FocusNET: An autofocusing learning -based model for digital lensless holographic microscopy

This paper reports on a convolutional neural network (CNN) - based regression model, called FocusNET, to predict the accurate reconstruction distance of raw holograms in Digital Lensless Holographic Microscopy (DLHM). This proposal provides a physical-mathematical formulation to extend its use to different DLHM setups than the optical and geometrical conditions utilized for recording the training dataset; this unique feature is tested by applying the proposal to holograms of diverse samples recorded with different DLHM setups. Additionally, a comparison between FocusNET and conventional autofocusing methods in terms of processing times and accuracy is provided. Although the proposed method predicts reconstruction distances with approximately 54 lam standard deviation, accurate information about the samples in the validation dataset is still retrieved. When compared to a method that utilizes a stack of reconstructions to find the best focal plane, FocusNET performs 600 times faster, as no hologram reconstruction is needed. When implemented in batches, the network can achieve up to a 1200-fold reduction in processing time, depending on the number of holograms to be processed. The training and validation datasets, and the code implementations, are hosted on a public GitHub repository that can be freely accessed.

Automated summary

This paper presents FocusNET, a convolutional neural network (CNN) - based regression model, for accurately predicting the reconstruction distance of raw holograms in Digital Lensless Holographic Microscopy (DLHM). The proposal extends its applicability to different DLHM setups and is validated on holograms recorded with diverse samples and setups. FocusNET outperforms conventional autofocusing methods in terms of processing times and achieves significant reduction in processing time when implemented in batches. The datasets and code implementations are available on a public GitHub repository.