A deep learning reconstruction framework for low dose phase contrast via inter-contrast enhancement

Phase contrast computed tomography (PCCT) offers excellent imaging contrast on soft tissue while it generate absorption, phase and dark-field contrast tomographic images. It has shown a great potential in clinical diagnosis. However, existing PCCT methods require high radiation doses. Reducing tube current is a universal low dose approach while it will introduce quantum noise in projections. In this paper, we report a deep learning (DL) framework for low dose PCCT based on inter-contrast enhancement. It utilizes the multi-contrast feature of PCCT and the varying effects of noise on each contrast. The missing structure in the contrasts that are more affected by noise can be recovered by those that are less affected. Considering the grating-based PCCT as example, the proposed framework is validated with experiments and a dramatic quality improvement of multi-contrast tomographic images has been obtained. This study shows potential of DL techniques in the field of low dose PCCT.

Automated summary

Phase contrast computed tomography (PCCT) provides excellent imaging contrast on soft tissue by generating absorption, phase and dark-field contrast tomographic images, showing great potential in clinical diagnosis. However, existing PCCT methods require high radiation doses. This paper proposes a deep learning (DL) framework for low dose PCCT based on inter-contrast enhancement, utilizing the multi-contrast feature of PCCT and the varying effects of noise on each contrast. Experimental validation on grating-based PCCT demonstrates a significant quality improvement of multi-contrast tomographic images, indicating the potential of DL techniques in low dose PCCT.