Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 13, 2026

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

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

Published on: October 10, 2018

CT Radiomics-based Machine Learning to Identify Intratumoral Fibrosis and Underlying Angiogenesis in Hepatocellular

Tian-Cheng Wang¹, Nan Wei², Yan Bao¹

¹Department of Radiology, the Second Xiangya Hospital of Central South University, Changsha, No.139 Middle Renmin Rd, 410011, China.

|May 12, 2026

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

Intratumoral Fibrosis is a Potential Biomarker in Patients with Hepatocellular Carcinoma Undergoing Liver Resection.

Journal of hepatocellular carcinoma·2026

Same author

Immunotherapy and Breast Reconstruction: Opportunities, Challenges, and Future Directions.

Cancer medicine·2026

Same author

DNA methylation patterns facilitate tracing the origin of neuroendocrine neoplasms.

Nature communications·2025

Same author

Radiomics-based prediction of HCC response to atezolizumab/bevacizumab.

Oncology letters·2025

Same author

Longitudinal CE-MRI-based Siamese network with machine learning to predict tumor response in HCC after DEB-TACE.

Cancer imaging : the official publication of the International Cancer Imaging Society·2025

Same author

Management of bilioenteric anastomosis leakage after major liver resection.

BJS open·2025

A new CT-based radiomics model, the Rad-ITF score, accurately classifies intratumoral fibrosis (ITF) in hepatocellular carcinoma (HCC). This score predicts treatment response and prognosis for patients undergoing transarterial chemoembolization (TACE).

Area of Science:

Radiology and Imaging Science
Oncology Research
Computational Pathology

Background:

Intratumoral fibrosis (ITF) is a key factor influencing hepatocellular carcinoma (HCC) prognosis and transarterial chemoembolization (TACE) efficacy.
Pretreatment biopsies for assessing ITF in HCC are not standard practice, necessitating alternative diagnostic methods.

Purpose of the Study:

To develop and validate a CT-based radiomics model (Rad-ITF score) for classifying ITF grade in HCC.
To assess the association between the Rad-ITF score, post-TACE prognosis, and tumor angiogenesis levels.

Main Methods:

A multicenter study involving retrospective and prospective cohorts for model development and validation (n=1675).
Histologic staining (Sirius red, H&E) served as the reference standard for ITF grading.

More Related Videos

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

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 13, 2026

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

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

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

Published on: August 16, 2020

Radiomics features extracted from CT images were used to build the Rad-ITF score, with performance evaluated using AUC.

Prognosis (PFS, tumor response) and angiogenesis were analyzed in independent cohorts using clinical data and multi-omics analyses (RNA-seq, scRNA-seq, spatial transcriptomics).

Main Results:

The Rad-ITF score demonstrated robust performance in classifying ITF grade across training, internal, and external validation cohorts (AUCs: 0.86, 0.85, 0.82).
High Rad-ITF scores were associated with significantly lower tumor response rates (46.2% vs 62.0%) and worse progression-free survival (PFS) (6.8 vs 11.2 months) in patients undergoing TACE.
Elevated Rad-ITF scores correlated with increased tumor angiogenesis, as confirmed by multi-omics data.

Conclusions:

The CT-based Rad-ITF score is an effective tool for classifying ITF grade in HCC.
The Rad-ITF score accurately reflects underlying tumor angiogenesis and stratifies prognosis in HCC patients treated with TACE.