Physics-informed neural networks for diffraction tomography

We propose a physics-informed neural network(PINN)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 PINNs can be generalized for any forward and inverse scattering problem.

Three-dimensional tomography of red blood cells using deep learning

We accurately reconstruct three-dimensional(3-D)refractive index(RI)distributions from highly ill-posed two-dimensional(2-D)measurements using a deep neural network(DNN).Strong distortions are introduced on reconstructions obtained by the Wolf transform inversion method due to the ill-posed measurements acquired from the limited numerical apertures(NAs)of the optical system.Despite the recent success of DNNs in solving ill-posed inverse problems,the application to 3-D optical imaging is particularly challenging due to the lack of the ground truth.We overcome this limitation by generating digital phantoms that serve as samples for the discrete dipole approximation(DDA)to generate multiple 2-D projection maps for a limited range of illumination angles.The presented samples are red blood cells(RBCs),which are highly affected by the ill-posed problems due to their morphology.The trained network using synthetic measurements from the digital phantoms successfully eliminates the introduced distortions.Most importantly,we obtain high fidelity reconstructions from experimentally recorded projections of real RBC sample using the network that was trained on digitally generated RBC phantoms.Finally,we confirm the reconstruction accuracy using the DDA to calculate the 2-D projections of the 3-D reconstructions and compare them to the experimentally recorded projections.

Multiscale label-free volumetric holographic histopathology of thick-tissue slides with subcellular resolution

Histopathology relies upon the staining and sectioning of biological tissues,which can be laborious and may cause artifacts and distort tissues.We develop label-free volumetric imaging of thick-tissue slides,exploiting refractive index distributions as intrinsic imaging contrast.The present method systematically exploits label-free quantitative phase imaging techniques,volumetric reconstruction of intrinsic refractive index distributions in tissues,and numerical algorithms for the seamless stitching of multiple three-dimensional tomograms and for reducing scattering-induced image distortion.We demonstrated label-free volumetric imaging of thick tissues with the field of view of 2 mm×1.75 mm×0.2 mm with a spatial resolution of 170 nm×170 nm×1400 nm.The number of optical modes,calculated as the reconstructed volume divided by the size of the point spread function,was∼20 giga voxels.We have also demonstrated that different tumor types and a variety of precursor lesions and pathologies can be visualized with the present method.