Physics-informed neural networks for diffraction tomography
This work addresses faster and more accurate tomographic reconstructions for biological imaging, though it appears incremental as it builds on existing physics-informed neural network methods.
The authors tackled the problem of tomographic reconstructions of biological samples by proposing a physics-informed neural network as a forward model, demonstrating that it predicts scattered fields accurately and can be fine-tuned for different samples to solve scattering problems faster than other numerical solutions.
We propose a physics-informed neural network as the forward model for tomographic reconstructions of biological samples. We demonstrate that by training this network with the Helmholtz equation as a physical loss, we can predict the scattered field accurately. It will be shown that a pretrained network can be fine-tuned for different samples and used for solving the scattering problem much faster than other numerical solutions. We evaluate our methodology with numerical and experimental results. Our physics-informed neural networks can be generalized for any forward and inverse scattering problem.