Two-stage deep learning method for sparse-view fluorescence molecular tomography reconstruction.

Fluorescence molecular tomography (FMT) is a preclinical optical tomographic imaging technique that can trace various physiological and pathological processes at the cellular or even molecular level. Reducing the number of FMT projection views can improve the data acquisition speed, which is significant in applications such as dynamic problems. However, a reduction in the number of projection views will dramatically aggravate the ill-posedness of the FMT inverse problem and lead to significant degradation of the reconstructed images. To deal with this problem, we have proposed a deep-learning-based reconstruction method for sparse-view FMT that only uses four perpendicular projection views and divides the image reconstruction into two stages: image restoration and inverse Radon transform. In the first stage, the projection views of the surface fluorescence are restored to eliminate the blur derived from photon diffusion through a fully convolutional neural network. In the second stage, another convolutional neural network is used to implement the inverse Radon transform between the restored projections from the first stage and the reconstructed transverse slices. Numerical simulation and phantom and mouse experiments are carried out. The results show that the proposed method can effectively deal with the image reconstruction problem of sparse-view FMT.

Image restoration for blurry optical images caused by photon diffusion with deep learning.

Optical macroscopic imaging techniques have shown great significance in the investigations of biomedical issues by revealing structural or functional information of living bodies through the detection of visible or near-infrared light derived from different mechanisms. However, optical macroscopic imaging techniques suffer from poor spatial resolution due to photon diffusion in biological tissues. This dramatically restricts the application of optical imaging techniques in numerous situations. In this paper, an image restoration method based on deep learning is proposed to eliminate the blur caused by photon diffusion in optical macroscopic imaging. Two blurry images captured at orthogonal angles are used as the additional information to ensure the uniqueness of the solution and restore the small targets at deep locations. Then a fully convolutional neural network is proposed to accomplish the image restoration, which consists of three sectors: V-shaped network for central view, V-shaped network for side views, and synthetical path. The two V-shaped networks are concatenated to the synthetical path with skip connections to generate the output image. Simulations as well as phantom and mouse experiments are implemented. Results indicate the effectiveness of the proposed method.