Cone-beam CT Iterative Reconstruction And Shading Correction

Cone-beam computed tomography(CBCT)plays an important role in image-guided radiation therapy and the dedicated imaging systems such as the dental imaging and breast imaging due to the high-resolution anatomical structure imaging.Subject to the high cumulative radiation dose and severe shading artifacts caused by non-ideal physical issues,the high-end medical applications of CBCT are constrained.To overcome the above limitations,we propose a shading correction assisted iterative CBCT reconstruction method(SCAIR)and a scheme of shading correction of cone-beam CT using a deep residual convolution neural network(DRCNN),respectively.Recent advances in total variation(TV)technology enable accurate CT image reconstruction from highly under-sampled and noisy projection data.The standard iterative reconstruction algorithms,which work well in conventional CT imaging,fail to perform as expected in CBCT applications,wherein the non-ideal physics issues,including scatter and beam hardening,are more severe.These physics issues result in large areas of shading artifacts and cause deterioration to the piecewise constant property assumed in reconstructed images.To overcome this obstacle,we incorporate a shading correction scheme into low-dose CBCT reconstruction and propose the shading correction assisted three-dimensional iterative reconstruction algorithm.In the proposed method,we modify the TV regularization term by adding a shading compensation image to the reconstructed image to compensate for the shading artifacts while leaving the data fidelity term intact.This compensation image is generated empirically,using image segmentation and low-pass filtering,and updated in the iterative process whenever necessary.When the compensation image is determined,the objective function is minimized using the fast iterative shrinkage-thresholding algorithm accelerated on a graphic processing unit.The proposed method is evaluated using CBCT projection data of the Catphan(?)600 phantom and three pelvis patients.Compared with the iterative reconstruction without shading correction,the proposed method reduces the overall CT number error from around 200 HU to be around 25 HU and increases the spatial uniformity by a factor of 20 percent,given the same number of sparsely sampled projections.A clinically acceptable and stable iterative reconstruction algorithm for CBCT is proposed in this paper.Although the different shading correction methods have been proposed in literature,a standard solution is still being studied due to the limitations including accuracy,computation efficiency and generalization.In this paper,we further propose the DRCNN to overcome the limitations.The proposed method combines the deep convolution neural network and the residual learning framework to train the mapping function from the uncorrected image to the corrected image.Two residual network modules are built based on the residual learning framework to improve the accuracy of the mapping function by strengthening the propagation of the gradient.Compared with the uncorrected image,the RMSE of the corrected images reconstructed using the DRCNN is reduced from over 200 HU to be about 20 HU.The structural similarity is slightly increased from 0.95 to 0.99,indicating that the proposed scheme maintains the anatomical structure.The proposed network is effective,efficient and robust as a solution to the CBCT shading correction.