Predicting radiation pneumonitis with fuzzy clustering neural network using 4DCT ventilation image based dosimetric parameters

Abstract

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.

Combining autoencoder with clustering analysis for anomaly detection in radiotherapy plans

“…If a point is found with the bestimproved value of distortion function, the new data point will replace the current best data point. These newly generated best data points form the new medoids (40)(41)(42).…”

Analysis of deep inspiration breath-hold technique to improve dosimetric and clinical advantages in postoperative intensity-modulated radiation therapy for thymomas

“…RP is a well-known complication in thoracic radiotherapy. Several studies have investigated the predictive dosimetric factors for RP risk during thoracic radiotherapy (21)(22)(23)(24). For treatment-related pneumonitis, the classic predictors considered are V5, V20, and the mean lung dose (22)(23)(24).…”

Improved Fuzzy C-Means Clustering Algorithm-Based Dynamic Contrast-Enhanced Magnetic Resonance Imaging Features in the Diagnosis of Invasive Breast Carcinoma before and after Menopause

“…Fuzzy theory possesses significant advantage in dealing with uncertain problems [ 18 ]. FCM algorithm is an unsupervised image segmentation method widely applied in image segmentation [ 19 , 20 ], and it is characterized by high sensitivity as well as accuracy and wide application in medical field. Joloudari et al [ 21 ] applied FCM deep neural network (FCM-DNN) in cardiac magnetic resonance CAD imaging dataset and found out that the accuracy of the proposed FCM-DNN model reached 99.91%, which indicated that the model achieved the optimal performance.…”