Slice-wise reconstruction for low-dose cone-beam CT using a deep residual convolutional neural network

Because of the growing concern over the radiation dose delivered to patients, X-ray cone-beam CT(CBCT) imaging of low dose is of great interest. It is difficult for traditional reconstruction methods such as Feldkamp to reduce noise and keep resolution at low doses. A typical method to solve this problem is using optimizationbased methods with careful modeling of physics and additional constraints. However, it is computationally expensive and very time-consuming to reach an optimal solution. Recently, some pioneering work applying deep neural networks had some success in characterizing and removing artifacts from a low-dose data set. In this study,we incorporate imaging physics for a cone-beam CT into a residual convolutional neural network and propose a new end-to-end deep learning-based method for slice-wise reconstruction. By transferring 3D projection to a 2D problem with a noise reduction property, we can not only obtain reconstructions of high image quality, but also lower the computational complexity. The proposed network is composed of three serially connected sub-networks: a cone-to-fan transformation sub-network, a 2D analytical inversion sub-network, and an image refinement sub-network. This provides a comprehensive solution for end-to-end reconstruction for CBCT. The advantages of our method are that the network can simplify a 3D reconstruction problem to a 2D slice-wise reconstruction problem and can complete reconstruction in an end-to-end manner with the system matrix integrated into the network design. Furthermore, reconstruction can be less computationally expensive and easily parallelizable compared with iterative reconstruction methods.

Searching for^(76)Ge neutrinoless double beta decay with the CDEX-1B experiment

We operated a p-type point contact high purity germanium(PPCGe)detector(CDEX-1B,1.008 kg)in the China Jinping Underground Laboratory(CJPL)for 500.3 days to search for neutrinoless double beta(0νββ)decay of^(76)Ge.A total of 504.3 kg⋅day effective exposure data was accumulated.The anti-coincidence and the multi/single-site event(MSE/SSE)discrimination methods were used to suppress the background in the energy region of interest(ROI,1989–2089 keV for this work)with a factor of 23.A background level of 0.33 counts/(keV⋅kg⋅yr)was realized.The lower limit on the half life of^(76)Ge 0νββdecay was constrained as T_(1/2)^(0ν)>1.0×10^(23)yr(90%C.L.),corresponding to the upper limits on the effective Majorana neutrino mass:<mββ><3.2–7.5 eV.

Introduction to the CDEX experiment

It is believed that weakly interacting massive particles （WIMPs） are candidates for dark matter （DM） in our universe which come from outer space and might interact with the standard model （SM） matter of our detectors on the earth. Many collaborations in the world are carrying out various experiments to directly detect DM particles. China Jinping underground Laboratory （CJPL） is the deepest underground laboratory in the world and provides a very promising environment for DM search. China Dark matter EXperiment （CDEX） is going to directly detect the WIMP flux with high sensitivity in the low WIMP-mass region. Both CJPL and CDEX have achieved a remarkable progress in recent three years. CDEX employs a point-contact germanium （PCGe） semi-conductor detector whose energy threshold is less than 300 eV. In this report we present the measurement results of muon flux, monitoring of radioactivity and radon concentration carried out in CJPL, as well describing the structure and performance of the 1 kg-PCGe detector in CDEX-1 and 10 kg- PCGe detector array in CDEX-10 including the detectors, electronics, shielding and cooling systems. Finally we discuss the physics goals of CDEX-1, CDEX-10 and the future CDEX-1T experiments.