Du Richard, Lee Victor H, Yuan Hui, Lam Ka-On, Pang Herbert H, Chen Yu, Lam Edmund Y, Khong Pek-Lan, Lee Anne W, Kwong Dora L, Vardhanabhuti Varut
Departments of Diagnostic Radiology (R.D., H.Y., P.L.K., V.V.) and Clinical Oncology (V.H.L., K.O.L., A.W.L., D.L.K.) and the School of Public Health (H.H.P.), Li Ka Shing Faculty of Medicine, The University of Hong Kong, Room 406, Block K, Queen Mary Hospital, Pok Fu Lam Road, Hong Kong SAR; Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Beijing, China (Y.C.); and Department of Electrical and Electronic Engineering, Faculty of Engineering, The University of Hong Kong, Hong Kong SAR (E.Y.L.).
Radiol Artif Intell. 2019 Jul 10;1(4):e180075. doi: 10.1148/ryai.2019180075. eCollection 2019 Jul.
To examine the prognostic value of a machine learning model trained with pretreatment MRI radiomic features in the assessment of patients with nonmetastatic nasopharyngeal carcinoma (NPC) who are at risk for 3-year disease progression after intensity-modulated radiation therapy and to explain the radiomics features in the model.
A total of 277 patients with nonmetastatic NPC admitted between March 2008 and December 2014 at two imaging centers were retrospectively reviewed. Patients were allocated to a discovery or validation cohort based on where they underwent MRI (discovery cohort, = 217; validation cohort, = 60). A total of 525 radiomics features extracted from contrast material-enhanced T1- or T2-weighted MRI studies and five clinical features were subjected to radiomic machine learning modeling to predict 3-year disease progression. Feature selection was performed by analyzing robustness to resampling, reproducibility between observers, and redundancy. Features for the final model were selected with Kaplan-Meier analysis and the log-rank test. A support vector machine was used as the classifier for the model. To interpret the pattern learned from the model, Shapley additive explanations (SHAP) was applied.
The final model yielded an area under the receiver operating characteristic curve of 0.80 in both the discovery (95% bootstrap confidence interval: 0.80, 0.81) and independent validation (95% bootstrap confidence interval: 0.73, 0.89) cohorts. Analysis with SHAP revealed that tumor shape sphericity, first-order mean absolute deviation, T stage, and overall stage were important factors in 3-year disease progression.
These results add to the growing evidence of the role of radiomics in the assessment of NPC. By using explanatory techniques, such as SHAP, the complex interaction of features learned by the model may be understood.© RSNA, 2019
研究利用治疗前MRI影像组学特征训练的机器学习模型在评估接受调强放射治疗后有3年疾病进展风险的非转移性鼻咽癌（NPC）患者中的预后价值，并解释模型中的影像组学特征。
回顾性分析2008年3月至2014年12月期间在两个影像中心收治的277例非转移性NPC患者。根据患者接受MRI检查的地点将其分为发现队列或验证队列（发现队列，n = 217；验证队列，n = 60）。从对比剂增强T1加权或T2加权MRI研究中提取的525个影像组学特征和5个临床特征用于影像组学机器学习建模，以预测3年疾病进展。通过分析对重采样的稳健性、观察者之间的可重复性和冗余性进行特征选择。最终模型的特征通过Kaplan-Meier分析和对数秩检验进行选择。使用支持向量机作为模型的分类器。为了解释从模型中学到的模式，应用了Shapley加性解释（SHAP）。
最终模型在发现队列（95%自抽样置信区间：0.80，0.81）和独立验证队列（95%自抽样置信区间：0.73，0.89）中的受试者操作特征曲线下面积均为0.80。SHAP分析显示，肿瘤形状球形度、一阶平均绝对偏差、T分期和总分期是3年疾病进展的重要因素。
这些结果进一步证明了影像组学在NPC评估中的作用。通过使用SHAP等解释技术，可以理解模型学到的特征之间的复杂相互作用。©RSNA，2019
