基于肿瘤及瘤-脑界面纹理特征鉴别胶质母细胞瘤与单发脑转移瘤
本研究回顾性收集2010至2024年间97例胶质母细胞瘤与90例单发脑转移瘤患者的增强T1加权成像数据,利用机器学习基于整个肿瘤及10 mm瘤-脑界面区域的纹理特征建立多个诊断模型,并以5折交叉验证评估。最优模型在测试集中AUC为0.880、准确率为0.824。结论认为联合肿瘤整体与瘤-脑界面的纹理特征模型有助于鉴别胶质母细胞瘤与单发转移瘤,且瘤界面纹理特征表现出更高的异质性。
要点
- 联合整个肿瘤与10 mm瘤-脑界面纹理特征建模,有助于鉴别胶质母细胞瘤与单发脑转移瘤。
- 测试集中KW1LR模型AUC最高,为0.880,准确率为0.824。
- 10mm_glrlm_GrayLevelNonUniformity被认为是稳定性与预测性最好的特征。
核心结论
- 联合肿瘤整体与瘤-脑界面的纹理特征模型有助于鉴别胶质母细胞瘤与单发转移瘤,且瘤界面纹理特征表现出更高的异质性。
研究设计与样本
- 回顾性收集2010至2024年间97例胶质母细胞瘤患者与90例单发脑转移瘤患者的增强T1加权成像数据。
- 基于整个肿瘤及10 mm瘤-脑界面区域的纹理特征,利用机器学习建立多个鉴别胶质母细胞瘤与单发脑转移瘤的诊断模型。
- 采用5折交叉验证评估模型,计算各模型的受试者工作特征曲线下面积(AUC),并用Delong检验比较各模型性能,进一步用Shapley加性解释(SHAP)增强优化模型的可解释性。
诊断标准与关键数值
- 在验证数据集中使用FeAture Explorer(FAE)软件比较所有流程的AUC。
- 在Kruskal-Wallis(KW)与逻辑回归(LR)建立的模型中,采用「一倍标准误」规则时AUC最高。
- 10mm_glrlm_GrayLevelNonUniformity被认为是稳定性与预测性最好的特征。
- 训练集、测试集与验证集中的最佳模型并不相同;测试集中KW1LR模型AUC最高,为0.880,准确率为0.824。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: Texture features, derived from both the entire tumor area and the region of the tumor-to-brain interface, are crucial indicators for distinguishing tumor types and their degrees of malignancy. However, the discriminative value of texture features from both regions for identifying glioblastomas and metastatic tumors has not been thoroughly explored. The aim of this study is to develop and validate a diagnostic model that combines texture features from the entire tumor area and a 10 mm tumor-to-brain interface region, in an attempt to identify more stable and effective texture features.
METHOD: We retrospectively collected enhanced T1-weighted imaging data from 97 patients with glioblastoma (GBM) and 90 patients with single brain metastasis (SBM) between 2010 and 2024. Machine learning is used to establish multiple diagnostic models for discriminating GBM and SBM based on texture features of the entire tumor and 10 mm tumor-to-brain interface regions. Results underwent evaluation through 5-fold cross-validation analysis, calculating the area under the receiver operating characteristic curve (AUC) for each model. The performance of each model was compared using the Delong test, and the interpretability of the optimized model was further augmented by employing Shapley additive explanations (SHAP).
RESULTS: The AUCs for all pipelines in the validation dataset were compared using FeAture Explorer (FAE) software. Among the models established by Kruskal-Wallis(KW) and Logistic Regression(LR), the AUC was highest using the "one-standard error" rule. '10mm_glrlm_GrayLevelNonUniformity' was considered the most stable and predictive feature. The best models in the training set, test set, and validation set were not the same. In the test set, the KW1LR model had the highest AUC of 0.880 and an accuracy of 0.824.
CONCLUSION: The texture feature model that combines the overall tumor and the tumor-brain interface is beneficial for distinguishing glioblastoma from solitary metastatic tumors, and the texture features of the tumor interface exhibit higher heterogeneity.
引用
- Chen Y, Lin H, Sun J, et al. Texture Feature Differentiation of Glioblastoma and Solitary Brain Metastases Based on Tumor and Tumor-brain Interface. Acad Radiol. 2024. PMID: 39217081. doi:10.1016/j.acra.2024.08.025
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。