Deep learning-based hologram generation using a white light source

Automated fast label-free quantification of cardiomyocyte dynamics with raw holograms for cardiotoxicity screening

Traditional cell analysis approaches based on quantitative phase imaging (QPI) necessitate a reconstruction stage, which utilizes digital holography. However, phase retrieval processing can be complicated and time-consuming since it needs numerical reconstruction and then phase unwrapping. For analysis of cardiomyocyte (CM) dynamics, it was reported that by estimating the spatial variance of the optical path difference from QPI, the spatial displacement of CMs can be quantified, thereby enabling monitoring of the excitation-contraction activity of CMs. Also, it was reported that the Farnebäck optical flow method could be combined with the holographic imaging information from QPI to characterize the contractile motion of single CMs, enabling monitoring of the mechanical beating activity of CMs for cardiotoxicity screening. However, no studies have analyzed the contractile dynamics of CMs based on raw holograms. In this paper, we present a fast, label-free, and high throughput method for contractile dynamic analysis of human-induced pluripotent stem cell-derived CMs using raw holograms or the filtered holograms, which are obtained by filtering only The proposed approach obviates the need for time-consuming numerical reconstruction and phase unwrapping for CM's dynamic analysis while still having performance comparable to that of the previous methods. Accordingly, we developed a computational algorithm to characterize the CM's functional behaviors from contractile motion waveform obtained from raw or filtered holograms, which allows the calculation of various temporal metrics related to beating activity from contraction-relaxation motion-speed profile. To the best of our knowledge, this approach is the first to analyze drug-treated CM's dynamics from raw or filtered holograms without the need for numerical phase image reconstruction. For one hologram, the reconstruction process itself in the existing methods takes at least three times longer than the process of tracking the contraction-relaxation motion-speed profile using optical flow in the proposed method. Furthermore, our proposed methodology was validated in the toxicity screening of two drugs (E-4031 and isoprenaline) with various concentrations. The findings provide information on CM contractile motion and kinetics for cardiotoxicity screening.

Open-access database for digital lensless holographic microscopy and its application on the improvement of deep-learning-based autofocusing models

Among modern optical microscopy techniques, digital lensless holographic microscopy (DLHM) is one of the simplest label-free coherent imaging approaches. However, the hardware simplicity provided by the lensless configuration is often offset by the demanding computational postprocessing required to match the retrieved sample information to the user's expectations. A promising avenue to simplify this stage is the integration of artificial intelligence and machine learning (ML) solutions into the DLHM workflow. The biggest challenge to do so is the preparation of an extensive and high-quality experimental dataset of curated DLHM recordings to train ML models. In this work, a diverse, open-access dataset of DLHM recordings is presented as support for future research, contributing to the data needs of the applied research community. The database comprises 11,760 experimental DLHM holograms of bio and non-bio samples with diversity on the main recording parameters of the DLHM architecture. The database is divided into two datasets of 10 independent imaged samples. The first group, named multi-wavelength dataset, includes 8160 holograms and was recorded using laser diodes emitting at 654 nm, 510 nm, and 405 nm; the second group, named single-wavelength dataset, is composed of 3600 recordings and was acquired using a 633 nm He-Ne laser. All the experimental parameters related to the dataset acquisition, preparation, and calibration are described in this paper. The advantages of this large dataset are validated by re-training an existing autofocusing model for DLHM and as the training set for a simpler architecture that achieves comparable performance, proving its feasibility for improving existing ML-based models and the development of new ones.

Volumetric monitoring of airborne particulate matter concentration using smartphone-based digital holographic microscopy and deep learning

Airborne particulate matter (PM) has become a global environmental issue. This PM has harmful effects on public health and precision industries. Conventional air-quality monitoring methods usually utilize expensive equipment, and they are cumbersome to handle for accurate and high throughput measurements. In addition, commercial particle counters have technical limitations in high-concentration measurement, and data fluctuations are induced during air sampling. In this study, a novel smartphone-based technique for monitoring airborne PM concentrations was developed using smartphone-based digital holographic microscopy (S-DHM) and deep learning network called Holo-SpeckleNet. Holographic speckle images of various PM concentrations were recorded by the S-DHM system. The recorded speckle images and the corresponding ground truth PM concentrations were used to train deep learning algorithms consisting of a deep autoencoder and regression layers. The performance of the proposed smartphone-based PM monitoring technique was validated through hyperparameter optimization. The developed S-DHM integrated with Holo-SpeckleNet can be smartly and effectively utilized for portable PM monitoring and safety alarm provision under perilous environmental conditions.

Adsorption of nanoparticles suspended in a drop on a leaf surface of Perilla frutescens and their infiltration through stomatal pathway

Particulate matter (PM) has become a severe environmental issue, and ultrafine PM particles such as PM2.5 or PM1 can cause various complications and respiratory diseases to human beings. In particular, heavy metals contained in PM particles can contaminate edible plants; for example, plant leaves are exposed to PM particle-laden raindrops. The contaminated edible plants can injure the human health by ingestion, so a detailed understanding on the accumulation of PM particles inside edible plants is essential. In this study, we investigate the infiltration of PM particles in plant tissues with a hypothesis that ultrafine PM particles are absorbed through stomatal pathways. As an edible test plant, Perilla frutescens is selected. Drops of gold nanoparticle (AuNP) suspension are deposited on a leaf of P. frutescens to simulate the scenario where PM particle-laden raindrops fall on patulous stomata of the test plant. To examine AuNP adsorption on the P. frutescens foliar surface and diffusional AuNP absorption through stomatal apertures, we investigate three physical dynamics of AuNPs suspended in a sessile drop: sedimentation, evaporation-driven convective flow, and shrinkage of the drop interface. Quantitative information on the 3D spatial distribution of AuNPs in plant tissues was measured by X-ray imaging and two-photon excitation microscopy.

Accurate real-time monitoring of high particulate matter concentration based on holographic speckles and deep learning

Accurate real-time monitoring of particulate matter (PM) has emerged as a global issue due to the hazardous effects of PM on public health and industry. However, conventional PM monitoring techniques are usually cumbersome and require expensive equipments. In this study, Holo-SpeckleNet is proposed as a fast and accurate PM concentration measurement technique with high throughput using a deep learning based holographic speckle pattern analysis. Speckle pattern datasets of PMs for a wide range of PM concentrations were acquired by using a digital in-line holography microscopy system. Deep autoencoder and regression algorithms were trained with the captured speckle pattern datasets to directly measure PM concentration from speckle pattern images without any air intake device and time-consuming post image processing. The proposed technique was applied to predict various PM concentrations using the test datasets, optimize hyperparameters, and compare its performance with a convolutional neural network (CNN) algorithm. As a result, high PM concentration values can be measured over air quality index of 150, above which human exposure is unhealthy. In addition, the proposed technique exhibits higher measurement accuracy and less overfitting than the CNN with a relative error of 7.46 ± 3.92%. It can be applied to design a compact air quality monitoring device for highly accurate and real-time measurement of PM concentrations under hazardous environment, such as factories or construction sites.