Abstract

Digital holography is a powerful imaging technique for quantitative analysis in various fields of science and technology, including biomedical applications. However, the development and validation of neural network-based methods in this field are often limited by the unavailability of large, well-annotated experimental data. For example, in biological studies, the typical size of an experimental dataset is around 1000 images. In this work, we present a procedural framework for generating synthetic datasets of biological cell phase images and digital holograms. The generated datasets were tested in several key tasks of neural network applications, including cell classification, detection, and phase reconstruction from in-line holograms. High classification accuracy is achieved for both phase images and holograms, while phase reconstruction reaches high structural similarity indices. The applicability of the generated datasets is further demonstrated in complex scenarios involving multiple moving cells and multiple object planes. The proposed approach provides a flexible and scalable platform for method development, performance evaluation, and future integration with experimental holographic imaging systems.

IPC Classification

Keywords