Jove
Visualize
Contact Us

Related Concept Videos

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
  1. Home
  3. A Novel Radiomics Approach For Predicting Tace Outcomes In Hepatocellular Carcinoma Patients Using Deep Learning For Multi-organ Segmentation.
  1. Home
  3. A Novel Radiomics Approach For Predicting Tace Outcomes In Hepatocellular Carcinoma Patients Using Deep Learning For Multi-organ Segmentation.

Related Experiment Video

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

8.2K

A novel radiomics approach for predicting TACE outcomes in hepatocellular carcinoma patients using deep learning for

Krzysztof Bartnik1, Mateusz Krzyziński2, Tomasz Bartczak2

  • 1Second Department of Radiology, Medical University of Warsaw, Banacha 1a st., 02-097, Warsaw, Poland. krzysztof.bartnik@wum.edu.pl.

Scientific Reports
|June 26, 2024

View abstract on PubMed

Summary
This summary is machine-generated.

This study introduces an automated radiomics approach to predict outcomes for hepatocellular carcinoma (HCC) patients undergoing transarterial chemoembolization (TACE). The novel method, using deep learning on CT scans, shows promise in forecasting treatment success beyond traditional clinical models.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
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

6.8K

Related Experiment Videos

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

8.2K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
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

6.8K

Area of Science:

  • Radiology
  • Oncology
  • Artificial Intelligence

Background:

  • Transarterial chemoembolization (TACE) is standard for unresectable hepatocellular carcinoma (HCC).
  • Predicting long-term TACE outcomes is challenging due to multifactorial influences.
  • Current radiomics models often rely on manual segmentation of tumor regions.

Purpose of the Study:

  • To develop and evaluate a novel machine learning approach using radiomics for predicting TACE outcomes in HCC patients.
  • To assess the performance of automated radiomics models compared to clinical predictors.
  • To investigate the significance of non-tumoral regions in outcome prediction.

Main Methods:

  • A fully automated, deep learning-based radiomics model was applied to pre-TACE CT images of 252 HCC patients.
  • Radiomics features were extracted from multiple organ volumes of interest (VOIs), including non-tumoral regions.
  • Random survival forest models were trained and compared against Cox proportional hazard models using clinical data.

    • Main Results:

    • The radiomics model demonstrated comparable performance to clinical models for overall survival prediction.
    • Radiomics models significantly outperformed clinical models in predicting progression-free survival.
    • Explainable AI analysis revealed the critical importance of non-tumoral VOI features, surpassing the predictive value of tumor-specific features.

    Conclusions:

    • Automated radiomics analysis of multiple VOIs offers a robust method for predicting TACE outcomes in HCC.
    • This approach overcomes limitations of manual segmentation and highlights the prognostic value of non-tumoral liver tissue.
    • The findings suggest potential clinical utility for this AI-driven radiomics model in personalized HCC treatment planning.