Development of an Unpaired Deep Neural Network for Synthesizing X-ray Fluoroscopic Images from Digitally Reconstructed Tomography in Image Guided Radiotherapy

Purpose The purpose of this study was to develop and evaluate a deep neural network (DNN) capable of generating flat-panel detector (FPD) images from digitally reconstructed radiography (DRR) images in lung cancer treatment, with the aim of improving clinical workflows in image-guided radiotherapy. Methods A modified CycleGAN architecture was trained on paired DRR-FPD image data obtained from patients with lung tumors. The training dataset consisted of over 400 DRR-FPD image pairs, and the final model was evaluated on an independent set of 100 FPD images. Mean absolute error (MAE), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and Kernel Inception Distance (KID) were used to quantify the similarity between synthetic and ground-truth FPD images. Computation time for generating synthetic images was also measured. Results Despite some positional mismatches in the DRR-FPD pairs, the synthetic FPD images closely resembled the ground-truth FPD images. The proposed DNN achieved notable improvements over both input DRR images and a U-Net-based method in terms of MAE, PSNR, SSIM, and KID. The average image generation time was on the order of milliseconds per image, indicating its potential for real-time application. Qualitative evaluations showed that the DNN successfully reproduced image noise patterns akin to real FPD images, reducing the need for manual noise adjustments. Conclusions The proposed DNN effectively converted DRR images into realistic FPD images for thoracic cases, offering a fast and practical method that could streamline patient setup verification and enhance overall clinical workflow. Future work should validate the model across different imaging systems and address remaining challenges in marker visualization, thereby fostering broader clinical adoption.