Identification of D842V mutation in gastrointestinal stromal tumors based on CT radiomics: a multi-center study
2024

Identifying D842V Mutation in GISTs Using CT Radiomics

Sample size: 872 publication 10 minutes Evidence: moderate

Author Information

Author(s): Xie Zhenhui, Zhang Qingwei, Zhang Ranying, Zhao Yuxuan, Zhang Wang, Song Yang, Yu Dexin, Lin Jiang, Li Xiaobo, Suo Shiteng, Zhou Yan

Primary Institution: Renji Hospital, School of Medicine, Shanghai Jiao Tong University

Hypothesis

Can radiomics features from CT images distinguish GISTs with D842V mutations?

Conclusion

Radiomics features from CT images can help identify D842V mutations in gastrointestinal stromal tumors.

Supporting Evidence

  • The combined model showed better average precision and F1 score than the non-radiomics model.
  • 24 patients with D842V-mutant GISTs were identified in the training cohort.
  • The study included data from three independent centers.
  • Radiomics features were extracted from venous-phase CECT images.
  • Patients with D842V mutations have a poor response to standard TKI therapies.
  • Statistical analysis indicated significant differences in model performance.
  • Random forest models were used to compare predictive capabilities.
  • Imaging features may help guide treatment decisions in resource-limited settings.

Takeaway

Doctors can use special pictures from CT scans to find out if a tumor has a specific mutation that makes it hard to treat.

Methodology

The study analyzed CT images from 872 GIST patients, using radiomics features to develop prediction models.

Potential Biases

Potential selection bias due to the retrospective nature of the study.

Limitations

The retrospective design may introduce selection bias, and the study may not represent all GIST patients due to the low prevalence of D842V mutations.

Participant Demographics

Patients included were diagnosed with GIST, with a higher proportion of males in the D842V-mutant group.

Statistical Information

P-Value

p=0.039 for average precision comparison

Confidence Interval

[0.097, 0.486] for average precision of the combined model

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/s40644-024-00815-3

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication