Sub-regional CT Radiomics for the Prediction of Ki-67 Proliferation Index in Gastrointestinal Stromal Tumors: A Multi-center Study

Abstract

Rationale and Objectives

The objective was to assess and examine radiomics models derived from contrast-enhanced CT for their predictive capacity using the sub-regional radiomics regarding the Ki-67 proliferation index (PI) in patients with pathologically confirmed gastrointestinal stromal tumors (GIST).

Methods

In this retrospective study, a total of 412 GIST patients across three institutions (223 from center 1, 106 from center 2, and 83 from center 3) was enrolled. Radiomic features were derived from various sub-regions of the tumor region of interest employing the K-means approach. The Least Absolute Shrinkage and Selection Operator (LASSO) regression was employed to identify features correlated with Ki-67 PI level in GIST patients. A support vector machine (SVM) model was then constructed to predict the high level of Ki-67 (Ki-67 index > 8%), drawing on the radiomics features from each sub-region within the training cohort.

Results

After features selection process, 6, 9, 9, 7 features were obtained to construct SVM models based on sub-region 1, 2, 3 and the entire tumor, respectively. Among different models, the model developed by the sub-region 1 achieved an area under the receiver operating characteristic curve (AUC) of 0.880 (95% confidence interval [CI]: 0.830 to 0.919), 0.852 (95% CI: 0.770–0.914), 0.799 (95% CI: 0.697–0.879) in the training, external test set 1, and 2, respectively.

Conclusion

The results of the present study suggested that SVM model based on the sub-regional radiomics features had the potential of predicting Ki-67 PI level in patients with GIST.