibited high predictive performance in the training set, with AUCs of 0.816 (95% CI 0.748–0.884), 0.978 (95% CI 0.958–0.998), and 0.898 (95% CI 0.846–0.950), respectively. In the validation set, their AUC values were 0.759 (95% CI 0.641–0.876), 0.789 (95% CI 0.684–0.894), and 0.760 (95% CI 0.650–0.869). Decision curve analysis indicated favorable net benefits for predicting early recurrence across all three models. Tumor margin and age were identified as significant factors, showing strong associations with early recurrence. This study developed AI model utilizing clinical blood biomarkers, MRI features, and pathological information to predict early recurrence of HCC after surgery. The models demonstrated good predictive performance and showed clinical applicability in predicting early recurrence, potentially assisting clinicians in identifying high-risk patients, guiding individualized surveillance, and optimizing postoperative management. However, inherent biases in this retrospective study necessitate further research for validation and refinement.

Similar content being viewed by others

Radiomics analysis based on dynamic contrast-enhanced MRI for predicting early recurrence after hepatectomy in hepatocellular carcinoma patients

Article Open access 01 July 2025

Artificial intelligence-based personalized treatment strategies for unresectable hepatocellular carcinoma: integrating HSP90α for prognosis and survival prediction

Article Open access 27 December 2025

Predicting hepatocellular carcinoma survival with artificial intelligence

Article Open access 20 February 2025

Data availability

The datasets used and/or analysed during the current study available from the corresponding author on reasonable request.

Abbreviations

AI:

Artificial intelligence

HCC:

Hepatocellular carcinoma

LASSO:

The least absolute shrinkage and selection operator

AFP:

Alpha-fetoprotein levels

NEUT:

Neutrophi

LY:

Lymphocyte

NLR:

Neutrophil-to-lymphocyte ratio

PLT:

Platelet count

ALB:

Albumin

ALT:

Alanine aminotransferase

AST:

Aspartate aminotransferase

PA:

Prealbumin

GGT:

Gamma-glutamyl transferase

TBIL:

Total bilirubin

DBIL:

Direct bilirubin

PT:

Prothrombin time

INR:

International normalized ratio

HBP:

Hepatobiliary phase

BCLC:

Barcelona clinical liver cancer

MVI:

Microvascular invasion

ES:

Edmondson–Steiner

AUC:

Area under the receiver operating characteristic curve

DCA:

Decision curve analysis

References

  1. Llovet, J. M. et al. Hepatocellular carcinoma. Nat. Rev. Dis. Primers. 7 (1), 6. https://doi.org/10.1038/s41572-020-00240-3 (2021).

    Google Scholar 

  2. Zhang, Z. H. et al. Role of microvascular invasion in early recurrence of hepatocellular carcinoma after liver resection: A literature review. Asian J. Surg. 47 (5), 2138–2143. https://doi.org/10.1016/j.asjsur.2024.02.115 (2024).

    Google Scholar 

  3. Shi, S., Zhao, Y. X., Fan, J. L., Chang, L. Y. & Yu, D. X. Development and external validation of a nomogram including body composition parameters for predicting early recurrence of hepatocellular carcinoma after hepatectomy. Acad. Radiol. 30 (12), 2940–2953. https://doi.org/10.1016/j.acra.2023.05.022 (2023).

    Google Scholar 

  4. Cheng, Z. et al. Risk factors and management for early and late intrahepatic recurrence of solitary hepatocellular carcinoma after curative resection. HPB 17 (5), 422–427. https://doi.org/10.1111/hpb.12367 (2015).

    Google Scholar 

  5. Nevola, R. et al. Predictors of early and late hepatocellular carcinoma recurrence. World J. Gastroenterol. 29 (8), 1243–1260. https://doi.org/10.3748/wjg.v29.i8.1243 (2023).

    Google Scholar 

  6. Zeng, J. et al. Development of a machine learning model to predict early recurrence for hepatocellular carcinoma after curative resection. Hepatobiliary Surg. Nutr. 11 (2), 176–187. https://doi.org/10.21037/hbsn-20-466 (2022).

    Google Scholar 

  7. Gao, W. et al. A predictive model integrating deep and radiomics features based on gadobenate dimeglumine-enhanced MRI for postoperative early recurrence of hepatocellular carcinoma. Radiol. Med. 127 (3), 259–271. https://doi.org/10.1007/s11547-021-01445-6 (2022).

    Google Scholar 

  8. Zhang, Z. et al. Hepatocellular carcinoma: radiomics nomogram on Gadoxetic acid-enhanced MR imaging for early postoperative recurrence prediction. Cancer Imaging. 19 (1), 22–32. https://doi.org/10.1186/s40644-019-0209-5 (2019).

    Google Scholar 

  9. Ji, G. W. et al. Machine-learning analysis of contrast-enhanced CT radiomics predicts recurrence of hepatocellular carcinoma after resection: a multi-institutional study. EBioMedicine 50, 156–165. https://doi.org/10.1016/j.ebiom.2019.10.057 (2019).

    Google Scholar 

  10. Yan, M. et al. Deep learning nomogram based on gd-EOB-DTPA MRI for predicting early recurrence in hepatocellular carcinoma after hepatectomy. Eur. Radiol. 33 (7), 4949–4961. https://doi.org/10.1007/s00330-023-09419-0 (2023).

    Google Scholar 

  11. Miranda, J. et al. Current status and future perspectives of radiomics in hepatocellular carcinoma. World J. Gastroenterol. 29 (1), 43–60. https://doi.org/10.3748/wjg.v29.i1.43 (2023).

    Google Scholar 

  12. Zheng, C. et al. Gut Microbiome as a biomarker for predicting early recurrence of < span style=font-variant:Small-caps;>HBV -related hepatocellular carcinoma. Cancer Sci. 114 (12), 4717–4731. https://doi.org/10.1111/cas.15983 (2023).

    Google Scholar 

  13. Zhou, S. L. et al. Genomic sequencing identifies WNK2 as a driver in hepatocellular carcinoma and a risk factor for early recurrence. J. Hepatol. 71 (6), 1152–1163. https://doi.org/10.1016/j.jhep.2019.07.014 (2019).

    Google Scholar 

  14. Fu, Y. et al. Combining a machine-learning derived 4-lncRNA signature with AFP and TNM stages in predicting early recurrence of hepatocellular carcinoma. BMC Genom. 24 (1), 89–104. https://doi.org/10.1186/s12864-023-09194-8 (2023).

    Google Scholar 

  15. Dong, B. et al. Development of a machine learning-based model to predict prognosis of alpha-fetoprotein-positive hepatocellular carcinoma. J. Transl. Med. 22 (1), 455–465. https://doi.org/10.1186/s12967-024-05203-w (2024).

    Google Scholar 

  16. Wang, X. et al. Clinical-radiological characteristic for predicting ultra-early recurrence after liver resection in solitary hepatocellular carcinoma patients. J. Hepatocell Carcinoma. 10, 2323–2335. https://doi.org/10.2147/JHC.S434955 (2023).

    Google Scholar 

  17. European Association for the Study of the Liver. EASL clinical practice guidelines: management of hepatocellular carcinoma. J. Hepatol. 69 (1), 182–236. https://doi.org/10.1016/j.jhep.2018.03.019 (2018).

    Google Scholar 

  18. Kang, I. et al. Subclassification of microscopic vascular invasion in hepatocellular carcinoma. Ann. Surg. 274 (6), e1170–e1178. https://doi.org/10.1097/SLA.0000000000003781 (2021).

    Google Scholar 

  19. Yan, Y. et al. Radiomic analysis based on Gd-EOB-DTPA enhanced MRI for the preoperative prediction of Ki-67 expression in hepatocellular carcinoma. Acad. Radiol. 31 (3), 859–869. https://doi.org/10.1016/j.acra.2023.07.019 (2024).

    Google Scholar 

  20. Shah, S. A. et al. Factors associated with early recurrence after resection for hepatocellular carcinoma and outcomes. J. Am. Coll. Surg. 202 (2), 275–283. https://doi.org/10.1016/j.jamcollsurg.2005.10.005 (2006).

    Google Scholar 

  21. Zeng, J. et al. Development of a machine learning model to predict early recurrence for hepatocellular carcinoma after curative resection. HepatoBiliary Surg. Nutr. 11 (2). https://doi.org/10.21037/hbsn-20-466 (2022).

  22. Wei, Y., Pei, W., Qin, Y., Su, D. & Liao, H. Preoperative MR imaging for predicting early recurrence of solitary hepatocellular carcinoma without microvascular invasion. Eur. J. Radiol. 138, 109663. https://doi.org/10.1016/j.ejrad.2021.109663 (2021).

    Google Scholar 

  23. Kawashima, J. et al. Development and validation of a preoperative risk prediction model for severe complications and very early recurrence after liver resection for hepatocellular carcinoma. Surgery 185, 109527. https://doi.org/10.1016/j.surg.2025.109527 (2025).

    Google Scholar 

  24. Ariizumi, S. et al. A non-smooth tumor margin in the hepatobiliary phase of Gadoxetic acid disodium (Gd‐EOB‐DTPA) ‐enhanced magnetic resonance imaging predicts microscopic portal vein invasion, intrahepatic metastasis, and early recurrence after hepatectomy in patients with hepatocellular carcinoma. J. Hepato Biliary Pancreat. 18 (4), 575–585. https://doi.org/10.1007/s00534-010-0369-y (2011).

    Google Scholar 

  25. Zhang, L. et al. The role of preoperative dynamic contrast-enhanced 3.0-T MR imaging in predicting early recurrence in patients with early-Stage hepatocellular carcinomas after curative resection. Front. Oncol. 9, 1336. https://doi.org/10.3389/fonc.2019.01336 (2019).

    Google Scholar 

  26. Chou, C. T. et al. Prediction of microvascular invasion of hepatocellular carcinoma: preoperative CT and histopathologic correlation. Am. J. Roentgenol. 203 (3), W253–W259. https://doi.org/10.2214/AJR.13.10595 (2014).

    Google Scholar 

  27. Chartampilas, E. et al. Current imaging diagnosis of hepatocellular carcinoma. Cancers 14 (16), 3997. https://doi.org/10.3390/cancers14163997 (2022).

    Google Scholar 

  28. Liu, C. et al. A K-nearest neighbor model to predict early recurrence of hepatocellular carcinoma after resection. J. Clin. Transl. Hepatol. 10 (4), 600–607. https://doi.org/10.14218/JCTH.2021.00348 (2022).

    Google Scholar 

  29. Wang, H. et al. A novel nomogram predicting the early recurrence of hepatocellular carcinoma patients after R0 resection. Front. Oncol. 13, 1133807. https://doi.org/10.3389/fonc.2023.1133807 (2023).

    Google Scholar 

  30. Yen, Y. H. et al. A simple model to predict early recurrence of hepatocellular carcinoma after liver resection. Langenbecks Arch. Surg. 409 (1), 261. https://doi.org/10.1007/s00423-024-03449-y (2024).

    Google Scholar 

  31. Giuffrè, M. et al. Predictors of hepatocellular carcinoma early recurrence in patients treated with surgical resection or ablation treatment: a single-center experience. Diagnostics 12 (10), 2517. https://doi.org/10.3390/diagnostics12102517 (2022).

    Google Scholar 

  32. Ryu, J. M. et al. Prognostic impact of elevation of cancer antigen 15 – 3 (CA15-3) in patients with early breast cancer with normal serum CA15-3 level. J. Breast Cancer. 26 (2), 126–136. https://doi.org/10.4048/jbc.2023.26.e17 (2023).

    Google Scholar 

  33. Zheng, C. et al. Nomogram based on clinical and preoperative CT features for predicting the early recurrence of combined hepatocellular-cholangiocarcinoma: a multicenter study. Radiol. med. 128 (12), 1460–1471. https://doi.org/10.1007/s11547-023-01726-2 (2023).

    Google Scholar 

  34. Wang, J. et al. 3D MR elastography of hepatocellular carcinomas as a potential biomarker for predicting tumor recurrence. Magn. Reson. Imaging. 49 (3), 719–730. https://doi.org/10.1002/jmri.26250 (2019).

    Google Scholar 

  35. Zang, Y., Long, P., Wang, M., Huang, S. & Chen, C. Development and validation of prognostic nomograms in patients with hepatocellular carcinoma: a population-based study. Future Oncol. 17 (36), 5053–5066. https://doi.org/10.2217/fon-2020-1065 (2021).

    Google Scholar 

  36. Qin, C., Gao, Y., Li, J., Huang, C. & He, S. Predictive effects of preoperative serum CA125 and AFP levels on post-hepatectomy survival in patients with hepatitis B-related hepatocellular carcinoma. Oncol. Lett. 21 (6), 487–500. https://doi.org/10.3892/ol.2021.12748 (2021).

    Google Scholar 

  37. Zhang, Z. Y., Guan, J., Wang, X. P., Hao, D. S. & Zhou, Z. Q. Outcomes of adolescent and young patients with hepatocellular carcinoma after curative liver resection: a retrospective study. World J. Surg. Oncol. 20 (1), 210–217. https://doi.org/10.1186/s12957-022-02658-3 (2022).

    Google Scholar 

  38. Zeng, J. et al. Prognosis factors of young patients undergoing curative resection for hepatitis B virus-related hepatocellular carcinoma: a multicenter study. Cancer Manag. Res. 12, 6597–6606. https://doi.org/10.2147/CMAR.S261368 (2020).

    Google Scholar 

  39. Chen, J. P. et al. Pre-operative enhanced magnetic resonance imaging combined with clinical features predict early recurrence of hepatocellular carcinoma after radical resection. World J. Gastrointest. Oncol. 16 (4), 1192–1203. https://doi.org/10.4251/wjgo.v16.i4.1192 (2024).

    Google Scholar 

  40. Romeo, M. et al. Clinical applications of artificial intelligence (AI) in human cancer: is it time to update the diagnostic and predictive models in managing hepatocellular carcinoma (HCC)? Diagnostics 15 (3), 252–274. https://doi.org/10.3390/diagnostics15030252 (2025).

    Google Scholar 

  41. Seven, İ. et al. Predicting hepatocellular carcinoma survival with artificial intelligence. Sci. Rep. 15 (1), 6226. https://doi.org/10.1038/s41598-025-90884-6 (2025).

    Google Scholar 

  42. Tibshirani, R. Regression shrinkage and selection via the Lasso. J. R. Stat. Soc. B. 58 (1), 267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x (1996).

    Google Scholar 

  43. Friedman, J., Hastie, T. & Tibshirani, R. Regularization paths for generalized linear models via coordinate descent. J. Stat. Softw. 33 (1), 1–22 (2010).

    Google Scholar 

  44. Feng, L. et al. Predicting overall survival in hepatocellular carcinoma patients via a combined MRI radiomics and pathomics signature. Transl. Oncol. 51, 102174. https://doi.org/10.1016/j.tranon.2024.102174 (2025).

    Google Scholar 

  45. Jiang, W. et al. Pathomics signature for prognosis and chemotherapy benefits in stage III colon cancer. JAMA Surg. 159 (5), 519–529. https://doi.org/10.1001/jamasurg.2023.8015 (2024).

    Google Scholar 

  46. Chen, D. et al. Prognostic and predictive value of a pathomics signature in gastric cancer. Nat. Commun. 13 (1), 6903. https://doi.org/10.1038/s41467-022-34703-w (2022).

    Google Scholar 

  47. Chen, T., Guestrin, C. & XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785 (2016).

Download references

Funding

This study was supported by the National Natural Science Foundation of China, Grant/Award Number: 82060310.

Author information

Author notes

  1. These authors contributed equally: Lijuan Feng and Ningbin Luo.

Authors and Affiliations

  1. Department of Radiology, First Affiliated Hospital of Guangxi Medical University, No. 6, Shuangyong Road, Zhuangautonomous region, Nanning, 530021, Guangxi, People’s Republic of China

    Lijuan Feng, Fengqiu Ruan, Xiaoyu Pan, Xuan Li, Liang Fu & Liling Long

  2. Department of Radiology, Guangxi Medical University Cancer Hospital, Nanning, China

    Ningbin Luo & Xihuan Zheng

  3. Key Laboratory of Early Prevention and Treatment for Regional High Frequency Tumor, Gaungxi Medical University, Ministry of Education, Nanning, Guangxi, China

    Liling Long

  4. Guangxi Key Laboratory of Immunology and Metabolism for Liver Diseases, First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, China

    Liling Long

Authors
  1. Lijuan Feng
    View author publications

    Search author on:PubMed Google Scholar

  2. Ningbin Luo
    View author publications

    Search author on:PubMed Google Scholar

  3. Fengqiu Ruan
    View author publications

    Search author on:PubMed Google Scholar

  4. Xihuan Zheng
    View author publications

    Search author on:PubMed Google Scholar

  5. Xiaoyu Pan
    View author publications

    Search author on:PubMed Google Scholar

  6. Xuan Li
    View author publications

    Search author on:PubMed Google Scholar

  7. Liang Fu
    View author publications

    Search author on:PubMed Google Scholar

  8. Liling Long
    View author publications

    Search author on:PubMed Google Scholar

Contributions

L.F.: Conceptualization, formal analysis, visualization, writing original draft, investigation, software. N.L.: Conceptualization, data curation, formal analysis, investigation, validation, visualization, software, writing original draft. F.R.: Investigation, data curation, validation. X.Z.: Data curation, validation. X.P.: Data curation, validation. X.L.: Data curation, validation. L.F.: Data curation, validation. L.L.: Methodology, project administration, writing review and editing, funding acquisition.

Corresponding author

Correspondence to Liling Long.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary Material 1

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Feng, L., Luo, N., Ruan, F. et al. Machine learning integrating MRI and clinical features predicts early recurrence of hepatocellular carcinoma after resection. Sci Rep (2026). https://doi.org/10.1038/s41598-026-36261-3

Download citation

  • Received: 25 October 2024

  • Accepted: 12 January 2026

  • Published: 18 January 2026

  • DOI: https://doi.org/10.1038/s41598-026-36261-3

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Keywords

  • Hepatocellular carcinoma
  • Early recurrence
  • MRI
  • Machine learning
  • AI
Download PDF

Advertisement

Explore content

  • Research articles
  • News & Comment
  • Collections
  • Subjects
  • Follow us on Facebook
  • Follow us on Twitter
  • Sign up for alerts
  • RSS feed

About the journal

  • About Scientific Reports
  • Contact
  • Journal policies
  • Guide to referees
  • Calls for Papers
  • Editor's Choice
  • Journal highlights
  • Open Access Fees and Funding

Publish with us

  • For authors
  • Language editing services
  • Open access funding
  • Submit manuscript

Search

Advanced search

Quick links

  • Explore articles by subject
  • Find a job
  • Guide to authors
  • Editorial policies

Scientific Reports (Sci Rep)

ISSN 2045-2322 (online)

nature.com sitemap

About Nature Portfolio

  • About us
  • Press releases
  • Press office
  • Contact us

Discover content

  • Journals A-Z
  • Articles by subject
  • protocols.io
  • Nature Index

Publishing policies

  • Nature portfolio policies
  • Open access

Author & Researcher services

  • Reprints & permissions
  • Research data
  • Language editing
  • Scientific editing
  • Nature Masterclasses
  • Research Solutions

Libraries & institutions

  • Librarian service & tools
  • Librarian portal
  • Open research
  • Recommend to library

Advertising & partnerships

  • Advertising
  • Partnerships & Services
  • Media kits
  • Branded content

Professional development

  • Nature Awards
  • Nature Careers
  • Nature Conferences

Regional websites

  • Nature Africa
  • Nature China
  • Nature India
  • Nature Japan
  • Nature Middle East
  • Privacy Policy
  • Use of cookies
  • Legal notice
  • Accessibility statement
  • Terms & Conditions
  • Your US state privacy rights
Springer Nature

© 2026 Springer Nature Limited

Nature Briefing: Translational Research

Sign up for the Nature Briefing: Translational Research newsletter — top stories in biotechnology, drug discovery and pharma.

Get what matters in translational research, free to your inbox weekly. Sign up for Nature Briefing: Translational Research