Is high sensitivity always desirable for a grating-based differential phase contrast imaging system?

Grating-free quantitative phase retrieval for x-ray phase-contrast imaging with conventional sources

X-ray phase-contrast imaging can display subtle differences in low-density materials (e.g., soft tissues) more readily than conventional x-ray imaging. However, producing x-ray phase images requires significant spatial coherence of the beam which requires highly specialized sources such as synchrotrons, small and low power microfocus sources, or complex procedures, such as multiple exposures with several carefully stepped precision gratings. To find appropriate approaches for producing x-ray phase-contrast imaging in a clinically meaningful way, we employed a grating-free method that utilized a low-cost, coarse wire mesh and simple processing. This method relaxes the spatial coherence constraint and allows quantitative phase retrieval for not only monochromatic but also polychromatic beams. We also combined the mesh-based system with polycapillary optics to significantly improve the accuracy of quantitative phase retrieval.

Enhancing the X-Ray Differential Phase Contrast Image Quality With Deep Learning Technique

OBJECTIVE

The purpose of this work is to investigate the feasibility of using deep convolutional neural network (CNN) to improve the image quality of a grating-based X-ray differential phase contrast imaging (XPCI) system.

METHODS

In this work, a novel deep CNN based phase signal extraction and image noise suppression algorithm (named as XP-NET) is developed. The numerical phase phantom, the ex vivo biological specimen and the ACR breast phantom are evaluated via the numerical simulations and experimental studies, separately. Moreover, images are also evaluated under different low radiation levels to verify its dose reduction capability.

RESULTS

Compared with the conventional analytical method, the novel XP-NET algorithm is able to reduce the bias of large DPC signals and hence increasing the DPC signal accuracy by more than 15%. Additionally, the XP-NET is able to reduce DPC image noise by about 50% for low dose DPC imaging tasks.

CONCLUSION

This proposed novel end-to-end supervised XP-NET has a great potential to improve the DPC signal accuracy, reduce image noise, and preserve object details.

SIGNIFICANCE

We demonstrate that the deep CNN technique provides a promising approach to improve the grating-based XPCI performance and its dose efficiency in future biomedical applications.