Search for: All records

Recovering 3D phase features of complex biological samples traditionally sacrifices computational efficiency and processing time for physical model accuracy and reconstruction quality. Here, we overcome this challenge using an approximant-guided deep learning framework in a high-speed intensity diffraction tomography system. Applying a physics model simulator-based learning strategy trained entirely on natural image datasets, we show our network can robustly reconstruct complex 3D biological samples. To achieve highly efficient training and prediction, we implement a lightweight 2D network structure that utilizes a multi-channel input for encoding the axial information. We demonstrate this framework on experimental measurements of weakly scattering epithelial buccal cells and strongly scatteringC. elegansworms. We benchmark the network’s performance against a state-of-the-art multiple-scattering model-based iterative reconstruction algorithm. We highlight the network’s robustness by reconstructing dynamic samples from a living worm video. We further emphasize the network’s generalization capabilities by recovering algae samples imaged from different experimental setups. To assess the prediction quality, we develop a quantitative evaluation metric to show that our predictions are consistent with both multiple-scattering physics and experimental measurements.

We propose a novel intensity diffraction tomography (IDT) reconstruction algorithm based on the split-step non-paraxial (SSNP) model for recovering the 3D refractive index (RI) distribution of multiple-scattering biological samples. High-quality IDT reconstruction requires high-angle illumination to encode both low- and high- spatial frequency information of the 3D biological sample. We show that our SSNP model can more accurately compute multiple scattering from high-angle illumination compared to paraxial approximation-based multiple-scattering models. We apply this SSNP model to both sequential and multiplexed IDT techniques. We develop a unified reconstruction algorithm for both IDT modalities that is highly computationally efficient and is implemented by a modular automatic differentiation framework. We demonstrate the capability of our reconstruction algorithm on both weakly scattering buccal epithelial cells and strongly scattering liveC. elegansworms and liveC. elegansembryos.

Photonics provides a promising approach for image processing by spatial filtering, with the advantage of faster speeds and lower power consumption compared to electronic digital solutions. However, traditional optical spatial filters suffer from bulky form factors that limit their portability. Here we present a new approach based on pixel arrays of plasmonic directional image sensors, designed to selectively detect light incident along a small, geometrically tunable set of directions. The resulting imaging systems can function as optical spatial filters without any external filtering elements, leading to extreme size miniaturization. Furthermore, they offer the distinct capability to perform multiple filtering operations at the same time, through the use of sensor arrays partitioned into blocks of adjacent pixels with different angular responses. To establish the image processing capabilities of these devices, we present a rigorous theoretical model of their filter transfer function under both coherent and incoherent illumination. Next, we use the measured angle-resolved responsivity of prototype devices to demonstrate two examples of relevant functionalities: (1) the visualization of otherwise invisible phase objects and (2) spatial differentiation with incoherent light. These results are significant for a multitude of imaging applications ranging from microscopy in biomedicine to object recognition for computer vision.

Deep learning has been broadly applied to imaging in scattering applications. A common framework is to train a descattering network for image recovery by removing scattering artifacts. To achieve the best results on a broad spectrum of scattering conditions, individual “expert” networks need to be trained for each condition. However, the expert’s performance sharply degrades when the testing condition differs from the training. An alternative brute-force approach is to train a “generalist” network using data from diverse scattering conditions. It generally requires a larger network to encapsulate the diversity in the data and a sufficiently large training set to avoid overfitting. Here, we propose anadaptive learningframework, termed dynamic synthesis network (DSN), whichdynamicallyadjusts the model weights andadaptsto different scattering conditions. The adaptability is achieved by a novel “mixture of experts” architecture that enables dynamically synthesizing a network by blending multiple experts using a gating network. We demonstrate the DSN in holographic 3D particle imaging for a variety of scattering conditions. We show in simulation that our DSN provides generalization across acontinuumof scattering conditions. In addition, we show that by training the DSN entirely on simulated data, the network can generalize to experiments and achieve robust 3D descattering. We expect themore »same concept can find many other applications, such as denoising and imaging in scattering media. Broadly, our dynamic synthesis framework opens up a new paradigm for designing highlyadaptivedeep learning and computational imaging techniques.

We propose a novel intensity diffraction tomography reconstruction algorithm based on the split-step non-paraxial model for recovering the 3D refractive index distribution of multiple-scattering biological samples.

We demonstrate an adaptive learning framework, termed dynamic synthesis network (DSN), which dynamically synthesizes model weights and adapts to different scattering conditions. The efficiency of DSN is demonstrated in holographic 3D particle descattering.