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

Postoperative lung geometric repositioning after right upper lobectomy: the role of thoracic morphology configuration.

Quantitative imaging in medicine and surgery·2026
Same author

How to Prevent Recurrence of Idiopathic Lead Migration: A Case Report and Discussion of Management.

Journal of arrhythmia·2026
Same author

Suspected Macrocreatine Kinase Type 1 in an Asymptomatic Young Cat.

Case reports in veterinary medicine·2026
Same author

Postoperative quality of life and nutritional outcomes following subtotal, proximal, or distal gastrectomy for upper gastric cancer: a retrospective cohort study.

Surgery today·2026
Same author

Preoperative prediction of meningioma grade based on synthetic MRI quantitative T1 and T2 mapping.

Japanese journal of radiology·2026
Same author

Fenestration Re-creation for Early Fontan Deterioration: Long-Term Hemodynamic and Clinical Outcomes.

Pediatric cardiology·2026

Related Experiment Video

Updated: Jul 4, 2026

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

Machine learning models using 18F-FDG PET/CT radiomics for RAS mutation prediction and prognostic stratification in

Masatoyo Nakajo1, Daisuke Hirahara2, Kenji Baba3

  • 1Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan.

The British Journal of Radiology
|July 3, 2026
PubMed
Summary

Machine learning models using 18F-FDG PET radiomics can predict RAS mutation status and prognosis in colorectal cancer (CRC) patients. This noninvasive approach offers prognostic stratification comparable to genetic profiling.

Keywords:
18F-FDGColorectal cancerMachine learningPositron emission tomography/computed tomographyRAS mutation

More Related Videos

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

Utilizing 18F-FDG PET/CT Imaging and Quantitative Histology to Measure Dynamic Changes in the Glucose Metabolism in Mouse Models of Lung Cancer
06:51

Utilizing 18F-FDG PET/CT Imaging and Quantitative Histology to Measure Dynamic Changes in the Glucose Metabolism in Mouse Models of Lung Cancer

Published on: July 21, 2018

Related Experiment Videos

Last Updated: Jul 4, 2026

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 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

Utilizing 18F-FDG PET/CT Imaging and Quantitative Histology to Measure Dynamic Changes in the Glucose Metabolism in Mouse Models of Lung Cancer
06:51

Utilizing 18F-FDG PET/CT Imaging and Quantitative Histology to Measure Dynamic Changes in the Glucose Metabolism in Mouse Models of Lung Cancer

Published on: July 21, 2018

Area of Science:

  • Oncology
  • Radiology
  • Data Science

Background:

  • Colorectal cancer (CRC) prognosis and treatment depend on RAS mutation status.
  • Accurate prediction of RAS mutations and patient prognosis is crucial for effective CRC management.
  • Current methods for genetic profiling can be invasive and time-consuming.

Purpose of the Study:

  • To evaluate a machine learning (ML) model integrating clinical data and 2-deoxy-2-[18F]fluoro-D-glucose (18F-FDG)-PET radiomic features.
  • To predict RAS mutation status and prognosis in patients with colorectal cancer (CRC).
  • To assess the potential of noninvasive radiomics for genetic profiling and prognostic assessment in CRC.

Main Methods:

  • Retrospective study of 90 CRC patients undergoing pretreatment 18F-FDG-PET/CT.
  • Extraction of radiomic features from PET images and analysis of clinical variables.
  • Development of clinical, radiomics, and combined ML models using AutoGluon with 10-fold cross-validation.
  • Evaluation of RAS mutation prediction using AUC and survival outcomes using a radiomics survival (RSF) model.

Main Results:

  • The radiomics ML model achieved the highest performance for RAS mutation prediction (AUC = 0.675).
  • Key radiomic features identified by SHAP analysis included NGTDM_Complexity, kurtosis, and skewness.
  • ML-predicted RAS status provided prognostic stratification comparable to true genetic profiles (C-indices 0.675 vs. 0.685).
  • Strong correlation (r=0.99, ρ=0.98) and comparable survival curves were observed between risk scores from true and ML-predicted RAS models.

Conclusions:

  • 18F-FDG PET-based radiomics with ML demonstrated moderate performance in predicting RAS mutation status.
  • The ML model provided prognostic stratification comparable to that based on true genetic profiles.
  • This approach shows potential as a noninvasive method for genetic profiling and prognostic assessment in CRC, requiring further validation.