A neural network model to predict lung radiation-induced pneumonitis
A neural network model to predict lung radiation-induced pneumonitis
复制标题
DOI：
10.1118/1.2759601
复制
发表时间：
2007-09-01
期刊：
影响因子：
3.8
通讯作者：
Das, Shiva K.
中科院分区：
文献类型：
--
作者：
Chen, Shifeng;Zhou, Sumin;Das, Shiva K.
研究了前馈神经网络预测肺辐射诱导的2+级肺炎的发生。该数据库包括235例接受放疗的肺癌患者，其中34例在随访时诊断为2+级肺炎。网络的构造采用了一种算法，该算法从最小的网络开始交替生长和修剪，直到找到满意的解。为了加快收敛速度，采用了动量和变量学习技术。使用生长/修剪方法，网络从66个剂量和27个非剂量变量中选择特征。在网络训练过程中，235名患者被随机分为10组，每组人数大致相等。八组用于训练网络，一组用于提前停止训练以防止过拟合，其余一组用作测试以测量网络的泛化能力（交叉验证）。使用这种方法，10个组中的每一个依次被认为是测试组（10倍交叉验证）。对于使用从剂量和非剂量变量中选择的输入特征构建的优化网络，交叉验证检验的受试者工作特征（ROC）曲线下面积为0.76（灵敏度：0.68，特异性：0.69）。对于仅从剂量变量中选择的输入特征构建的优化网络，交叉验证的ROC曲线下面积为0.67（灵敏度：0.53，特异性：0.69）。这两个区域之间的差异具有统计学意义（p=0.020），表明添加非剂量特征可以显著提高网络的泛化能力。使用从剂量和非剂量变量中选择的输入特征构建前瞻性测试网络（所有数据均用于训练）。优化后的网络结构由6个输入节点（特征）、4个隐藏节点和1个输出节点组成。这六个输入功能是：接受>16戈伊的肺容量（V-16）、指数a= I的广义等效均匀剂量（gEUD）（平均肺剂量）、指数a= 3.5的gEUD、1秒内的自由呼气量（FEV 1）、一氧化碳弥散量（DLCO%）以及患者在放疗前是否接受化疗。通过在网络训练期间忽略每个输入特征并通过交叉验证的ROC区域中随之发生的恶化来衡量其影响，从而单独评估每个输入特征的重要性。除了FEV 1和患者在放疗前是否接受化疗外，所有输入特征均具有个体显著性（p < 0.05）。前瞻性测试网络可通过互联网访问公开提供。(c)2007年美国医学物理学家协会。
A feed-forward neural network was investigated to predict the occurrence of lung radiation-induced Grade 2+ pneumonitis. The database consisted of 235 patients with lung cancer treated using radiotherapy, of whom 34 were diagnosed with Grade 2+ pneumonitis at follow-up. The network was constructed using an algorithm that alternately grew and pruned it, starting from the smallest possible network, until a satisfactory solution was found. The weights and biases of the network were computed using the error back-propagation approach. Momentum and variable leaning techniques were used,to speed convergence. Using the growing/pruning approach, the network selected features from 66 dose and 27 non-dose variables. During network training, the 235 patients were randomly split into ten groups of approximately equal size. Eight groups were used to train the network, one group was used for early stopping training to prevent overfitting, and the remaining group was used as a test to measure the generalization capability of the network (cross-validation). Using this methodology, each of the ten groups was considered, in turn, as the test group (ten-fold cross-validation). For the optimized network constructed with input features selected from dose and non-dose variables, the area under the receiver operating characteristics (ROC) curve for cross-validated testing was 0.76 (sensitivity: 0.68, specificity: 0.69). For the optimized network constructed with input features selected only from dose variables, the area under the ROC curve for cross-validation was 0.67 (sensitivity: 0.53, specificity: 0.69). The difference between these two areas was statistically significant (p=0.020), indicating that the addition of non-dose features can significantly improve the generalization capability of the network. A network for prospective testing was constructed with input features selected from dose and non-dose variables (all data were used for training). The optimized network architecture consisted of six input nodes (features), four hidden nodes, and one output node. The six input features were: lung volume receiving >16 Gy (V-16), generalized equivalent uniform dose (gEUD) for the exponent a= I (mean lung dose), gEUD for the exponent a= 3.5, free expiratory volume in, 1 s (FEV1), diffusion capacity of carbon monoxide (DLCO%), and whether or not the patient underwent chemotherapy prior to radiotherapy. The significance of each input feature was individually evaluated by omitting it during network training and gauging its impact by the consequent deterioration in cross-validated ROC area. With the , exception of FEV1 and whether or not the patient underwent chemotherapy prior to radiotherapy, all input features were found to be individually significant (p < 0.05). The network for prospective testing is publicly available via internet access. (c) 2007 American Association of Physicists in Medicine.