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

You might also read

Related Articles

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

Sort by
Same author

JUNB transcriptional regulation of KRT20 via ITGB1 activates PI3K/AKT signaling pathway against fibrosis-induced by renal injury.

Biology direct·2026
Same author

ASO Author Reflections: Foundation Models Unlock Lymphovascular Invasion Prediction from Routine Prostate Cancer Histology.

Annals of surgical oncology·2026
Same author

Foundation Model and Multi-Instance Learning-Based Framework for Predicting Lymphovascular Invasion in Prostate Cancer.

Annals of surgical oncology·2026
Same author

Risk Factors and Prediction Model for Early-Onset Immune-Related Adverse Events in Pan-Cancer Patients Undergoing Anti-PD-(L)1 Therapy: A Retrospective Study in a Tertiary-Level Hospital.

Cancer medicine·2026
Same author

Machine Learning Integration Framework Constructs a Lactylation-Associated Gene Signature to Improve Prognosis in Bladder Cancer.

Cancer medicine·2026
Same author

Apigenin combined with cisplatin suppressed the progression of colorectal cancer by targeting the KRT23/Wnt/β-catenin signaling pathway.

Discover oncology·2025

Related Experiment Video

Updated: Jan 13, 2026

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

7.4K

Biological Interpretable Machine Learning Model for Predicting Pathological Grading in Clear Cell Renal Cell

Dingzhong Yang1, Haonan Mei2, Panpan Jiao2

  • 1Experimental Teaching and Engineering Training Center, South-Central Minzu University, Wuhan 430074, China.

Bioengineering (Basel, Switzerland)
|October 29, 2025
PubMed
Summary

Machine learning models using CT urography radiomics can predict clear cell renal cell carcinoma (ccRCC) International Society of Urological Pathology (ISUP) grade non-invasively. The XGBoost model showed the best predictive performance, aiding risk stratification and clinical decisions.

Keywords:
ISUP gradingclear cell renal cell carcinomamachine learningperitumoral arearadiomics

More Related Videos

In Vivo, Percutaneous, Needle Based, Optical Coherence Tomography of Renal Masses
09:31

In Vivo, Percutaneous, Needle Based, Optical Coherence Tomography of Renal Masses

Published on: March 30, 2015

9.3K
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

8.6K

Related Experiment Videos

Last Updated: Jan 13, 2026

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

7.4K
In Vivo, Percutaneous, Needle Based, Optical Coherence Tomography of Renal Masses
09:31

In Vivo, Percutaneous, Needle Based, Optical Coherence Tomography of Renal Masses

Published on: March 30, 2015

9.3K
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

8.6K

Area of Science:

  • Radiology
  • Oncology
  • Artificial Intelligence

Background:

  • Clear cell renal cell carcinoma (ccRCC) grading is crucial for treatment decisions.
  • Current grading relies on invasive methods, prompting research into non-invasive alternatives.
  • CT urography (CTU) offers potential for non-invasive tumor characterization.

Purpose of the Study:

  • To evaluate machine learning models for predicting ccRCC ISUP grade using CTU-derived peritumoral area (PAT) radiomics.
  • To assess the non-invasive predictive value of radiomics features for tumor aggressiveness.

Main Methods:

  • Retrospective analysis of 328 ccRCC patients and external validation with 175 patients (The Cancer Genome Atlas).
  • Extraction of 1218 radiomics features from contrast-enhanced CT images.
  • Feature selection using LASSO regression and model development with Logistic Regression, Multilayer Perceptron, Support Vector Machine, and XGBoost.
  • Performance evaluation using Receiver Operating Characteristic (ROC) analysis.

Main Results:

  • The XGBoost model achieved high discriminative ability: AUCs of 0.95 (training), 0.93 (internal validation), and 0.92 (external validation).
  • XGBoost significantly outperformed other models (p < 0.001) and showed prognostic value (Log-rank p = 0.018).
  • Transcriptomic analysis revealed distinct biological signatures associated with high-grade predictions, including metabolic and immune pathways.

Conclusions:

  • Machine learning models utilizing CTU PAT radiomics effectively predict ccRCC ISUP grade non-invasively.
  • The XGBoost model demonstrated superior predictive performance.
  • This non-invasive approach can improve preoperative risk stratification and guide clinical decision-making, potentially reducing the need for biopsies.