Predicting radiation pneumonitis with fuzzy clustering neural network using 4DCT ventilation image based dosimetric parameters
Predicting radiation pneumonitis with fuzzy clustering neural network using 4DCT ventilation image based dosimetric parameters
复制标题
使用基于 4DCT 通气图像的剂量学参数，通过模糊聚类神经网络预测放射性肺炎
DOI：
10.21037/qims-20-1095
复制
发表时间：
2021-12-01
影响因子：
2.8
通讯作者：
Dai, Jianrong
中科院分区：
文献类型：
--
作者：
Huang, Peng;Yan, Hui;Dai, Jianrong
背景：利用基于四维CT(4DCT)通风图像(VI)的剂量学参数建立模糊聚类神经网络来预测胸癌患者放射性肺炎(RP)。方法：采用可变形图像配准(DIR)和改进VI算法对治疗前的4DCT数据进行回顾性计算。与调强放射治疗(IMRT)的剂量-体积直方图(DVH)类似，剂量-功能直方图(DFH)由剂量分布和VI得到，然后由DFH计算出剂量-功能指标。为了进行比较，剂量-体积指标是根据DVH计算的。相应地，由剂量-体积度量和剂量-函数度量分别形成两组特征向量。对于每个集合的特征向量，首先对它们进行主成分分析(PCA)预处理，以降低特征维度。然后，用模糊c-均值(FCM)算法将它们分成几个聚类。然后，训练神经网络，根据每个簇的特征向量将剂量学参数与RP关联起来。结果：通过主成分分析，选出了最主要的5个主成分。它们的贡献率超过98%，足以表示输入数据的原始特征空间。基于聚类有效性指标，最优聚类个数为4，并用于输入数据的后续模糊聚类。网络训练后，基于VI的剂量学参数预测模型的曲线下面积(AUC)为0.77，基于结构的剂量学参数预测模型的曲线下面积(AUC)为0.67。结论：与基于结构的剂量学特征相比，基于VI的剂量学特征与肺功能的相关性更强，具有更高的Rp预测精度。与传统神经网络相比，模糊聚类神经网络提高了快速成形的预测精度。基于VI的剂量-函数度量和模糊聚类神经网络的结合为评估放射治疗后肺毒性风险提供了一个有效的预测模型。
Background: To develop a fuzzy clustering neural network to predict radiation-induced pneumonitis (RP) using four-dimensional computed tomography (4DCT) ventilation image (VI) based dosimetric parameters for thoracic cancer patients.Methods: The VI were retrospectively calculated from pre-treatment 4DCT data using a deformable image registration (DIR) and an improved VI algorithm. Similar to dose-volume histogram (DVH) of intensity modulated radiotherapy (IMRT), dose-function histogram (DFH) was derived from dose distribution and VI. Then, the dose-function metrics were calculated from DFH. For comparison, the dose-volume metrics were calculated from DVH. Correspondingly, two sets of feature vectors were formed from the dose-volume metrics and the dose-function metrics, respectively. For the feature vectors of each set, they were first preprocessed by principal component analysis (PCA) to reduce feature dimensions. Then, they were grouped to few clusters determined by fuzzy c-means (FCM) algorithm. Next, the neural network was trained to correlate the dosimetric parameters with RP based on the feature vectors of each cluster. Finally, the occurrence of RP was predicted by the neural network on the test data.Results: Through PCA analysis, the top 5 principal components were selected. Their contribution is more than 98%, which is adequate to represent the original feature space of input data. Based on the clustering validity indexes, the optimal number of clusters is 4 and used for subsequent fuzzy clustering of the input data. After network training, the areas under the curve (AUC) of the prediction model is 0.77 using VI-based dosimetric parameters and 0.67 using structure-based dosimetric parameters.Conclusions: Compared to the structure-based dosimetric features, the VI-based dosimetric features are more relevant to lung function and presented higher prediction accuracy of RP. The fuzzy clustering neural network improved the prediction accuracy of RP compared to the conventional neural network. The combination of VI-based dose-function metrics and fuzzy clustering neural network provides an effective predictive model for assessing lung toxicity risk after radiotherapy.