SynthEllips

SynthEllips is a coded wavefront sensing synthetic dataset. For each datapoint, a refractive index volume composed of a random configuration of ellipsoids (refractive indices, positions, diameters, and rotations) is imaged using a wave-optical simulation of the Coded Wavefront Sensing pipeline to create a reference-specimen speckle image pair. The amplitude and scaled gradient vector field in the phase mask are also provided to assist with the supervised training of optical flow neural networks to estimate the quantitative phase from a reference-specimen speckle image pair. Training with SynthEllips demonstrated strong generalization to real biological specimens recorded experimentally, and to optical systems with different diffusers/phase masks and microscopes. The QPI performance of these networks is found to be quantitatively and qualitatively superior to classical phase retrieval methods. The data_creation_cwfs_params JSON file provides the metadata used to create the dataset. It lists the distribution parameters of the optical systems, which were sampled independently to create each datapoint, along with scaling parameters that were used to save the dataset as 16-bit integer TIFF files. The dataset_details CSV file provides additional information for each datapoint, including the sampled phase mask parameters, phase-mask sensor distances, and the number of ellipsoids sampled. SynthEllips/│├── reference/│ ├── 0.tiff│ ├── 1.tiff│ ├── ...├── specimen/│ ├── 0.tiff│ ├── 1.tiff│ ├── ...├── gt_gradients/│ ├── 0_0.tiff│ ├── 0_1.tiff│ ├── 1_0.tiff│ ├── 1_1.tiff│ ├── ...├── amplitude│ ├── 0.tiff│ ├── 1.tiff│ ├── ...├── data_creation_cwfs_params.json├── dataset_details.csv The dataloader Python file implements a PyTorch custom dataset loading function. This function can be used to input data to the network for training. The subset_params JSON file is used by the dataloader to filter dataset points based on their optical system attributes.