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 Concept Videos

  1. Home
  3. Research Domains
  5. Biomedical And Clinical Sciences
  7. Oncology And Carcinogenesis
  9. Predictive And Prognostic Markers
  11. Radiomics And Deep Learning As Important Techniques Of Artificial Intelligence - Diagnosing Perspectives In Cytokeratin 19 Positive Hepatocellular Carcinoma

Radiomics and Deep Learning as Important Techniques of Artificial Intelligence - Diagnosing Perspectives in Cytokeratin 19 Positive Hepatocellular Carcinoma

Fei Wang1, Chunyue Yan2, Xinlan Huang3

  • 1Department of Radiology, Luzhou People's Hospital, Luzhou, 646000, People's Republic of China.

Journal of Hepatocellular Carcinoma
|June 11, 2025

Related Experiment Videos

Non-Invasive PET/MR Imaging in an Orthotopic Mouse Model of Hepatocellular Carcinoma
07:47

Non-Invasive PET/MR Imaging in an Orthotopic Mouse Model of Hepatocellular Carcinoma

Published on: August 31, 2022

2.2K
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
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

6.7K

View abstract on PubMed

Summary
This summary is machine-generated.

Predicting Cytokeratin 19 (CK19) expression in hepatocellular carcinoma (HCC) is inconsistent. Combined imaging, radiomics, and deep learning models show excellent potential for accurate, non-invasive prediction of CK19-positive HCC.

Area of Science:

  • Medical Imaging
  • Oncology
  • Artificial Intelligence in Medicine

Background:

  • Existing studies show inconsistencies in predicting Cytokeratin 19 (CK19) expression in hepatocellular carcinoma (HCC) using traditional imaging, radiomics, and deep learning.
  • Accurate preoperative prediction of CK19 expression is crucial for stratified management of HCC patients.

Purpose of the Study:

  • To systematically analyze and compare the performance of non-invasive methods for predicting CK19-positive HCC.
  • To provide insights for improving the stratified management of HCC patients.

Main Methods:

  • A comprehensive literature search was conducted across major databases (PubMed, EMBASE, Web of Science, Cochrane Library) up to February 2025.
  • Data from eligible studies were independently screened and extracted by two investigators.
Keywords:
artificial intelligencecytokeratin 19deep learninghepatocellular carcinoma

Related Experiment Videos

Non-Invasive PET/MR Imaging in an Orthotopic Mouse Model of Hepatocellular Carcinoma
07:47

Non-Invasive PET/MR Imaging in an Orthotopic Mouse Model of Hepatocellular Carcinoma

Published on: August 31, 2022

2.2K
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
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

6.7K
  • Key findings were summarized to provide a clear overview of study characteristics and performance metrics.

    • Main Results:

    • 22 studies involving 3395 HCC patients were included, with varying focus on traditional imaging (72.7%), radiomics (36.4%), deep learning (9.1%), and combined models (54.5%).
    • Magnetic resonance imaging was the most common modality. Most studies were published recently (2022-2025), but few were multicenter (27.3%) or prospective (13.6%).
    • Area Under the Curve (AUC) ranges varied: traditional imaging (0.560-0.917), radiomics (0.648-0.951), deep learning (0.718-0.820), and combined models (0.614-0.995).

    Conclusions:

    • Combined models integrating traditional imaging, radiomics, and deep learning demonstrate excellent potential for predicting CK19 expression in HCC.
    • Future research should prioritize developing user-friendly online tools utilizing multicenter, multimodal imaging, and advanced deep learning for enhanced prediction accuracy and robustness.
    • Addressing limitations in multicenter external data validation is essential for clinical translation.
    radiomics
    systematic review