Department of Pediatric Oncology, Tianjin Medical University Cancer Institute and Hospital, Tianjin, China.
National Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin, China.
Int J Med Sci. 2023 Jan 22;20(2):278-286. doi: 10.7150/ijms.79758. eCollection 2023.
To explore extrathyroidal extension (ETE) in children and adolescents with papillary thyroid carcinoma using a multiclassifier ultrasound radiomic model. In this study, data from 164 pediatric patients with papillary thyroid cancer (PTC) were retrospectively analyzed and patients were randomly divided into a training cohort (115) and a validation cohort (49) in a 7:3 ratio. To extract radiomics features from ultrasound images of the thyroid, areas of interest (ROIs) were delineated layer by layer along the edge of the tumor contour. The feature dimension was then reduced using the correlation coefficient screening method, and 16 features with a nonzero coefficient were chosen using Lasso. Then, in the training cohort, four supervised machine learning radiomics models (k-nearest neighbor, random forest, support vector machine [SVM], and LightGBM) were developed. ROC and decision-making curves were utilized to compare model performance, which was validated using validation cohorts. In addition, the SHapley Additive exPlanations (SHAP) framework was applied to explain the optimal model. In the training cohort, the average area under the curve (AUC) was 0.880 (0.835-0.927), 0.873 (0.829-0.916), 0.999 (0.999-1.000), and 0.926 (0.892-0.926) for the SVM, KNN, random forest, and LightGBM, respectively. In the validation cohort, the AUC for the SVM was 0.784 (0.680-0.889), for the KNN, it was 0.720 (0.615-0.825), for the random forest, it was 0.728 (0.622-0.834), and for the LightGBM, it was 0.832 (0.742-0.921). Generally, the LightGBM model performed well in both the training and validation cohorts. From the SHAP results, original_shape_MinorAxisLength,original_shape_Maximum2DDiameterColumn, and wavelet-HHH_glszm_SmallAreaLowGrayLevelEmphasis have the most significant effect on the model. Our combined model based on machine learning and ultrasonic radiomics demonstrate the excellent predictive ability for extrathyroidal extension (ETE) in pediatric PTC.
利用多分类器超声放射组学模型探讨儿童和青少年甲状腺乳头状癌的甲状腺外延伸（ETE）。在这项研究中，回顾性分析了 164 例儿童甲状腺乳头状癌（PTC）患者的数据，并将患者按 7:3 的比例随机分为训练队列（115 例）和验证队列（49 例）。为了从甲状腺超声图像中提取放射组学特征，沿着肿瘤轮廓的边缘逐层勾勒出感兴趣区域（ROI）。然后使用相关系数筛选方法降低特征维度，并使用 Lasso 选择具有非零系数的 16 个特征。然后，在训练队列中，建立了四个有监督的机器学习放射组学模型（k-近邻、随机森林、支持向量机[SVM]和 LightGBM）。利用 ROC 和决策曲线比较模型性能，并用验证队列进行验证。此外，还应用了 SHapley Additive exPlanations（SHAP）框架来解释最优模型。在训练队列中，SVM、KNN、随机森林和 LightGBM 的平均曲线下面积（AUC）分别为 0.880（0.835-0.927）、0.873（0.829-0.916）、0.999（0.999-1.000）和 0.926（0.892-0.926）。在验证队列中，SVM 的 AUC 为 0.784（0.680-0.889），KNN 的 AUC 为 0.720（0.615-0.825），随机森林的 AUC 为 0.728（0.622-0.834），LightGBM 的 AUC 为 0.832（0.742-0.921）。一般来说，LightGBM 模型在训练和验证队列中表现良好。从 SHAP 结果来看，原始形状_MinorAxisLength、原始形状_Maximum2DDiameterColumn 和小波-HHH_glszm_SmallAreaLowGrayLevelEmphasis 对模型的影响最大。我们基于机器学习和超声放射组学的联合模型对儿童 PTC 的甲状腺外延伸（ETE）具有出色的预测能力。
