Department of Radiology, Peking University People's Hospital, 11 Xizhimen Nandajie, Xicheng District, Beijing, 100044, P. R. China.
Department of Research and Development, United Imaging Intelligence (Beijing) Co.,Ltd, Yongteng North Road, Haidian District, Beijing, 100089, China.
BMC Med Imaging. 2023 Mar 23;23(1):40. doi: 10.1186/s12880-023-00991-x.
Osteosarcoma (OS) is the most common primary malignant bone tumor in adolescents. Lung metastasis (LM) occurs in more than half of patients at different stages of the disease course, which is one of the important factors affecting the long-term survival of OS. To develop and validate machine learning radiomics model based on radiographic and clinical features that could predict LM in OS within 3 years.
486 patients (LM = 200, non-LM = 286) with histologically proven OS were retrospectively analyzed and divided into a training set (n = 389) and a validation set (n = 97). Radiographic features and risk factors (sex, age, tumor location, etc.) associated with LM of patients were evaluated. We built eight clinical-radiomics models (k-nearest neighbor [KNN], logistic regression [LR], support vector machine [SVM], random forest [RF], Decision Tree [DT], Gradient Boosting Decision Tree [GBDT], AdaBoost, and extreme gradient boosting [XGBoost]) and compared their performance. The area under the receiver operating characteristic curve (AUC) and accuracy (ACC) were used to evaluate different models.
The radscore, ALP, and tumor size had significant differences between the LM and non-LM groups (t = -5.829, χ = 97.137, t = -3.437, P < 0.01). Multivariable LR analyses showed that ALP was an important indicator for predicting LM of OS (odds ratio [OR] = 7.272, P < 0.001). Among the eight models, the SVM-based clinical-radiomics model had the best performance in the validation set (AUC = 0.807, ACC = 0.784).
The clinical-radiomics model had good performance in predicting LM in OS, which would be helpful in clinical decision-making.
骨肉瘤（OS）是青少年中最常见的原发性恶性骨肿瘤。在疾病的不同阶段，超过一半的患者会发生肺转移（LM），这是影响 OS 长期生存的重要因素之一。本研究旨在开发和验证一种基于影像学和临床特征的机器学习放射组学模型，以预测 OS 患者 3 年内发生 LM 的情况。
回顾性分析了 486 例经组织学证实的 OS 患者（LM=200 例，非 LM=286 例），并将其分为训练集（n=389）和验证集（n=97）。评估与患者 LM 相关的影像学特征和危险因素（性别、年龄、肿瘤位置等）。我们构建了 8 种临床放射组学模型（k-最近邻[KNN]、逻辑回归[LR]、支持向量机[SVM]、随机森林[RF]、决策树[DT]、梯度提升决策树[GBDT]、AdaBoost 和极端梯度提升[XGBoost]），并比较了它们的性能。使用受试者工作特征曲线下面积（AUC）和准确性（ACC）评估不同模型。
LM 组和非 LM 组之间的 radscore、碱性磷酸酶（ALP）和肿瘤大小差异有统计学意义（t=-5.829，χ²=97.137，t=-3.437，P<0.01）。多变量 LR 分析显示，ALP 是预测 OS 患者 LM 的重要指标（比值比[OR]=7.272，P<0.001）。在 8 种模型中，基于 SVM 的临床放射组学模型在验证集的表现最佳（AUC=0.807，ACC=0.784）。
临床放射组学模型在预测 OS 患者 LM 方面具有良好的性能，有助于临床决策。
