A deep learning-based dual-omics prediction model for radiation pneumonitis

PURPOSE Radiation pneumonitis (RP) is the main source of toxicity in thoracic radiotherapy. This study proposed a deep learning-based dual-omics model, which aims to improve the RP prediction performance by integrating more data points and exploring the data in greater depth. MATERIALS AND METHODS The bimodality data were the original dose (OD) distribution and the ventilation image (VI) derived from four-dimensional computed tomography (4DCT). The functional dose (FD) distribution was obtained by weighting OD with VI. A pre-trained three-dimensional convolution (C3D) network was used to extract the features from FD, VI, and OD. The extracted features were then filtered and selected using entropy-based methods. The prediction models were constructed with four most commonly used binary classifiers. Cross-validation, bootstrap, and nested sampling methods were adopted in the process of training and hyper-tuning. RESULTS Data from 217 thoracic cancer patients treated with radiotherapy were used to train and validate the prediction model. The 4DCT-based VI showed the inhomogeneous pulmonary function of the lungs. More than half of the extracted features were singular (of none-zero value for few patients), which were eliminated to improve the stability of the model. The area under curve (AUC) of the dual-omics model was 0.874 (95% confidence interval: 0.871-0.877), and the AUC of the single-omics model was 0.780 (0.775-0.785, VI) and 0.810 (0.804-0.811, OD), respectively. CONCLUSIONS The dual-omics outperformed single-omics for RP prediction, which can be contributed to: (1) using more data points; (2) exploring the data in greater depth; and (3) incorporating of the bimodality data.