Subregional CT radiomics for preoperative prediction of mitotic index and risk stratification in 2-5 cm gastrointestinal stromal tumors of the stomach: a dual-center study

TL;DR

This study uses CT scans to predict the mitotic index of stomach tumors before surgery, showing that analyzing specific tumor regions improves prediction accuracy.

Contribution

The novelty lies in using subregional CT radiomics to predict mitotic index in gastric GISTs, outperforming conventional whole-tumor models.

Findings

Subregional radiomics models based on unenhanced CT showed high predictive performance with an AUC of 0.98 in the training set.

The conventional whole-tumor model using venous phase CT achieved an AUC of 0.956 in the training set.

Subregional models demonstrated better sensitivity and specificity compared to conventional models in predicting mitotic index.

Abstract

To propose a model based on computed tomography (CT) subregional radiomics to predict the preoperative mitotic index of 2-5 cm Gastrointestinal Stromal Tumors (GISTs) of the stomach.

This retrospective study enrolled a total of 368 patients with GISTs from two institutions: Center 1 comprised 239 patients (122 M, 117 F; mean age 61.66 ± 10.86 years), and Center 2 comprised 129 patients (51 M, 78 F; mean age 60.28 ± 9.72 years). Radiomics features were extracted from the entire tumor. Concurrently, k-means clustering was applied to imaging features to define three distinct tumor subregions, from which radiomics features were subsequently extracted. The Recursive Feature Addition method was used to identify features correlated with the mitotic index in patients with 2-5 cm gastric GISTs. Using the selected features from each subregion and the whole tumor, logistic regression (LR) was employed to construct subregion-based radiomics models and conventional whole-tumor-based radiomics models, respectively.

Better performance was observed for unenhanced CT subregions 1, 2, and 3 compared with the conventional radiomics model. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the model for subregion 3 in the training set were 0.98, 0.97, 0.98, and 0.90, respectively. In the validation and external test sets, the AUC values were 0.874 and 0.804, respectively. The conventional whole-tumor radiomics model based on venous phase CT demonstrated superior performance compared to all subregion-based models, achieving an AUC of 0.956 in the training set, with accuracy, sensitivity, and specificity of 0.94, 0.97, and 0.83, respectively. In the validation and external test sets, it attained AUC values of 0.892 and 0.805, respectively.

Subregional CT radiomics may be used to predict the mitotic index of patients with 2-5 cm gastric GIST before surgery. In particular, subregional radiomics models based on unenhanced CT showed excellent predictive performance.

Figures