Preoperative CT-Based Deep Learning Model for Predicting Risk Stratification in Patients With Gastrointestinal Stromal Tumors

Bing Kang; Xianshun Yuan; Hexiang Wang; Songnan Qin; Xuelin Song; Xinxin Yu; Shuai Zhang; Cong Sun; Qing Zhou; Ying Wei; Feng Shi; Shifeng Yang; Ximing Wang

doi:10.3389/fonc.2021.750875

Preoperative CT-Based Deep Learning Model for Predicting Risk Stratification in Patients With Gastrointestinal Stromal Tumors

Front Oncol. 2021 Sep 17:11:750875. doi: 10.3389/fonc.2021.750875. eCollection 2021.

Authors

Bing Kang^{1

2}, Xianshun Yuan^{1

2}, Hexiang Wang³, Songnan Qin^{1

2}, Xuelin Song⁴, Xinxin Yu^{1

2}, Shuai Zhang⁵, Cong Sun², Qing Zhou⁶, Ying Wei⁶, Feng Shi⁶, Shifeng Yang², Ximing Wang²

Affiliations

¹ Cheeloo College of Medicine, School of Medicine, Shandong University, Jinan, China.
² Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong University, Jinan, China.
³ Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
⁴ Department of Radiology, Hospital of Traditional Chinese Medicine of Liaocheng City, Liaocheng, China.
⁵ School of Medicine, Shandong First Medical University, Jinan, China.
⁶ Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China.

Abstract

Objective: To develop and evaluate a deep learning model (DLM) for predicting the risk stratification of gastrointestinal stromal tumors (GISTs).

Methods: Preoperative contrast-enhanced CT images of 733 patients with GISTs were retrospectively obtained from two centers between January 2011 and June 2020. The datasets were split into training (n = 241), testing (n = 104), and external validation cohorts (n = 388). A DLM for predicting the risk stratification of GISTs was developed using a convolutional neural network and evaluated in the testing and external validation cohorts. The performance of the DLM was compared with that of radiomics model by using the area under the receiver operating characteristic curves (AUROCs) and the Obuchowski index. The attention area of the DLM was visualized as a heatmap by gradient-weighted class activation mapping.

Results: In the testing cohort, the DLM had AUROCs of 0.90 (95% confidence interval [CI]: 0.84, 0.96), 0.80 (95% CI: 0.72, 0.88), and 0.89 (95% CI: 0.83, 0.95) for low-malignant, intermediate-malignant, and high-malignant GISTs, respectively. In the external validation cohort, the AUROCs of the DLM were 0.87 (95% CI: 0.83, 0.91), 0.64 (95% CI: 0.60, 0.68), and 0.85 (95% CI: 0.81, 0.89) for low-malignant, intermediate-malignant, and high-malignant GISTs, respectively. The DLM (Obuchowski index: training, 0.84; external validation, 0.79) outperformed the radiomics model (Obuchowski index: training, 0.77; external validation, 0.77) for predicting risk stratification of GISTs. The relevant subregions were successfully highlighted with attention heatmap on the CT images for further clinical review.

Conclusion: The DLM showed good performance for predicting the risk stratification of GISTs using CT images and achieved better performance than that of radiomics model.

Keywords: X-ray computed; deep learning; gastrointestinal stromal tumors; prediction model; risk assessment; tomography.