Related Experiment Video
Updated: Jun 4, 2025
Gene Regulation and Targeted Therapy in Gastric Cancer Peritoneal Metastasis: Radiological Findings from Dual Energy CT and PET/CT
Published on: January 22, 2018
Identification of D842V mutation in gastrointestinal stromal tumors based on CT radiomics: a multi-center study
Zhenhui Xie1, Qingwei Zhang2, Ranying Zhang3
1Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Pujian Road 160, Pudong District, 200127, Shanghai, China.
Background:
Gastrointestinal stromal tumors (GISTs) are the most common mesenchymal tumors of the gastrointestinal tract. Recent advent of tyrosine kinase inhibitors (TKIs) has significantly improved the prognosis of GIST patients. However, responses to TKI therapy can vary depending on the specific gene mutation. D842V, which is the most common mutation in platelet-derived growth factor receptor alpha exon 18, shows no response to imatinib and sunitinib. Radiomics features based on venous-phase contrast-enhanced computed tomography (CECT) have shown potential in non-invasive prediction of GIST genotypes. This study sought to determine whether radiomics features could help distinguish GISTs with D842V mutations.
Methods:
A total of 872 pathologically confirmed GIST patients with CECT data available from three independent centers were included and divided into the training cohort ( ) and the external validation cohort ( ). Clinical features including age, sex, tumor size and location were collected. Radiomics features on the largest axial image of venous-phase CECT were analyzed and a total of two radiomics features were selected after feature selection. Random forest models trained on non-radiomics features only (the non-radiomics model) and on both non-radiomics and radiomics features (the combined model) were compared.
Results:
The combined model showed better average precision (0.250 vs. 0.102, p = 0.039) and F1 score (0.253 vs. 0.155, p = 0.012) than the non-radiomics model. There was no significant difference in ROC-AUC (0.728 vs. 0.737, p = 0.836) and geometric mean (0.737 vs. 0.681, p = 0.352).
Conclusions:
This study demonstrated the potential of radiomics features based on venous-phase CECT images to identify D842V mutation in GISTs. Our model may provide an alternative approach to guide TKI therapy for patients inaccessible to sequence variant testing, potentially improving treatment outcomes for GIST patients especially in resource-limited settings.
Insights
Radiomics features from CT scans can help identify D842V mutations in gastrointestinal stromal tumors (GISTs). This approach may guide tyrosine kinase inhibitor (TKI) therapy for patients lacking genetic testing, improving GIST treatment outcomes.
Area of Science:
- Oncology
- Medical Imaging
- Genetics
Background:
- Gastrointestinal stromal tumors (GISTs) are common mesenchymal tumors.
- Tyrosine kinase inhibitors (TKIs) have improved GIST prognosis, but treatment response varies by mutation.
- The D842V mutation confers resistance to certain TKIs like imatinib and sunitinib.
Purpose of the Study:
- To investigate the potential of radiomics features from venous-phase contrast-enhanced computed tomography (CECT) for non-invasively predicting the D842V mutation in GISTs.
- To develop and validate a model combining clinical and radiomics features for D842V mutation identification.
Main Methods:
- Analysis of 872 GIST patients' CECT data from three centers, divided into training and validation cohorts.
- Extraction and selection of radiomics features from venous-phase CECT images.
- Comparison of random forest models: one using only clinical features (non-radiomics) and another combining clinical and radiomics features.
Main Results:
- The combined model demonstrated significantly improved average precision (0.250 vs. 0.102, p=0.039) and F1 score (0.253 vs. 0.155, p=0.012) compared to the non-radiomics model.
- No significant differences were observed in ROC-AUC (0.728 vs. 0.737, p=0.836) or geometric mean (0.737 vs. 0.681, p=0.352) between the models.
Conclusions:
- Radiomics features from venous-phase CECT show promise in identifying the D842V mutation in GISTs.
- This radiomics-based model offers a potential non-invasive alternative for guiding TKI therapy, especially for patients unable to undergo genetic sequencing.
- The findings could enhance treatment strategies and outcomes for GIST patients, particularly in resource-limited settings.
