In Physics in medicine and biology
PURPOSE : Although deep learning technique has been successfully used for CT reconstruction, its implementation on cone-beam CT (CBCT) reconstruction is extremely challenging due to memory limitations. In this study, a novel deep learning technique is developed to resolve the memory issue, and its feasibility is demonstrated for CBCT reconstruction from sparsely sampled projection data.
METHODS : The novel geometry-guided deep learning (GDL) technique is composed of a GDL reconstruction module and a post-processing module. The GDL reconstruction module learns and performs projection-to-image domain transformation by replacing the traditional single fully connected layer with an array of small fully connected layers in the network architecture based on the projection geometry. The deep learning post-processing module further improves image quality after reconstruction. We demonstrated the feasibility and advantage of the model by comparing ground truth CBCT with CBCT images reconstructed using 1) GDL reconstruction module only, 2) GDL reconstruction module with deep learning post-processing module, 3) Feldkamp, Davis, and Kress (FDK) only, 4) FDK with deep learning post-processing module, 5) ray-tracing only, and 6) ray-tracing with deep learning post-processing module. The differences are quantified by peak-signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and root-mean-square error (RMSE).
RESULTS : CBCT images reconstructed with GDL show improvements in quantitative scores of PSNR, SSIM, and RMSE. Reconstruction time per image for all reconstruction methods are comparable. Compared to current deep learning methods using large fully connected layers, the estimated memory requirement using GDL is four orders of magnitude less, making deep learning CBCT reconstruction feasible.
CONCLUSION : With much lower memory requirement compared to other existing networks, the GDL technique is demonstrated to be the first deep learning technique that can rapidly and accurately reconstruct CBCT images from sparsely sampled data.
Lu Ke, Ren Lei, Yin Fang-Fang
CBCT, deep learning, fully connected layer, reconstruction