JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Predictive value of CT-based imaging model for BRAF gene mutation in patients with colorectal cancer: a retrospective study

  • 0Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen, China.
Translational Cancer Research +

|

July 21, 2025

|

July 21, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

This study developed a CT-based radiomics model to predict BRAF gene mutations in colorectal cancer patients. The model shows promise in identifying mutations associated with poor outcomes and treatment resistance.

Area Of Science

  • Oncology
  • Radiology
  • Genetics

Background

  • BRAF gene mutations in colorectal cancer correlate with adverse clinical outcomes and resistance to therapy.
  • Radiomics offers a quantitative method to analyze CT scan features for predictive modeling.
  • Accurate prediction of BRAF mutations is crucial for personalized treatment strategies in colorectal cancer.

Purpose Of The Study

  • To evaluate the predictive capability of a CT imaging-based radiomics model for BRAF gene mutations in colorectal cancer.
  • To establish a CT-based radiomics nomogram for predicting BRAF mutation status.
  • To provide a valuable tool for clinical decision-making in colorectal cancer management.

Main Methods

  • A cohort of 100 colorectal cancer patients were analyzed, divided into BRAF mutation and non-mutation groups.
  • Univariate and multivariate logistic regression analyses identified key influencing factors for BRAF mutations.
  • A CT-based radiomics nomogram was constructed and validated using Receiver Operating Characteristic (ROC) curve analysis.

Main Results

  • Lymph node metastasis, tumor differentiation, invasion depth, and tumor size were identified as independent predictors of BRAF mutation.
  • The CT-based radiomics model achieved an Area Under the Curve (AUC) of 0.826 in the training set and 0.670 in the verification set.
  • The developed radiomics nomogram demonstrated significant predictive value for BRAF gene mutations.

Conclusions

  • A CT-based radiomics nomogram was successfully developed and validated for predicting BRAF gene mutations in colorectal cancer.
  • The CT imaging model holds substantial value in predicting BRAF gene mutations, aiding in risk stratification and treatment planning.
  • This approach offers a non-invasive method to assess genetic status, complementing traditional diagnostic methods.

Keywords: