Accelerated Stimulated Raman Projection Tomography by Sparse Reconstruction From Sparse-View Data

Tilt-angle stimulated Raman projection tomography

Stimulated Raman projection tomography is a label-free volumetric chemical imaging technology allowing three-dimensional (3D) reconstruction of chemical distribution in a biological sample from the angle-dependent stimulated Raman scattering projection images. However, the projection image acquisition process requires rotating the sample contained in a capillary glass held by a complicated sample rotation stage, limiting the volumetric imaging speed, and inhibiting the study of living samples. Here, we report a tilt-angle stimulated Raman projection tomography (TSPRT) system which acquires angle-dependent projection images by utilizing tilt-angle beams to image the sample from different azimuth angles sequentially. The TSRPT system, which is free of sample rotation, enables rapid scanning of different views by a tailor-designed four-galvo-mirror scanning system. We present the design of the optical system, the theory, and calibration procedure for chemical tomographic reconstruction. 3D vibrational images of polystyrene beads and C. elegans are demonstrated in the C-H vibrational region.

Two-stage deep learning network-based few-view image reconstruction for parallel-beam projection tomography

BACKGROUND

Projection tomography (PT) is a very important and valuable method for fast volumetric imaging with isotropic spatial resolution. Sparse-view or limited-angle reconstruction-based PT can greatly reduce data acquisition time, lower radiation doses, and simplify sample fixation modes. However, few techniques can currently achieve image reconstruction based on few-view projection data, which is especially important for in vivo PT in living organisms.

METHODS

A 2-stage deep learning network (TSDLN)-based framework was proposed for parallel-beam PT reconstructions using few-view projections. The framework is composed of a reconstruction network (R-net) and a correction network (C-net). The R-net is a generative adversarial network (GAN) used to complete image information with direct back-projection (BP) of a sparse signal, bringing the reconstructed image close to reconstruction results obtained from fully projected data. The C-net is a U-net array that denoises the compensation result to obtain a high-quality reconstructed image.

RESULTS

The accuracy and feasibility of the proposed TSDLN-based framework in few-view projection-based reconstruction were first evaluated with simulations, using images from the DeepLesion public dataset. The framework exhibited better reconstruction performance than traditional analytic reconstruction algorithms and iterative algorithms, especially in cases using sparse-view projection images. For example, with as few as two projections, the TSDLN-based framework reconstructed high-quality images very close to the original image, with structural similarities greater than 0.8. By using previously acquired optical PT (OPT) data in the TSDLN-based framework trained on computed tomography (CT) data, we further exemplified the migration capabilities of the TSDLN-based framework. The results showed that when the number of projections was reduced to 5, the contours and distribution information of the samples in question could still be seen in the reconstructed images.

CONCLUSIONS

The simulations and experimental results showed that the TSDLN-based framework has strong reconstruction abilities using few-view projection images, and has great potential in the application of in vivo PT.