Department of medical imaging, The Affiliated Huaian No.1 People's Hospital of Nanjing Medical University, No.1, Huang he West Road, Huai'an, 223300, Jiangsu, China.
Sci Rep. 2024 Nov 26;14(1):29336. doi: 10.1038/s41598-024-80978-y.
To develop and validate a machine learning (ML) model which combined computed tomography (CT) semantic and radiomics features to preoperatively predict Ki-67 expression in gastrointestinal stromal tumors (GISTs) patients. We retrospectively collected the clinical, imaging and pathological data of 149 GISTs patients. We randomly assigned the patients in a ratio of 7:3 to a training set (104 cases) and a validation (45 cases) set. We divided the patients into low and high Ki-67 expression group according to postoperative pathology. CT semantic features were analyzed from preoperative enhancement CT images and radiomics features were extracted from venous phase-enhanced images. We used intraclass correlation coefficient, maximal relevance and minimal redundancy and least absolute shrinkage and selection operator method to screen radiomics features and build radiomics label. 6 ML models were used for model construction. Receiver operating characteristic curves were used to evaluate the predictive efficiency of ML models. SHAP analysis was used to explain the contribution of different variables and their risk threshold. AUC of radscores in predicting Ki-67 expression of GIST patients were 0.749 and 0.729 in training and validation set. Among the 6 ML models, SVM exhibited best prediction accuracy. AUC of SVM model in predicting Ki-67 expression of GIST patients were 0.840, 0.767 and 0.832 in training, validation and test set. SHAP analysis showed that radscores and tumor diameter had highly positive contribution to the model. Therefore, the interpretable SVM model can predict Ki-67 expression of GISTs patients individually before surgery, which can provide reliable imaging biomarkers for clinical treatment decisions.
为了开发和验证一种机器学习（ML）模型，该模型结合了计算机断层扫描（CT）语义和放射组学特征，以术前预测胃肠道间质瘤（GIST）患者的 Ki-67 表达。我们回顾性收集了 149 例 GIST 患者的临床、影像学和病理学数据。我们将患者按 7:3 的比例随机分配到训练集（104 例）和验证集（45 例）。我们根据术后病理将患者分为低 Ki-67 表达组和高 Ki-67 表达组。从术前增强 CT 图像分析 CT 语义特征，从静脉期增强图像提取放射组学特征。我们使用组内相关系数、最大相关性和最小冗余以及最小绝对收缩和选择算子方法筛选放射组学特征并构建放射组学标签。使用 6 种 ML 模型进行模型构建。使用受试者工作特征曲线评估 ML 模型的预测效率。使用 SHAP 分析解释不同变量的贡献及其风险阈值。在训练集和验证集中，radscores 预测 GIST 患者 Ki-67 表达的 AUC 分别为 0.749 和 0.729。在 6 种 ML 模型中，SVM 表现出最佳的预测准确性。在训练、验证和测试集中，SVM 模型预测 GIST 患者 Ki-67 表达的 AUC 分别为 0.840、0.767 和 0.832。SHAP 分析表明，radscores 和肿瘤直径对模型有高度的正贡献。因此，可解释的 SVM 模型可以在术前单独预测 GIST 患者的 Ki-67 表达，为临床治疗决策提供可靠的影像学生物标志物。
