CT Radiomics for the Preoperative Prediction of Ki67 Index in Gastrointestinal Stromal Tumors: A Multi-Center Study.

Yilei Zhao,Chencui Huang,Liang Zhang,Meirong Li,Meibao Feng,Minhong Wang

doi:10.3389/fonc.2021.689136

Abstract

PurposeThis study established and verified a radiomics model for the preoperative prediction of the Ki67 index of gastrointestinal stromal tumors (GISTs).Materials and MethodsA total of 344 patients with GISTs from three hospitals were divided into a training set and an external validation set. The tumor region of interest was delineated based on enhanced computed-tomography (CT) images to extract radiomic features. The Boruta algorithm was used for dimensionality reduction of the features, and the random forest algorithm was used to construct the model for radiomics prediction of the Ki67 index. The receiver operating characteristic (ROC) curve was used to evaluate the model’s performance and generalization ability.ResultsAfter dimensionality reduction, a feature subset having 21 radiomics features was generated. The generated radiomics model had an the area under curve (AUC) value of 0.835 (95% confidence interval(CI): 0.761–0.908) in the training set and 0.784 (95% CI: 0.691–0.874) in the external validation cohort.ConclusionThe radiomics model of this study had the potential to predict the Ki67 index of GISTs preoperatively.

Highlights

Gastrointestinal stromal tumors (GISTs) are the most common mesenchymal-derived tumors of the gastrointestinal tract, with complex biological behaviors
The pathogenesis of GISTs is mainly due to functional gene mutations of KIT, which lead to the continuous activation of the proto-oncogene receptor tyrosine kinase [1]
Studies have found that patients with Ki67 index > 8% have a high risk of recurrence, which is an adverse factor for adjuvant imatinib therapy

Summary

INTRODUCTION

Gastrointestinal stromal tumors (GISTs) are the most common mesenchymal-derived tumors of the gastrointestinal tract, with complex biological behaviors. Radiomics Ki67 Gastrointestinal Stromal Tumors activated pathways and is often used to control postoperative recurrence of high-risk GISTs and in neoadjuvant therapy [2, 3]. Studies have found that patients with Ki67 index > 8% have a high risk of recurrence, which is an adverse factor for adjuvant imatinib therapy. The CT imaging characteristics, including size, contour, and tumor margin, are correlated with the Ki67 index in GISTs, suggesting that imaging features can be used to predict the expression of Ki67 in GISTs [9]. In this study we constructed a prediction model of the Ki67 index (cutoff value of 8%) for patients with GISTs by extracting the texture and morphological features of tumors from enhanced CT images, and verified the model with independent external data to evaluate the generalization ability

MATERIALS AND METHODS

DISCUSSION

CONCLUSION

ETHICS STATEMENT