Prediction model of NIH risk stratification for gastrointestinal stromal tumor based on ultrasonographic radiomics by oral contrast enhanced ultrasonography
10.3760/cma.j.cn131148-20230628-00351
- VernacularTitle:基于胃充盈超声造影下的影像组学构建胃间质瘤NIH危险度分级预测模型
- Author:
Fan YANG
1
;
Chunwei LIU
;
Dai ZHANG
;
Lihui ZHAO
;
Yiran MAO
;
Jie MU
;
Hailing WANG
;
Xi WEI
Author Information
1. 天津医科大学肿瘤医院超声诊疗科 国家恶性肿瘤临床医学研究中心 天津市肿瘤防治重点实验室 天津市恶性肿瘤临床医学研究中心，天津 300060
- Keywords:
Gastrointestinal stromal tumor;
Ultrasonography;
Radiomics;
Risk stratification
- From:
Chinese Journal of Ultrasonography
2023;32(12):1062-1069
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To investigate the prediction of National Institute of Healthy (NIH) risk stratification of gastrointestinal stromal tumor(GIST) based on clinical ultrasound model, ultrasonographic radiomics model and combined model by oral contrast enhanced ultrasonography.Methods:The clinical and ultrasound imaging data of 204 gastric GIST patients attending Tianjin Medical University Cancer Institute and Hospital from June 2021 to June 2022 were retrospectively analyzed, among whom a total of 101 patients with high and moderate NIH risk stratification GIST confirmed by postoperative pathology were included in the high risk group, and a total of 103 patients with low and extremely low NIH risk stratification GIST were in the low risk group. The ultrasound images of the largest diameter of the GIST were manually segmented by ITK-SNAP software, and Pyradiomics (v3.0.1) module in Python 3.8.7 was applied to extract ultrasonographic radiomics features from the ROI segmented images. The patients were randomly divided into training and validation sets in the ratio of 7∶3. The XGBoost of Sklearn module was applied to construct the clinical ultrasound imaging model, ultrasonographic radiomics model, and combined model. Then the area under ROC curve (AUC), sensitivity, specificity, and accuracy were evaluated; the predictive ability of the three models was compared by Delong test. Calibration Curve was applied to evaluate the model performance, and the clinical Decision Curve Analysis was applied to determine the net benefit to patients.Results:A total of 578 ultrasonographic radiomics features were extracted from ROI, and 8 ultrasonographic radiomics features were finally retained for modeling after regression and dimensionality reduction. Finally, test results showed that AUC, sensitivity, specificity and accuracy of clinical ultrasound imaging model, ultrasonographic radiomics model and combined model were 0.75, 69.3%, 68.9%, 69.1%; 0.87, 79.2%, 81.6%, 80.4%; 0.91, 80.2%, 83.5%, 81.9%, respectively. Delong test showed that the difference of AUC between ultrasonographic radiomics model and clinical ultrasound imaging model was statistically significant ( Z=2.698, P<0.001), and the combined model was significantly better than clinical ultrasound imaging model ( Z=4.062, P<0.001) and ultrasonographic radiomics model ( Z=2.225, P=0.026). Calibration Curve showed the high performance of combined model, and Decision Curve Analysis showed the superior clinical usefulness of combined model. Conclusions:It is feasible to construct an ultrasonographic radiomics model for GIST NIH risk stratification based on oral contrast enhanced ultrasonography images, and the combined model has more advantageous diagnostic performance, which can identify high risk NIH GIST objectively and stably for clinical purposes.
