Computed-Tomography-Based Radiomics Model for Predicting the Malignant Potential of Gastrointestinal Stromal Tumors Preoperatively: A Multi-Classifier and Multicenter Study

Minhong Wang; Zhan Feng; Lixiang Zhou; Liang Zhang; Xiaojun Hao; Jian Zhai

doi:10.3389/fonc.2021.582847

Computed-Tomography-Based Radiomics Model for Predicting the Malignant Potential of Gastrointestinal Stromal Tumors Preoperatively: A Multi-Classifier and Multicenter Study

Front Oncol. 2021 Apr 22:11:582847. doi: 10.3389/fonc.2021.582847. eCollection 2021.

Authors

Minhong Wang¹, Zhan Feng², Lixiang Zhou³, Liang Zhang⁴, Xiaojun Hao¹, Jian Zhai¹

Affiliations

¹ Department of Radiology, The First Affiliated Hospital of Wannan Medical College, Wuhu, China.
² Department of Radiology, College of Medicine, The First Affiliated Hospital, Zhejiang University, Hangzhou, China.
³ Department of Pharmacy, The First Affiliated Hospital of Wannan Medical College, Wuhu, China.
⁴ Department of Radiology, Zhejiang Cancer Hospital, Hangzhou, China.

Abstract

Background: Our goal was to establish and verify a radiomics risk grading model for gastrointestinal stromal tumors (GISTs) and to identify the optimal algorithm for risk stratification. Methods: We conducted a retrospective analysis of 324 patients with GISTs, the presence of which was confirmed by surgical pathology. Patients were treated at three different hospitals. A training cohort of 180 patients was collected from the largest center, while an external validation cohort of 144 patients was collected from the other two centers. To extract radiomics features, regions of interest (ROIs) were outlined layer by layer along the edge of the tumor contour on CT images of the arterial and portal venous phases. The dimensionality of radiomic features was reduced, and the top 10 features with importance value above 5 were selected before modeling. The training cohort used three classifiers [logistic regression, support vector machine (SVM), and random forest] to establish three GIST risk stratification prediction models. The receiver operating characteristic curve (ROC) was used to compare model performance, which was validated by external data. Results: In the training cohort, the average area under the curve (AUC) was 0.84 ± 0.07 of the logistic regression, 0.88 ± 0.06 of the random forest, and 0.81 ± 0.08 of the SVM. In the external validation cohort, the AUC was 0.85 of the logistic regression, 0.90 of the random forest, and 0.80 of the SVM. The random forest model performed the best in both the training and the external validation cohorts and could be generalized. Conclusion: Based on CT radiomics, there are multiple machine-learning models that can predict the risk of GISTs. Among them, the random forest algorithm had the highest prediction efficiency and could be readily generalizable. Through external validation data, we assume that the random forest model may be used as an effective tool to guide preoperative clinical decision-making.

Keywords: X-ray computer; gastrointestinal stromal tumor; multi-classifier; radiomics; risk classification.