Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 29, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Novel Unsupervised Machine Learning Model Using Multi-Parametric Radiomics for Prognostic Stratification of Bifocal

Xi Jia1,2, Fei Wu1,2, Haoran Dai1,2

  • 1Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, People's Republic of China.

Journal of Hepatocellular Carcinoma
|May 28, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Multiparametric MRI-Based Machine Learning Radiomics Prognostic Models for Multifocal Hepatocellular Carcinoma Beyond Milan Criteria: A Retrospective Study.

Journal of hepatocellular carcinoma·2025
Same author

Exploring the MRI and Clinical Features of P53-Mutated Hepatocellular Carcinoma.

Journal of hepatocellular carcinoma·2024
Same author

Estimating Microvascular Invasion in Patients with Resectable Multinodular Hepatocellular Carcinoma by Using Preoperative Contrast-Enhanced MRI: Establishment and Validation of a Risk Score.

Journal of hepatocellular carcinoma·2023
Same author

Crossover phenomena of percolation transition in evolution networks with hybrid attachment.

Chaos (Woodbury, N.Y.)·2016
Same author

Relation Between C-X-C Motif Chemokine Receptor 4 Levels and the Presence and Extent of Angiographic Coronary Collaterals in Patients With Chronic Total Coronary Occlusion.

The American journal of cardiology·2016
Same author

Quantify patient-specific coronary material property and its impact on stress/strain calculations using in vivo IVUS data and 3D FSI models: a pilot study.

Biomechanics and modeling in mechanobiology·2016
Same journal

Machine-Learning Based Prognostic Model for Predicting Early Recurrence in HCC Patients After Hepatectomies: An Explainable AI Approach.

Journal of hepatocellular carcinoma·2026
Same journal

Multimodal Modeling Distinguishes Treatment Response from Overall Survival in Hepatocellular Carcinoma Receiving Combined Interventional and Targeted Immunotherapy.

Journal of hepatocellular carcinoma·2026
Same journal

Angiogenic Prognostic Signature for Stratification in Hepatocellular Carcinoma.

Journal of hepatocellular carcinoma·2026
Same journal

Current Status and Emerging Trends in Global Research on Liposome Therapy for Hepatocellular Carcinoma: A Bibliometric Analysis.

Journal of hepatocellular carcinoma·2026
Same journal

Integrating Combination Therapy and Smart Embolic Materials to Overcome the Therapeutic Ceiling of Transarterial Chemoembolization in Hepatocellular Carcinoma.

Journal of hepatocellular carcinoma·2026
Same journal

Putative Imprinting Control Regions with Aberrant Blood-Based DNA Methylation are Associated with Hepatocellular Carcinoma Risk.

Journal of hepatocellular carcinoma·2026
See all related articles
This summary is machine-generated.

This study identified two radiomics subtypes in bifocal hepatocellular carcinoma (bHCC) that predict patient outcomes after surgery. High radiomics image heterogeneity (high-RIH) is linked to worse recurrence-free survival and overall survival.

Area of Science:

  • Radiology
  • Oncology
  • Machine Learning

Background:

  • Bifocal hepatocellular carcinoma (bHCC) presents unique challenges due to tumor heterogeneity.
  • Understanding tumor heterogeneity is crucial for predicting patient prognosis after surgical resection.

Purpose of the Study:

  • To identify radiomics subtypes reflecting tumor heterogeneity in bHCC using unsupervised machine learning.
  • To develop preoperative and postoperative models for predicting recurrence-free survival (RFS) and overall survival (OS) in bHCC patients post-hepatectomy.

Main Methods:

  • Retrospective analysis of 182 bHCC patients.
  • Radiomics features extracted from both lesions across six MR sequences, integrated using a two-lesion fusion approach.
  • Similarity network fusion and spectral clustering used to identify radiomics subtypes.
Keywords:
hepatocellular carcinomamagnetic resonance imagingprognosisunsupervised machine learning

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: May 29, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

  • Multivariable Cox regression analysis to develop prognostic models for RFS and OS.

    • Main Results:

    • Unsupervised clustering revealed two radiomics subtypes associated with distinct clinical outcomes.
    • High radiomics image heterogeneity (high-RIH) was significantly correlated with poorer RFS (p=0.0059) and OS (p=0.0343).
    • Independent predictors for shorter RFS included RIH cluster, pathological satellite nodule, and microvascular invasion (MVI).
    • Independent predictors for shorter OS included RIH cluster, radiological satellite nodule, and MVI.

    Conclusions:

    • Two distinct radiomics subtypes in bHCC were identified, reflecting tumor heterogeneity.
    • These subtypes can predict clinical outcomes in bHCC patients following hepatectomy.
    • Radiomics analysis offers a valuable tool for prognostic assessment in bHCC.