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

Multimodality staging of renal cell carcinoma-pearls & pitfalls.

Abdominal radiology (New York)·2026
Same author

Reduced environmental impact in body CT imaging with deep learning reconstruction: experience of a high-volume tertiary referral center.

Insights into imaging·2026
Same author

IgG4-related retroperitoneal fibrosis mimicking perinephric extension of renal cell carcinoma on CT: a case report.

BJR case reports·2026
Same author

Use of Artificial Intelligence in prostate MRI: A rapid scoping review highlighting limited evidence in screening context.

European journal of radiology·2026
Same author

Differentiation of <i>Lupinus</i> and <i>Mimosa</i> by Machine Learning Employing Spectroscopic Data: A Comparative Study.

ACS omega·2026
Same author

Breast Cancer Metastasis to a Renal Cell Carcinoma: A Comprehensive Review with Emphasis on Novel Immunohistochemical Tools.

International journal of surgical pathology·2026

Related Experiment Video

Updated: Jun 16, 2025

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

Radiomics-Based Classification of Clear Cell Renal Cell Carcinoma ISUP Grade: A Machine Learning Approach with

María Aymerich1, Alejandra García-Baizán1,2, Paolo Niccolò Franco3

  • 1Diagnostic Imaging Research Group, Galicia Sur Health Research Institute, Hospital Álvaro Cunqueiro, 36312 Vigo, Spain.

Diagnostics (Basel, Switzerland)
|June 13, 2025
PubMed
Summary

This study developed a radiomics machine learning model using CT scans to accurately classify clear cell renal cell carcinoma (ccRCC) ISUP grade, improving non-invasive diagnosis and treatment planning.

Keywords:
ISUP gradeSHAP valuesclear cell renal cell carcinomacomputed tomographyfeature selectionmachine learningnon-invasive biomarkersradiomicstexture analysis

More Related Videos

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

6.8K
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

Related Experiment Videos

Last Updated: Jun 16, 2025

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
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

6.8K
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

Area of Science:

  • Radiology
  • Oncology
  • Machine Learning

Background:

  • Clear cell renal cell carcinoma (ccRCC) is the most common kidney cancer subtype.
  • Prognosis is linked to International Society of Urological Pathology (ISUP) grade.
  • Radiomics offers non-invasive classification potential, complementing histopathology.

Purpose of the Study:

  • Develop and interpret a radiomics-based machine learning model for ccRCC ISUP grade classification.
  • Utilize nephrographic-phase CT images for automated grading.
  • Enhance model transparency with SHAP values for clinical interpretability.

Main Methods:

  • Retrospective analysis of 109 ccRCC patients.
  • Extraction and feature selection of radiomic features from CT scans.
  • Training logistic regression, SVM, and random forest models with cross-validation; SHAP value computation.

Main Results:

  • Logistic regression model achieved 82% accuracy and 0.86 AUC.
  • SHAP analysis highlighted major axis length, busyness, and large area emphasis as key features.
  • Identified shape and texture features critical for distinguishing high vs. low ISUP grades.

Conclusions:

  • Nephrographic-phase CT radiomics enables accurate, non-invasive ISUP grading of ccRCC.
  • SHAP values improve model interpretability for clinical adoption.
  • Potential for integration into precision oncology workflows.