Deep learning based de-overlapping correction of projections from a flat-panel micro array X-ray source: Simulation study

Purpose: Flat-panel X-ray source is an experimental X-ray emitter with target application of static computer tomography (CT), which can save imaging space and time. However, the X-ray cone beams emitted by the densely arranged micro-ray sources are overlapped, causing serious structural overlapping and visual blur in the projection results. Traditional deoverlapping methods can hardly solve this problem well. Method: We converted the overlapping cone beam projections to parallel beam projections through a U-like neural network and selected structural similarity (SSIM) loss as the loss function. In this study, we converted three kinds of overlapping cone beam projections of the Shepp-Logan, line-pairs, and abdominal data with two overlapping levels to corresponding parallel beam projections. Training completed, we tested the model using the test set data that was not used at the training phase, and evaluated the difference between the test set conversion results and their corresponding parallel beams through three indicators: mean squared error (MSE), peak signal-to-noise ratio (PSNR) and SSIM. In addition, projections from head phantoms were applied for generalization test. Result: In the Shepp-Logan low-overlapping task, we obtained a MSE of 1.624x10-5, a PSNR of 47.892 dB, and a SSIM of 0.998 which are the best results of the six experiments. For the most challenging abdominal task, the MSE, PSNR, and SSIM are 1.563x10- 3, 28.0586 dB, and 0.983, respectively. In more generalized data, the model also achieved good results. Conclusion: This study proves the feasibility of utilizing the end-to-end U-net for deblurring and deoverlapping in the flat-panel X-ray source domain.

Automated summary

This study demonstrates the feasibility of using an end-to-end U-net for deblurring and deoverlapping in the flat-panel X-ray source domain. The neural network successfully converts overlapping cone beam projections to parallel beam projections, and the resulting images have high structural similarity to the original parallel beams. The model achieves excellent performance on different tasks and shows good generalization ability.