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

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

A novel recombinant human Frizzled-7 protein exhibits anti-tumor activity against triple negative breast cancer via abating Wnt/β-catenin pathway.

The international journal of biochemistry & cell biology·2018

Same author

Low-Temperature Carbide-Mediated Growth of Bicontinuous Nitrogen-Doped Mesoporous Graphene as an Efficient Oxygen Reduction Electrocatalyst.

Advanced materials (Deerfield Beach, Fla.)·2018

Same author

Dichloroacetic acid (DCA) synergizes with the SIRT2 inhibitor Sirtinol and AGK2 to enhance anti-tumor efficacy in non-small cell lung cancer.

Cancer biology & therapy·2018

Same author

A systematic analysis of the association between Notch1 expression and the patients with digestive tract cancers.

Biomarkers in medicine·2018

Same author

Occurrence and regression of BK polyomavirus associated carcinoma: a clinical and next-generation sequencing study.

Clinical science (London, England : 1979)·2018

Same author

Role of hepatoma-derived growth factor in promoting de novo lipogenesis and tumorigenesis in hepatocellular carcinoma.

Molecular oncology·2018

Same journal

End-to-end 2.5D multisequence-multichannel fusion model for preoperative survival prediction in glioma: a retrospective study.

BMC medical imaging·2026

Same journal

Association between 3 D CT-based volumetric fat infiltration of lumbar paraspinal muscles and bone mineral density: a clinical study.

BMC medical imaging·2026

Same journal

A study to measure the utility of an AI-enhanced reporting tool in assisting busy CCTA readers with REPORT generation (SMART-REPORT).

BMC medical imaging·2026

Same journal

Age-specific MRI patterns in pediatric epilepsy: insights from a sudanese cohort and implications for low-resources settings.

BMC medical imaging·2026

Same journal

Qualitative and quantitative assessment of intratumoral fat using chemical-shift MRI for predicting histological grade of hepatocellular carcinoma.

BMC medical imaging·2026

Same journal

Gd-EOB-DTPA-enhanced MRI in the diagnosis of intrahepatic cholestasis in mice: an experimental study.

BMC medical imaging·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jan 8, 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

Deep learning-based MRI model for predicting P53-mutated hepatocellular carcinoma.

Lulu Jia¹, Qing Yang^2,3, Hanchen Jiang⁴

¹The First Clinical Medical College of Lanzhou University, Lanzhou City, Gansu Province, China.

BMC Medical Imaging

|December 22, 2025

Summary

This summary is machine-generated.

A deep learning model using MRI sequences effectively predicts P53-mutated Hepatocellular Carcinoma (HCC). The combined model, integrating arterial phase (AP), portal venous phase (VP), and T2-weighted imaging (T2WI), showed high accuracy in identifying this aggressive cancer variant.

Keywords:

Deep learning Hepatocellular carcinoma Magnetic resonance imaging P53

More Related Videos

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI

Published on: July 21, 2023

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: Jan 8, 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

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI

Published on: July 21, 2023

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

Area of Science:

Radiology and Medical Imaging
Artificial Intelligence in Medicine
Oncology

Background:

P53-mutated Hepatocellular Carcinoma (HCC) is aggressive, linked to vascular endothelial growth factor (VEGF) and increased microvascular density.
Predicting P53 mutation status in HCC is crucial for targeted therapies and improved patient outcomes.

Purpose of the Study:

To develop and evaluate a deep learning model utilizing MRI data for the non-invasive prediction of P53-mutated HCC.
To compare the performance of single MRI sequences versus combined sequences in predicting P53 mutation status.

Main Methods:

Retrospective analysis of 312 pathologically confirmed HCC patients who underwent gadolinium-enhanced MRI.
Development of an EfficientNetV2-based deep learning model using arterial phase (AP), portal venous phase (VP), T2-weighted imaging (T2WI), and hepatobiliary phase (HBP) sequences.
Model performance assessed using AUC, accuracy, sensitivity, specificity, precision, and F1 score, with Delong's test for AUC comparisons.

Main Results:

The combined multiphase model (T2WI+AP+VP) significantly outperformed single-sequence models, achieving an AUC of 0.914 in the test dataset.
The hepatobiliary phase (HBP) model showed the best performance among single-sequence models (AUC=0.715).
Incorporating HBP into the combined model did not significantly improve predictive performance (P>0.05).

Conclusions:

A deep learning model integrating T2WI, AP, and VP MRI sequences is highly effective for predicting P53-mutated HCC.
This AI-driven approach offers a promising non-invasive tool for identifying aggressive HCC variants.
Further research may explore additional sequences or features to potentially enhance predictive accuracy.