Clinical-radiomics-based treatment decision support for KIT Exon 11 deletion in gastrointestinal stromal tumors: a multi-institutional retrospective study

Yu Zhang; Xiaofei Yue; Peng Zhang; Yuying Zhang; Linxia Wu; Nan Diao; Guina Ma; Yuting Lu; Ling Ma; Kaixiong Tao; Qian Li; Ping Han

doi:10.3389/fonc.2023.1193010

Clinical-radiomics-based treatment decision support for KIT Exon 11 deletion in gastrointestinal stromal tumors: a multi-institutional retrospective study

Front Oncol. 2023 Aug 14:13:1193010. doi: 10.3389/fonc.2023.1193010. eCollection 2023.

Authors

Yu Zhang^{1

2}, Xiaofei Yue^{1

2}, Peng Zhang³, Yuying Zhang⁴, Linxia Wu^{1

2}, Nan Diao^{1

2}, Guina Ma^{1

2}, Yuting Lu^{1

2}, Ling Ma⁵, Kaixiong Tao³, Qian Li^{1

2}, Ping Han^{1

2}

Affiliations

¹ Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
² Hubei Province Key Laboratory of Molecular Imaging, Wuhan, China.
³ Department of Gastrointestinal Surgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
⁴ Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, Nanning, China.
⁵ He Kang Corporate Management (SH) Co. Ltd., Shanghai, China.

Abstract

Objective: gastrointestinal stromal tumors (GISTs) with KIT exon 11 deletions have more malignant clinical outcomes. A radiomics model was constructed for the preoperative prediction of KIT exon 11 deletion in GISTs.

Methods: Overall, 126 patients with GISTs who underwent preoperative enhanced CT were included. GISTs were manually segmented using ITK-SNAP in the arterial phase (AP) and portal venous phase (PVP) images of enhanced CT. Features were extracted using Anaconda (version 4.2.0) with PyRadiomics. Radiomics models were constructed by LASSO. The clinical-radiomics model (combined model) was constructed by combining the clinical model with the best diagnostic effective radiomics model. ROC curves were used to compare the diagnostic effectiveness of radiomics model, clinical model, and combined model. Diagnostic effectiveness among radiomics model, clinical model and combine model were analyzed in external cohort (n=57). Statistics were carried out using R 3.6.1.

Results: The Radscore showed favorable diagnostic efficacy. Among all radiomics models, the AP-PVP radiomics model exhibited excellent performance in the training cohort, with an AUC of 0.787 (95% CI: 0.687-0.866), which was verified in the test cohort (AUC=0.775, 95% CI: 0.608-0.895). Clinical features were also analyzed. Among the radiomics, clinical and combined models, the combined model showed favorable diagnostic efficacy in the training (AUC=0.863) and test cohorts (AUC=0.851). The combined model yielded the largest AUC of 0.829 (95% CI, 0.621-0.950) for the external validation of the combined model. GIST patients could be divided into high or low risk subgroups of recurrence and mortality by the Radscore.

Conclusion: The radiomics models based on enhanced CT for predicting KIT exon 11 deletion mutations have good diagnostic performance.

Keywords: CT; KIT exon 11; gastrointestinal stromal tumor; nomogram; radiomics.