Search for: All records

Imaging through scattering is a pervasive and difficult problem in many biological applications. The high background and the exponentially attenuated target signals due to scattering fundamentally limits the imaging depth of fluorescence microscopy. Light-field systems are favorable for high-speed volumetric imaging, but the 2D-to-3D reconstruction is fundamentally ill-posed, and scattering exacerbates the condition of the inverse problem. Here, we develop a scattering simulator that models low-contrast target signals buried in heterogeneous strong background. We then train a deep neural network solely on synthetic data to descatter and reconstruct a 3D volume from a single-shot light-field measurement with low signal-to-background ratio (SBR). We apply this network to our previously developed computational miniature mesoscope and demonstrate the robustness of our deep learning algorithm on scattering phantoms with different scattering conditions. The network can robustly reconstruct emitters in 3D with a 2D measurement of SBR as low as 1.05 and as deep as a scattering length. We analyze fundamental tradeoffs based on network design factors and out-of-distribution data that affect the deep learning model’s generalizability to real experimental data. Broadly, we believe that our simulator-based deep learning approach can be applied to a wide range of imaging through scattering techniques where experimental paired training data is lacking.

 

Abstract Digital light processing (DLP)-based three-dimensional (3D) printing technology has the advantages of speed and precision comparing with other 3D printing technologies like extrusion-based 3D printing. Therefore, it is a promising biomaterial fabrication technique for tissue engineering and regenerative medicine. When printing cell-laden biomaterials, one challenge of DLP-based bioprinting is the light scattering effect of the cells in the bioink, and therefore induce unpredictable effects on the photopolymerization process. In consequence, the DLP-based bioprinting requires extra trial-and-error efforts for parameters optimization for each specific printable structure to compensate the scattering effects induced by cells, which is often difficult and time-consuming for a machine operator. Such trial-and-error style optimization for each different structure is also very wasteful for those expensive biomaterials and cell lines. Here, we use machine learning to learn from a few trial sample printings and automatically provide printer the optimal parameters to compensate the cell-induced scattering effects. We employ a deep learning method with a learning-based data augmentation which only requires a small amount of training data. After learning from the data, the algorithm can automatically generate the printer parameters to compensate the scattering effects. Our method shows strong improvement in the intra-layer printing resolution for bioprinting, which can be further extended to solve the light scattering problems in multilayer 3D bioprinting processes. 

Abstract When using light-based three-dimensional (3D) printing methods to fabricate functional micro-devices, unwanted light scattering during the printing process is a significant challenge to achieve high-resolution fabrication. We report the use of a deep neural network (NN)-based machine learning (ML) technique to mitigate the scattering effect, where our NN was employed to study the highly sophisticated relationship between the input digital masks and their corresponding output 3D printed structures. Furthermore, the NN was used to model an inverse 3D printing process, where it took desired printed structures as inputs and subsequently generated grayscale digital masks that optimized the light exposure dose according to the desired structures’ local features. Verification results showed that using NN-generated digital masks yielded significant improvements in printing fidelity when compared with using masks identical to the desired structures.