An accurate and universal approach for short-exposure-time microscopy image enhancement

Distinct actin microfilament localization during early cell plate formation through deep learning-based image restoration

KEY MESSAGE

Using deep learning-based image restoration, we achieved high-resolution 4D imaging with minimal photodamage, revealing distinct localization and suggesting Lifeact-RFP-labeled actin microfilaments play a role in initiating cell plate formation. Phragmoplasts are plant-specific intracellular structures composed of microtubules, actin microfilaments (AFs), membranes, and associated proteins. Importantly, they are involved in the formation and the expansion of cell plates that partition daughter cells during cell division. While previous studies have revealed the important role of cytoskeletal dynamics in the proper functioning of the phragmoplast, the localization and the role of AFs in the initial phase of cell plate formation remain controversial. Here, we used deep learning-based image restoration to achieve high-resolution 4D imaging with minimal laser-induced damage, enabling us to investigate the dynamics of AFs during the initial phase of cell plate formation in transgenic tobacco BY-2 cells labeled with Lifeact-RFP or RFP-ABD2 (actin-binding domain 2). This computational approach overcame the limitation of conventional imaging, namely laser-induced photobleaching and phototoxicity. The restored images indicated that RFP-ABD2-labeled AFs were predominantly localized near the daughter nucleus, whereas Lifeact-RFP-labeled AFs were found not only near the daughter nucleus but also around the initial cell plate. These findings, validated by imaging with a long exposure time, highlight distinct localization patterns between the two AF probes and suggest that Lifeact-RFP-labeled AFs play a role in initiating cell plate formation.

MVE-Net: A label-free microscopic image visual enhancement network via mRetinex and nonreference loss guidance

Label-free microscopic cell image analysis (segmentation, detection, counting, e.g.) is elementary for unravelling the biological functions of cells and their organelles. However, low contrast, darker brightness, background inhomogeneous, and weak edges of cells cause challenges in subsequent cell image analysis processes. To address these challenges, a Microscopic Visual Enhancement Network (MVE-Net) is proposed to improve microscopic visual effects through pre-enhancement and enhancement processes. In the pre-enhancement stage, to overcome the difficulty of acquiring paired or unpaired images for training, the mRetinex block is proposed to guide the pre-enhancement network to image contrast, cell details, and structural features. Furthermore, a multi-scale extraction module is employed to extract and fuse cell texture and structural features from the pre-enhanced images at various scales, guiding the generator training. In the enhancement stage, a nonreference loss block is designed, incorporating spatial consistency, uneven illumination smoothness, and exposure adjustment loss terms, to further enhance the contrast between cells and the background, smooth the inhomogeneous background, and adjust overall image brightness, thereby guiding the generator's enhancement process and improving the visual effect of microscopic images. Experiments on the LIVECell and PNT1A datasets demonstrate that MVE-Net outperforms state-of-the-art image enhancement methods, significantly improving image contrast, brightness, cell detail, and structural features without the need for paired or unpaired reference standard images for training.

Determination of the Localized Surface Plasmon Resonance Alteration of AgNPs via Multiwavelength Evanescent Scattering Microscopy for Pb(II) Detection

We developed multiwavelength evanescent scattering microscopy (MWESM), which can acquire plasmonic nanoparticle images at the particle level using the evanescent field as the incident source and distinguish different LSPR (localized surface plasmon resonance) spectral peaks among four wavelengths. Our microscope could be easily and simply built by modifying a commercial total internal reflection fluorescence microscope (TIRFM) with the substitution of a beamsplitter and the addition of a semicircular stop. The ultrathin depth of illumination and rejection of the reflected incident source together contribute to the high sensitivity and contrast of single nanoparticle imaging. We first validated the capability of our imaging system in distinguishing plasmonic nanoparticles bearing different LSPR spectral peaks, and the results were consistent with the scattering spectra results of hyperspectral imaging. Moreover, we demonstrated high imaging quality from the aspects of the signal/noise ratio and point spread function of the single-particle images. Meaningfully, the system can be utilized in rapidly determining the concentration of toxic lead ions in environmental and biological samples with good linearity and sensitivity, based on single-particle evanescent scattering imaging through the detection of the alteration of the LSPR of silver nanoparticles. This system holds the potential to advance the field of nanoparticle imaging and foster the application of nanomaterials as sensors.

VA-TIRFM-based SM kymograph analysis for dwell time and colocalization of plasma membrane protein in plant cells

BACKGROUND

The plasma membrane (PM) proteins function in a highly dynamic state, including protein trafficking and protein homeostasis, to regulate various biological processes. The dwell time and colocalization of PM proteins are considered to be two important dynamic features determining endocytosis and protein interactions, respectively. Dwell-time and colocalization detected using traditional fluorescence microscope techniques are often misestimated due to bulk measurement. In particular, analyzing these two features of PM proteins at the single-molecule level with spatiotemporal continuity in plant cells remains greatly challenging.

RESULTS

We developed a single molecular (SM) kymograph method, which is based on variable angle-total internal reflection fluorescence microscopy (VA-TIRFM) observation and single-particle (co-)tracking (SPT) analysis, to accurately analyze the dwell time and colocalization of PM proteins in a spatial and temporal manner. Furthermore, we selected two PM proteins with distinct dynamic behaviors, including AtRGS1 (Arabidopsis regulator of G protein signaling 1) and AtREM1.3 (Arabidopsis remorin 1.3), to analyze their dwell time and colocalization upon jasmonate (JA) treatment by SM kymography. First, we established new 3D (2D+t) images to view all trajectories of the interest protein by rotating these images, and then we chose the appropriate point without changing the trajectory for further analysis. Upon JA treatment, the path lines of AtRGS1-YFP appeared curved and short, while the horizontal lines of mCherry-AtREM1.3 demonstrated limited changes, indicating that JA might initiate the endocytosis of AtRGS1. Analysis of transgenic seedlings coexpressing AtRGS1-YFP/mCherry-AtREM1.3 revealed that JA induces a change in the trajectory of AtRGS1-YFP, which then merges into the kymography line of mCherry-AtREM1.3, implying that JA increases the colocalization degree between AtRGS1 and AtREM1.3 on the PM. These results illustrate that different types of PM proteins exhibit specific dynamic features in line with their corresponding functions.

CONCLUSIONS

The SM-kymograph method provides new insight into quantitively analyzing the dwell time and correlation degree of PM proteins at the single-molecule level in living plant cells.

Demonstration of Neural Networks to Reconstruct Temperatures from Simulated Fluorescent Data Toward Use in Bio-microfluidics

Biological systems often have a narrow temperature range of operation, which require highly accurate spatially resolved temperature measurements, often near ±0.1 K. However, many temperature sensors cannot meet both accuracy and spatial distribution requirements, often because their accuracy is limited by data fitting and temperature reconstruction models. Machine learning algorithms have the potential to meet this need, but their usage in generating spatial distributions of temperature is severely lacking in the literature. This work presents the first instance of using neural networks to process fluorescent images to map the spatial distribution of temperature. Three standard network architectures were investigated using non-spatially resolved fluorescent thermometry (simply-connected feed-forward network) or during image or pixel identification (U-net and convolutional neural network, CNN). Simulated fluorescent images based on experimental data were generated based on known temperature distributions where Gaussian white noise with a standard deviation of ±0.1 K was added. The poor results from these standard networks motivated the creation of what is termed a moving CNN, with an RMSE error of ±0.23 K, where the elements of the matrix represent the neighboring pixels. Finally, the performance of this MCNN is investigated when trained and applied to three distinctive temperature distributions characteristic within microfluidic devices, where the fluorescent image is simulated at either three or five different wavelengths. The results demonstrate that having a minimum of 10 ^3.5 data points per temperature and the broadest range of temperatures during training provides temperature predictions nearest to the true temperatures of the images, with a minimum RMSE of ±0.15 K. When compared to traditional curve fitting techniques, this work demonstrates that greater accuracy when spatially mapping temperature from fluorescent images can be achieved when using convolutional neural networks.