11 / 2021-08-27 20:33:15

Four-Dimensional Cone Beam CT Imaging Using A Single Routine Scan via Deep Learning

4D cone beam CT,deep learning,motion compensation,Generative Adversarial Networks

We propose a novel method to obtain four-dimensional (4D) cone-beam computed tomography (CBCT) images from a routine scan in patients with upper abdominal cancer. The projections are sorted according to the location of the lung diaphragm before being reconstructed to phase-sorted data. A multiscale-discriminator generative adversarial network (MSD-GAN) is proposed to alleviate the severe streaking artifacts in the original images. The MSD-GAN is trained using simulated CBCT datasets from patient planning CT images. The enhanced images are further used to estimate the deformable vector field (DVF) among breathing phases using the deformable image registration method. The estimated DVF is then applied in the motion-compensated ordered-subset simultaneous algebraic reconstruction approach to generate 4D CBCT images. The proposed MSD-GAN is compared with U-Net on the performance of image enhancement. Results show that our method significantly outperforms the total variation (TV) regularization based and MSD-GAN only methods in simulation and patient studies on 4D reconstruction quality. In the region of interest (ROI) on the liver region, the root-mean-square error (RMSE) between the CBCT images using the TV-based method and the ground-true image is 98.98 HU while it reduces to 61.63 HU using the proposed method. Compared with the TV-based method, the RMSE in ROI-2 and ROI-3 reduces from 122.14 HU to 72.09 HU and from 101.34 HU to 53.84 HU, respectively. The MSD-GAN also shows higher accuracy than the U-Net. The proposed method enables a practical way for 4D-CBCT imaging from a single routine scan in upper abdominal cancer treatment.