Three-dimensional residual channel attention networks denoise and sharpen fluorescence microscopy image volumes

Opportunities and challenges for deep learning in cell dynamics research

The growth of artificial intelligence (AI) has led to an increase in the adoption of computer vision and deep learning (DL) techniques for the evaluation of microscopy images and movies. This adoption has not only addressed hurdles in quantitative analysis of dynamic cell biological processes but has also started to support advances in drug development, precision medicine, and genome-phenome mapping. We survey existing AI-based techniques and tools, as well as open-source datasets, with a specific focus on the computational tasks of segmentation, classification, and tracking of cellular and subcellular structures and dynamics. We summarise long-standing challenges in microscopy video analysis from a computational perspective and review emerging research frontiers and innovative applications for DL-guided automation in cell dynamics research.

A Type I Photosensitizer-Polymersome Boosts Reactive Oxygen Species Generation by Forcing H-Aggregation for Amplifying STING Immunotherapy

Activation of the innate immune Stimulator of Interferon Genes (STING) pathway potentiates antitumor immunity. However, delivering STING agonists systemically to tumors presents a formidable challenge, and resistance to STING monotherapy has emerged in clinical trials with diminishing natural killer (NK) cell proliferation. Here, we encapsulated the STING agonist diABZI within polymersomes containing a Type I photosensitizer (NBS), creating a nanoagonist (PNBS/diABZI) for highly responsive tumor immunotherapy. This structure promoted H-aggregation and intersystem crossing of NBS, resulting in a ∼ 3-fold amplification in superoxide anion and singlet oxygen generation. The photodynamic therapy directly damaged hypoxia tumor cells and stimulated the proliferation of NK cells and cytotoxic T lymphocytes, thereby sensitizing STING immunotherapy. A single systemic intravenous administration of PNBS/diABZI eradicated orthotopic mammary tumors in murine models, achieving long-term antitumor immune memory to inhibit tumor recurrence and metastasis and significantly improving long-term tumor-free survival. This work provides a design rule for boosting reactive oxygen species production by promoting the intersystem crossing process, highlighting the potential of Type I photosensitizer-polymer vehicles for augmenting STING immunotherapy.

Overcoming photon and spatiotemporal sparsity in fluorescence lifetime imaging with SparseFLIM

Fluorescence lifetime imaging microscopy (FLIM) provides quantitative readouts of biochemical microenvironments, holding great promise for biomedical imaging. However, conventional FLIM relies on slow photon counting routines to accumulate sufficient photon statistics, restricting acquisition speeds. Here we demonstrate SparseFLIM, an intelligent paradigm for achieving high-fidelity FLIM reconstruction from sparse photon measurements. We develop a coupled bidirectional propagation network that enriches photon counts and recovers hidden spatial-temporal information. Quantitative analysis shows over tenfold photon enrichment, dramatically improving signal-to-noise ratio, lifetime accuracy, and correlation compared to the original sparse data. SparseFLIM enables reconstructing spatially and temporally undersampled FLIM at full resolution and channel count. The model exhibits strong generalization across experimental modalities including multispectral FLIM and in vivo endoscopic FLIM. This work establishes deep learning as a promising approach to enhance fluorescence lifetime imaging and transcend limitations imposed by the inherent codependence between measurement duration and information content.

Neural network-assisted localization of clustered point spread functions in single-molecule localization microscopy

Single-molecule localization microscopy (SMLM), which has revolutionized nanoscale imaging, faces challenges in densely labelled samples due to fluorophore clustering, leading to compromised localization accuracy. In this paper, we propose a novel convolutional neural network (CNN)-assisted approach to address the issue of locating the clustered fluorophores. Our CNN is trained on a diverse data set of simulated SMLM images where it learns to predict point spread function (PSF) locations by generating Gaussian blobs as output. Through rigorous evaluation, we demonstrate significant improvements in PSF localization accuracy, especially in densely labelled samples where traditional methods struggle. In addition, we employ blob detection as a post-processing technique to refine the predicted PSF locations and enhance localization precision. Our study underscores the efficacy of CNN in addressing clustering challenges in SMLM, thereby advancing spatial resolution and enabling deeper insights into complex biological structures.

Mitochondrial Structure, Dynamics, and Physiology: Light Microscopy to Disentangle the Network

Mitochondria serve as energetic and signaling hubs of the cell: This function results from the complex interplay between their structure, function, dynamics, interactions, and molecular organization. The ability to observe and quantify these properties often represents the puzzle piece critical for deciphering the mechanisms behind mitochondrial function and dysfunction. Fluorescence microscopy addresses this critical need and has become increasingly powerful with the advent of superresolution methods and context-sensitive fluorescent probes. In this review, we delve into advanced light microscopy methods and analyses for studying mitochondrial ultrastructure, dynamics, and physiology, and highlight notable discoveries they enabled.

Self-inspired learning for denoising live-cell super-resolution microscopy

Every collected photon is precious in live-cell super-resolution (SR) microscopy. Here, we describe a data-efficient, deep learning-based denoising solution to improve diverse SR imaging modalities. The method, SN2N, is a Self-inspired Noise2Noise module with self-supervised data generation and self-constrained learning process. SN2N is fully competitive with supervised learning methods and circumvents the need for large training set and clean ground truth, requiring only a single noisy frame for training. We show that SN2N improves photon efficiency by one-to-two orders of magnitude and is compatible with multiple imaging modalities for volumetric, multicolor, time-lapse SR microscopy. We further integrated SN2N into different SR reconstruction algorithms to effectively mitigate image artifacts. We anticipate SN2N will enable improved live-SR imaging and inspire further advances.

Frontiers in artificial intelligence-directed light-sheet microscopy for uncovering biological phenomena and multi-organ imaging

Light-sheet fluorescence microscopy (LSFM) introduces fast scanning of biological phenomena with deep photon penetration and minimal phototoxicity. This advancement represents a significant shift in 3-D imaging of large-scale biological tissues and 4-D (space + time) imaging of small live animals. The large data associated with LSFM requires efficient imaging acquisition and analysis with the use of artificial intelligence (AI)/machine learning (ML) algorithms. To this end, AI/ML-directed LSFM is an emerging area for multi-organ imaging and tumor diagnostics. This review will present the development of LSFM and highlight various LSFM configurations and designs for multi-scale imaging. Optical clearance techniques will be compared for effective reduction in light scattering and optimal deep-tissue imaging. This review will further depict a diverse range of research and translational applications, from small live organisms to multi-organ imaging to tumor diagnosis. In addition, this review will address AI/ML-directed imaging reconstruction, including the application of convolutional neural networks (CNNs) and generative adversarial networks (GANs). In summary, the advancements of LSFM have enabled effective and efficient post-imaging reconstruction and data analyses, underscoring LSFM's contribution to advancing fundamental and translational research.

Θ-Net: A Deep Neural Network Architecture for the Resolution Enhancement of Phase-Modulated Optical Micrographs In Silico

Optical microscopy is widely regarded to be an indispensable tool in healthcare and manufacturing quality control processes, although its inability to resolve structures separated by a lateral distance under ~200 nm has culminated in the emergence of a new field named fluorescence nanoscopy, while this too is prone to several caveats (namely phototoxicity, interference caused by exogenous probes and cost). In this regard, we present a triplet string of concatenated O-Net ('bead') architectures (termed 'Θ-Net' in the present study) as a cost-efficient and non-invasive approach to enhancing the resolution of non-fluorescent phase-modulated optical microscopical images in silico. The quality of the afore-mentioned enhanced resolution (ER) images was compared with that obtained via other popular frameworks (such as ANNA-PALM, BSRGAN and 3D RCAN), with the Θ-Net-generated ER images depicting an increased level of detail (unlike previous DNNs). In addition, the use of cross-domain (transfer) learning to enhance the capabilities of models trained on differential interference contrast (DIC) datasets [where phasic variations are not as prominently manifested as amplitude/intensity differences in the individual pixels unlike phase-contrast microscopy (PCM)] has resulted in the Θ-Net-generated images closely approximating that of the expected (ground truth) images for both the DIC and PCM datasets. This thus demonstrates the viability of our current Θ-Net architecture in attaining highly resolved images under poor signal-to-noise ratios while eliminating the need for a priori PSF and OTF information, thereby potentially impacting several engineering fronts (particularly biomedical imaging and sensing, precision engineering and optical metrology).

Iterative Immunostaining and NEDD Denoising for Improved Signal-To-Noise Ratio in ExM-LSCM

Expansion microscopy (ExM) has significantly reformed the field of super-resolution imaging, emerging as a powerful tool for visualizing complex cellular structures with nanoscale precision. Despite its capabilities, the epitope accessibility, labeling density, and precision of individual molecule detection pose challenges. We recently developed an iterative indirect immunofluorescence (IT-IF) method to improve the epitope labeling density, improving the signal and total intensity. In our protocol, we iteratively apply immunostaining steps before the expansion and exploit signal processing through noise estimation, denoising, and deblurring (NEDD) to aid in quantitative image analyses. Herein, we describe the steps of the iterative staining procedure and provide instructions on how to perform NEDD-based signal processing. Overall, IT-IF in ExM-laser scanning confocal microscopy (LSCM) represents a significant advancement in the field of cellular imaging, offering researchers a versatile tool for unraveling the structural complexity of biological systems at the molecular level with an increased signal-to-noise ratio and fluorescence intensity. Key features • Builds upon the method developed by Mäntylä et al. [1] and introduces the IT-IF method and signal-processing platform for several nanoscopy imaging applications. • Retains signal-to-noise ratio and significantly enhances the fluorescence intensity of ExM-LSCM data. • Automatic estimation of noise, signal reconstruction, denoising, and deblurring for increased reliability in image quantifications. • Requires at least seven days to complete.

Super-resolution reconstruction improves multishell diffusion: using radiomics to predict adult-type diffuse glioma IDH and grade

Objectives

Multishell diffusion scanning is limited by low spatial resolution. We sought to improve the resolution of multishell diffusion images through deep learning-based super-resolution reconstruction (SR) and subsequently develop and validate a prediction model for adult-type diffuse glioma, isocitrate dehydrogenase status and grade 2/3 tumors.

Materials and methods

A simple diffusion model (DTI) and three advanced diffusion models (DKI, MAP, and NODDI) were constructed based on multishell diffusion scanning. Migration was performed with a generative adversarial network based on deep residual channel attention networks, after which images with 2x and 4x resolution improvements were generated. Radiomic features were used as inputs, and diagnostic models were subsequently constructed via multiple pipelines.

Results

This prospective study included 90 instances (median age, 54.5 years; 39 men) diagnosed with adult-type diffuse glioma. Images with both 2x- and 4x-improved resolution were visually superior to the original images, and the 2x-improved images allowed better predictions than did the 4x-improved images (P<.001). A comparison of the areas under the curve among the multiple pipeline-constructed models revealed that the advanced diffusion models did not have greater diagnostic performance than the simple diffusion model (P>.05). The NODDI model constructed with 2x-improved images had the best performance in predicting isocitrate dehydrogenase status (AUC_validation=0.877; Brier score=0.132). The MAP model constructed with the original images performed best in classifying grade 2 and grade 3 tumors (AUC_validation=0.806; Brier score=0.168).

Conclusion

SR improves the resolution of multishell diffusion images and has different advantages in achieving different goals and creating different target diffusion models.

Benchmarking robustness of deep neural networks in semantic segmentation of fluorescence microscopy images

BACKGROUND

Fluorescence microscopy (FM) is an important and widely adopted biological imaging technique. Segmentation is often the first step in quantitative analysis of FM images. Deep neural networks (DNNs) have become the state-of-the-art tools for image segmentation. However, their performance on natural images may collapse under certain image corruptions or adversarial attacks. This poses real risks to their deployment in real-world applications. Although the robustness of DNN models in segmenting natural images has been studied extensively, their robustness in segmenting FM images remains poorly understood RESULTS: To address this deficiency, we have developed an assay that benchmarks robustness of DNN segmentation models using datasets of realistic synthetic 2D FM images with precisely controlled corruptions or adversarial attacks. Using this assay, we have benchmarked robustness of ten representative models such as DeepLab and Vision Transformer. We find that models with good robustness on natural images may perform poorly on FM images. We also find new robustness properties of DNN models and new connections between their corruption robustness and adversarial robustness. To further assess the robustness of the selected models, we have also benchmarked them on real microscopy images of different modalities without using simulated degradation. The results are consistent with those obtained on the realistic synthetic images, confirming the fidelity and reliability of our image synthesis method as well as the effectiveness of our assay.

CONCLUSIONS

Based on comprehensive benchmarking experiments, we have found distinct robustness properties of deep neural networks in semantic segmentation of FM images. Based on the findings, we have made specific recommendations on selection and design of robust models for FM image segmentation.

Convolutional neural network transformer (CNNT) for fluorescence microscopy image denoising with improved generalization and fast adaptation

Deep neural networks can improve the quality of fluorescence microscopy images. Previous methods, based on Convolutional Neural Networks (CNNs), require time-consuming training of individual models for each experiment, impairing their applicability and generalization. In this study, we propose a novel imaging-transformer based model, Convolutional Neural Network Transformer (CNNT), that outperforms CNN based networks for image denoising. We train a general CNNT based backbone model from pairwise high-low Signal-to-Noise Ratio (SNR) image volumes, gathered from a single type of fluorescence microscope, an instant Structured Illumination Microscope. Fast adaptation to new microscopes is achieved by fine-tuning the backbone on only 5-10 image volume pairs per new experiment. Results show that the CNNT backbone and fine-tuning scheme significantly reduces training time and improves image quality, outperforming models trained using only CNNs such as 3D-RCAN and Noise2Fast. We show three examples of efficacy of this approach in wide-field, two-photon, and confocal fluorescence microscopy.

Pretraining a foundation model for generalizable fluorescence microscopy-based image restoration

Fluorescence microscopy-based image restoration has received widespread attention in the life sciences and has led to significant progress, benefiting from deep learning technology. However, most current task-specific methods have limited generalizability to different fluorescence microscopy-based image restoration problems. Here, we seek to improve generalizability and explore the potential of applying a pretrained foundation model to fluorescence microscopy-based image restoration. We provide a universal fluorescence microscopy-based image restoration (UniFMIR) model to address different restoration problems, and show that UniFMIR offers higher image restoration precision, better generalization and increased versatility. Demonstrations on five tasks and 14 datasets covering a wide range of microscopy imaging modalities and biological samples demonstrate that the pretrained UniFMIR can effectively transfer knowledge to a specific situation via fine-tuning, uncover clear nanoscale biomolecular structures and facilitate high-quality imaging. This work has the potential to inspire and trigger new research highlights for fluorescence microscopy-based image restoration.

Deep 3D histology powered by tissue clearing, omics and AI

To comprehensively understand tissue and organism physiology and pathophysiology, it is essential to create complete three-dimensional (3D) cellular maps. These maps require structural data, such as the 3D configuration and positioning of tissues and cells, and molecular data on the constitution of each cell, spanning from the DNA sequence to protein expression. While single-cell transcriptomics is illuminating the cellular and molecular diversity across species and tissues, the 3D spatial context of these molecular data is often overlooked. Here, I discuss emerging 3D tissue histology techniques that add the missing third spatial dimension to biomedical research. Through innovations in tissue-clearing chemistry, labeling and volumetric imaging that enhance 3D reconstructions and their synergy with molecular techniques, these technologies will provide detailed blueprints of entire organs or organisms at the cellular level. Machine learning, especially deep learning, will be essential for extracting meaningful insights from the vast data. Further development of integrated structural, molecular and computational methods will unlock the full potential of next-generation 3D histology.

Simultaneous removal of noise and correction of motion warping in neuron calcium imaging using a pipeline structure of self-supervised deep learning models

Calcium imaging is susceptible to motion distortions and background noises, particularly for monitoring active animals under low-dose laser irradiation, and hence unavoidably hinder the critical analysis of neural functions. Current research efforts tend to focus on either denoising or dewarping and do not provide effective methods for videos distorted by both noises and motion artifacts simultaneously. We found that when a self-supervised denoising model of DeepCAD [Nat. Methods18, 1359 (2021)10.1038/s41592-021-01225-0] is used on the calcium imaging contaminated by noise and motion warping, it can remove the motion artifacts effectively but with regenerated noises. To address this issue, we develop a two-level deep-learning (DL) pipeline to dewarp and denoise the calcium imaging video sequentially. The pipeline consists of two 3D self-supervised DL models that do not require warp-free and high signal-to-noise ratio (SNR) observations for network optimization. Specifically, a high-frequency enhancement block is presented in the denoising network to restore more structure information in the denoising process; a hierarchical perception module and a multi-scale attention module are designed in the dewarping network to tackle distortions of various sizes. Experiments conducted on seven videos from two-photon and confocal imaging systems demonstrate that our two-level DL pipeline can restore high-clarity neuron images distorted by both motion warping and background noises. Compared to typical DeepCAD, our denoising model achieves a significant improvement of approximately 30% in image resolution and up to 28% in signal-to-noise ratio; compared to traditional dewarping and denoising methods, our proposed pipeline network recovers more neurons, enhancing signal fidelity and improving data correlation among frames by 35% and 60% respectively. This work may provide an attractive method for long-term neural activity monitoring in awake animals and also facilitate functional analysis of neural circuits.

Live-cell imaging powered by computation

The proliferation of microscopy methods for live-cell imaging offers many new possibilities for users but can also be challenging to navigate. The prevailing challenge in live-cell fluorescence microscopy is capturing intra-cellular dynamics while preserving cell viability. Computational methods can help to address this challenge and are now shifting the boundaries of what is possible to capture in living systems. In this Review, we discuss these computational methods focusing on artificial intelligence-based approaches that can be layered on top of commonly used existing microscopies as well as hybrid methods that integrate computation and microscope hardware. We specifically discuss how computational approaches can improve the signal-to-noise ratio, spatial resolution, temporal resolution and multi-colour capacity of live-cell imaging.

Zero-shot learning enables instant denoising and super-resolution in optical fluorescence microscopy

Computational super-resolution methods, including conventional analytical algorithms and deep learning models, have substantially improved optical microscopy. Among them, supervised deep neural networks have demonstrated outstanding performance, however, demanding abundant high-quality training data, which are laborious and even impractical to acquire due to the high dynamics of living cells. Here, we develop zero-shot deconvolution networks (ZS-DeconvNet) that instantly enhance the resolution of microscope images by more than 1.5-fold over the diffraction limit with 10-fold lower fluorescence than ordinary super-resolution imaging conditions, in an unsupervised manner without the need for either ground truths or additional data acquisition. We demonstrate the versatile applicability of ZS-DeconvNet on multiple imaging modalities, including total internal reflection fluorescence microscopy, three-dimensional wide-field microscopy, confocal microscopy, two-photon microscopy, lattice light-sheet microscopy, and multimodal structured illumination microscopy, which enables multi-color, long-term, super-resolution 2D/3D imaging of subcellular bioprocesses from mitotic single cells to multicellular embryos of mouse and C. elegans.

Revealing speckle obscured living human retinal cells with artificial intelligence assisted adaptive optics optical coherence tomography

BACKGROUND

In vivo imaging of the human retina using adaptive optics optical coherence tomography (AO-OCT) has transformed medical imaging by enabling visualization of 3D retinal structures at cellular-scale resolution, including the retinal pigment epithelial (RPE) cells, which are essential for maintaining visual function. However, because noise inherent to the imaging process (e.g., speckle) makes it difficult to visualize RPE cells from a single volume acquisition, a large number of 3D volumes are typically averaged to improve contrast, substantially increasing the acquisition duration and reducing the overall imaging throughput.

METHODS

Here, we introduce parallel discriminator generative adversarial network (P-GAN), an artificial intelligence (AI) method designed to recover speckle-obscured cellular features from a single AO-OCT volume, circumventing the need for acquiring a large number of volumes for averaging. The combination of two parallel discriminators in P-GAN provides additional feedback to the generator to more faithfully recover both local and global cellular structures. Imaging data from 8 eyes of 7 participants were used in this study.

RESULTS

We show that P-GAN not only improves RPE cell contrast by 3.5-fold, but also improves the end-to-end time required to visualize RPE cells by 99-fold, thereby enabling large-scale imaging of cells in the living human eye. RPE cell spacing measured across a large set of AI recovered images from 3 participants were in agreement with expected normative ranges.

CONCLUSIONS

The results demonstrate the potential of AI assisted imaging in overcoming a key limitation of RPE imaging and making it more accessible in a routine clinical setting.

Harnessing artificial intelligence to reduce phototoxicity in live imaging

Fluorescence microscopy is essential for studying living cells, tissues and organisms. However, the fluorescent light that switches on fluorescent molecules also harms the samples, jeopardizing the validity of results - particularly in techniques such as super-resolution microscopy, which demands extended illumination. Artificial intelligence (AI)-enabled software capable of denoising, image restoration, temporal interpolation or cross-modal style transfer has great potential to rescue live imaging data and limit photodamage. Yet we believe the focus should be on maintaining light-induced damage at levels that preserve natural cell behaviour. In this Opinion piece, we argue that a shift in role for AIs is needed - AI should be used to extract rich insights from gentle imaging rather than recover compromised data from harsh illumination. Although AI can enhance imaging, our ultimate goal should be to uncover biological truths, not just retrieve data. It is essential to prioritize minimizing photodamage over merely pushing technical limits. Our approach is aimed towards gentle acquisition and observation of undisturbed living systems, aligning with the essence of live-cell fluorescence microscopy.

Noise learning of instruments for high-contrast, high-resolution and fast hyperspectral microscopy and nanoscopy

The low scattering efficiency of Raman scattering makes it challenging to simultaneously achieve good signal-to-noise ratio (SNR), high imaging speed, and adequate spatial and spectral resolutions. Here, we report a noise learning (NL) approach that estimates the intrinsic noise distribution of each instrument by statistically learning the noise in the pixel-spatial frequency domain. The estimated noise is then removed from the noisy spectra. This enhances the SNR by ca. 10 folds, and suppresses the mean-square error by almost 150 folds. NL allows us to improve the positioning accuracy and spatial resolution and largely eliminates the impact of thermal drift on tip-enhanced Raman spectroscopic nanoimaging. NL is also applicable to enhance SNR in fluorescence and photoluminescence imaging. Our method manages the ground truth spectra and the instrumental noise simultaneously within the training dataset, which bypasses the tedious labelling of huge dataset required in conventional deep learning, potentially shifting deep learning from sample-dependent to instrument-dependent.

Quantitative real-time phase microscopy for extended depth-of-field imaging based on the 3D single-shot differential phase contrast (ssDPC) imaging method

Optical diffraction tomography (ODT) is a promising label-free imaging method capable of quantitatively measuring the three-dimensional (3D) refractive index distribution of transparent samples. In recent years, partially coherent ODT (PC-ODT) has attracted increasing attention due to its system simplicity and absence of laser speckle noise. Quantitative phase imaging (QPI) technologies represented by Fourier ptychographic microscopy (FPM), differential phase contrast (DPC) imaging and intensity diffraction tomography (IDT) need to collect several or hundreds of intensity images, which usually introduce motion artifacts when shooting fast-moving targets, leading to a decrease in image quality. Hence, a quantitative real-time phase microscopy (qRPM) for extended depth of field (DOF) imaging based on 3D single-shot differential phase contrast (ssDPC) imaging method is proposed in this research study. qRPM incorporates a microlens array (MLA) to simultaneously collect spatial information and angular information. In subsequent optical information processing, a deconvolution method is used to obtain intensity stacks under different illumination angles in a raw light field image. Importing the obtained intensity stack into the 3D DPC imaging model is able to finally obtain the 3D refractive index distribution. The captured four-dimensional light field information enables the reconstruction of 3D information in a single snapshot and extending the DOF of qRPM. The imaging capability of the proposed qRPM system is experimental verified on different samples, achieve single-exposure 3D label-free imaging with an extended DOF for 160 µm which is nearly 30 times higher than the traditional microscope system.

MMV_Im2Im: an open-source microscopy machine vision toolbox for image-to-image transformation

Over the past decade, deep learning (DL) research in computer vision has been growing rapidly, with many advances in DL-based image analysis methods for biomedical problems. In this work, we introduce MMV_Im2Im, a new open-source Python package for image-to-image transformation in bioimaging applications. MMV_Im2Im is designed with a generic image-to-image transformation framework that can be used for a wide range of tasks, including semantic segmentation, instance segmentation, image restoration, image generation, and so on. Our implementation takes advantage of state-of-the-art machine learning engineering techniques, allowing researchers to focus on their research without worrying about engineering details. We demonstrate the effectiveness of MMV_Im2Im on more than 10 different biomedical problems, showcasing its general potentials and applicabilities. For computational biomedical researchers, MMV_Im2Im provides a starting point for developing new biomedical image analysis or machine learning algorithms, where they can either reuse the code in this package or fork and extend this package to facilitate the development of new methods. Experimental biomedical researchers can benefit from this work by gaining a comprehensive view of the image-to-image transformation concept through diversified examples and use cases. We hope this work can give the community inspirations on how DL-based image-to-image transformation can be integrated into the assay development process, enabling new biomedical studies that cannot be done only with traditional experimental assays. To help researchers get started, we have provided source code, documentation, and tutorials for MMV_Im2Im at [https://github.com/MMV-Lab/mmv_im2im] under MIT license.

Physics-informed deep neural network for image denoising

Image enhancement deep neural networks (DNN) can improve signal to noise ratio or resolution of optically collected visual information. The literature reports a variety of approaches with varying effectiveness. All these algorithms rely on arbitrary data (the pixels' count-rate) normalization, making their performance strngly affected by dataset or user-specific data pre-manipulation. We developed a DNN algorithm capable to enhance images signal-to-noise surpassing previous algorithms. Our model stems from the nature of the photon detection process which is characterized by an inherently Poissonian statistics. Our algorithm is thus driven by distance between probability functions instead than relying on the sole count-rate, producing high performance results especially in high-dynamic-range images. Moreover, it does not require any arbitrary image renormalization other than the transformation of the camera's count-rate into photon-number.

Video-rate 3D imaging of living cells using Fourier view-channel-depth light field microscopy

Interrogation of subcellular biological dynamics occurring in a living cell often requires noninvasive imaging of the fragile cell with high spatiotemporal resolution across all three dimensions. It thereby poses big challenges to modern fluorescence microscopy implementations because the limited photon budget in a live-cell imaging task makes the achievable performance of conventional microscopy approaches compromise between their spatial resolution, volumetric imaging speed, and phototoxicity. Here, we incorporate a two-stage view-channel-depth (VCD) deep-learning reconstruction strategy with a Fourier light-field microscope based on diffractive optical element to realize fast 3D super-resolution reconstructions of intracellular dynamics from single diffraction-limited 2D light-filed measurements. This VCD-enabled Fourier light-filed imaging approach (F-VCD), achieves video-rate (50 volumes per second) 3D imaging of intracellular dynamics at a high spatiotemporal resolution of ~180 nm × 180 nm × 400 nm and strong noise-resistant capability, with which light field images with a signal-to-noise ratio (SNR) down to -1.62 dB could be well reconstructed. With this approach, we successfully demonstrate the 4D imaging of intracellular organelle dynamics, e.g., mitochondria fission and fusion, with ~5000 times of observation.

Spatial redundancy transformer for self-supervised fluorescence image denoising

Fluorescence imaging with high signal-to-noise ratios has become the foundation of accurate visualization and analysis of biological phenomena. However, the inevitable noise poses a formidable challenge to imaging sensitivity. Here we provide the spatial redundancy denoising transformer (SRDTrans) to remove noise from fluorescence images in a self-supervised manner. First, a sampling strategy based on spatial redundancy is proposed to extract adjacent orthogonal training pairs, which eliminates the dependence on high imaging speed. Second, we designed a lightweight spatiotemporal transformer architecture to capture long-range dependencies and high-resolution features at low computational cost. SRDTrans can restore high-frequency information without producing oversmoothed structures and distorted fluorescence traces. Finally, we demonstrate the state-of-the-art denoising performance of SRDTrans on single-molecule localization microscopy and two-photon volumetric calcium imaging. SRDTrans does not contain any assumptions about the imaging process and the sample, thus can be easily extended to various imaging modalities and biological applications.

Live-cell imaging in the deep learning era

Live imaging is a powerful tool, enabling scientists to observe living organisms in real time. In particular, when combined with fluorescence microscopy, live imaging allows the monitoring of cellular components with high sensitivity and specificity. Yet, due to critical challenges (i.e., drift, phototoxicity, dataset size), implementing live imaging and analyzing the resulting datasets is rarely straightforward. Over the past years, the development of bioimage analysis tools, including deep learning, is changing how we perform live imaging. Here we briefly cover important computational methods aiding live imaging and carrying out key tasks such as drift correction, denoising, super-resolution imaging, artificial labeling, tracking, and time series analysis. We also cover recent advances in self-driving microscopy.

Roadmap on Label-Free Super-Resolution Imaging

Label-free super-resolution (LFSR) imaging relies on light-scattering processes in nanoscale objects without a need for fluorescent (FL) staining required in super-resolved FL microscopy. The objectives of this Roadmap are to present a comprehensive vision of the developments, the state-of-the-art in this field, and to discuss the resolution boundaries and hurdles which need to be overcome to break the classical diffraction limit of the LFSR imaging. The scope of this Roadmap spans from the advanced interference detection techniques, where the diffraction-limited lateral resolution is combined with unsurpassed axial and temporal resolution, to techniques with true lateral super-resolution capability which are based on understanding resolution as an information science problem, on using novel structured illumination, near-field scanning, and nonlinear optics approaches, and on designing superlenses based on nanoplasmonics, metamaterials, transformation optics, and microsphere-assisted approaches. To this end, this Roadmap brings under the same umbrella researchers from the physics and biomedical optics communities in which such studies have often been developing separately. The ultimate intent of this paper is to create a vision for the current and future developments of LFSR imaging based on its physical mechanisms and to create a great opening for the series of articles in this field.

Registration-free 3D super-resolution generative deep-learning network for fluorescence microscopy imaging

Volumetric fluorescence microscopy has a great demand for high-resolution (HR) imaging and comes at the cost of sophisticated imaging solutions. Image super-resolution (SR) methods offer an effective way to recover HR images from low-resolution (LR) images. Nevertheless, these methods require pixel-level registered LR and HR images, posing a challenge in accurate image registration. To address these issues, we propose a novel registration-free image SR method. Our method conducts SR training and prediction directly on unregistered LR and HR volume neuronal images. The network is built on the CycleGAN framework and the 3D UNet based on attention mechanism. We evaluated our method on LR (5×/0.16-NA) and HR (20×/1.0-NA) fluorescence volume neuronal images collected by light-sheet microscopy. Compared to other super-resolution methods, our approach achieved the best reconstruction results. Our method shows promise for wide applications in the field of neuronal image super-resolution.

Restoration of metabolic functional metrics from label-free, two-photon human tissue images using multiscale deep-learning-based denoising algorithms

Significance

Label-free, two-photon excited fluorescence (TPEF) imaging captures morphological and functional metabolic tissue changes and enables enhanced understanding of numerous diseases. However, noise and other artifacts present in these images severely complicate the extraction of biologically useful information.

Aim

We aim to employ deep neural architectures in the synthesis of a multiscale denoising algorithm optimized for restoring metrics of metabolic activity from low-signal-to-noise ratio (SNR), TPEF images.

Approach

TPEF images of reduced nicotinamide adenine dinucleotide (phosphate) (NAD(P)H) and flavoproteins (FAD) from freshly excised human cervical tissues are used to assess the impact of various denoising models, preprocessing methods, and data on metrics of image quality and the recovery of six metrics of metabolic function from the images relative to ground truth images.

Results

Optimized recovery of the redox ratio and mitochondrial organization is achieved using a novel algorithm based on deep denoising in the wavelet transform domain. This algorithm also leads to significant improvements in peak-SNR (PSNR) and structural similarity index measure (SSIM) for all images. Interestingly, other models yield even higher PSNR and SSIM improvements, but they are not optimal for recovery of metabolic function metrics.

Conclusions

Denoising algorithms can recover diagnostically useful information from low SNR label-free TPEF images and will be useful for the clinical translation of such imaging.

Imagining the future of optical microscopy: everything, everywhere, all at once

The optical microscope has revolutionized biology since at least the 17th Century. Since then, it has progressed from a largely observational tool to a powerful bioanalytical platform. However, realizing its full potential to study live specimens is hindered by a daunting array of technical challenges. Here, we delve into the current state of live imaging to explore the barriers that must be overcome and the possibilities that lie ahead. We venture to envision a future where we can visualize and study everything, everywhere, all at once - from the intricate inner workings of a single cell to the dynamic interplay across entire organisms, and a world where scientists could access the necessary microscopy technologies anywhere.

Attention-based generative adversarial networks improve prognostic outcome prediction of cancer from multimodal data

The prediction of prognostic outcome is critical for the development of efficient cancer therapeutics and potential personalized medicine. However, due to the heterogeneity and diversity of multimodal data of cancer, data integration and feature selection remain a challenge for prognostic outcome prediction. We proposed a deep learning method with generative adversarial network based on sequential channel-spatial attention modules (CSAM-GAN), a multimodal data integration and feature selection approach, for accomplishing prognostic stratification tasks in cancer. Sequential channel-spatial attention modules equipped with an encoder-decoder are applied for the input features of multimodal data to accurately refine selected features. A discriminator network was proposed to make the generator and discriminator learning in an adversarial way to accurately describe the complex heterogeneous information of multiple modal data. We conducted extensive experiments with various feature selection and classification methods and confirmed that the CSAM-GAN via the multilayer deep neural network (DNN) classifier outperformed these baseline methods on two different multimodal data sets with miRNA expression, mRNA expression and histopathological image data: lower-grade glioma and kidney renal clear cell carcinoma. The CSAM-GAN via the multilayer DNN classifier bridges the gap between heterogenous multimodal data and prognostic outcome prediction.

Three-dimensional structured illumination microscopy with enhanced axial resolution

The axial resolution of three-dimensional structured illumination microscopy (3D SIM) is limited to ∼300 nm. Here we present two distinct, complementary methods to improve axial resolution in 3D SIM with minimal or no modification to the optical system. We show that placing a mirror directly opposite the sample enables four-beam interference with higher spatial frequency content than 3D SIM illumination, offering near-isotropic imaging with ∼120-nm lateral and 160-nm axial resolution. We also developed a deep learning method achieving ∼120-nm isotropic resolution. This method can be combined with denoising to facilitate volumetric imaging spanning dozens of timepoints. We demonstrate the potential of these advances by imaging a variety of cellular samples, delineating the nanoscale distribution of vimentin and microtubule filaments, observing the relative positions of caveolar coat proteins and lysosomal markers and visualizing cytoskeletal dynamics within T cells in the early stages of immune synapse formation.

Optimal sparsity allows reliable system-aware restoration of fluorescence microscopy images

Fluorescence microscopy is one of the most indispensable and informative driving forces for biological research, but the extent of observable biological phenomena is essentially determined by the content and quality of the acquired images. To address the different noise sources that can degrade these images, we introduce an algorithm for multiscale image restoration through optimally sparse representation (MIRO). MIRO is a deterministic framework that models the acquisition process and uses pixelwise noise correction to improve image quality. Our study demonstrates that this approach yields a remarkable restoration of the fluorescence signal for a wide range of microscopy systems, regardless of the detector used (e.g., electron-multiplying charge-coupled device, scientific complementary metal-oxide semiconductor, or photomultiplier tube). MIRO improves current imaging capabilities, enabling fast, low-light optical microscopy, accurate image analysis, and robust machine intelligence when integrated with deep neural networks. This expands the range of biological knowledge that can be obtained from fluorescence microscopy.

Deep self-learning enables fast, high-fidelity isotropic resolution restoration for volumetric fluorescence microscopy

One intrinsic yet critical issue that troubles the field of fluorescence microscopy ever since its introduction is the unmatched resolution in the lateral and axial directions (i.e., resolution anisotropy), which severely deteriorates the quality, reconstruction, and analysis of 3D volume images. By leveraging the natural anisotropy, we present a deep self-learning method termed Self-Net that significantly improves the resolution of axial images by using the lateral images from the same raw dataset as rational targets. By incorporating unsupervised learning for realistic anisotropic degradation and supervised learning for high-fidelity isotropic recovery, our method can effectively suppress the hallucination with substantially enhanced image quality compared to previously reported methods. In the experiments, we show that Self-Net can reconstruct high-fidelity isotropic 3D images from organelle to tissue levels via raw images from various microscopy platforms, e.g., wide-field, laser-scanning, or super-resolution microscopy. For the first time, Self-Net enables isotropic whole-brain imaging at a voxel resolution of 0.2 × 0.2 × 0.2 μm3, which addresses the last-mile problem of data quality in single-neuron morphology visualization and reconstruction with minimal effort and cost. Overall, Self-Net is a promising approach to overcoming the inherent resolution anisotropy for all classes of 3D fluorescence microscopy.

Machine learning in cardiology: Clinical application and basic research

Machine learning is a subfield of artificial intelligence. The quality and versatility of machine learning have been rapidly improving and playing a critical role in many aspects of social life. This trend is also observed in the medical field. Generally, there are three main types of machine learning: supervised, unsupervised, and reinforcement learning. Each type of learning is adequately selected for the purpose and type of data. In the field of medicine, various types of information are collected and used, and research using machine learning is becoming increasingly relevant. Many clinical studies are conducted using electronic health and medical records, including in the cardiovascular area. Machine learning has also been applied in basic research. Machine learning has been widely used for several types of data analysis, such as clustering of microarray analysis and RNA sequence analysis. Machine learning is essential for genome and multi-omics analyses. This review summarizes the recent advancements in the use of machine learning in clinical applications and basic cardiovascular research.

Iterative immunostaining combined with expansion microscopy and image processing reveals nanoscopic network organization of nuclear lamina

Investigation of nuclear lamina architecture relies on superresolved microscopy. However, epitope accessibility, labeling density, and detection precision of individual molecules pose challenges within the molecularly crowded nucleus. We developed iterative indirect immunofluorescence (IT-IF) staining approach combined with expansion microscopy (ExM) and structured illumination microscopy to improve superresolution microscopy of subnuclear nanostructures like lamins. We prove that ExM is applicable in analyzing highly compacted nuclear multiprotein complexes such as viral capsids and provide technical improvements to ExM method including three-dimensional-printed gel casting equipment. We show that in comparison with conventional immunostaining, IT-IF results in a higher signal-to-background ratio and a mean fluorescence intensity by improving the labeling density. Moreover, we present a signal-processing pipeline for noise estimation, denoising, and deblurring to aid in quantitative image analyses and provide this platform for the microscopy imaging community. Finally, we show the potential of signal-resolved IT-IF in quantitative superresolution ExM imaging of nuclear lamina and reveal nanoscopic details of the lamin network organization-a prerequisite for studying intranuclear structural coregulation of cell function and fate.

Resolution enhancement with a task-assisted GAN to guide optical nanoscopy image analysis and acquisition

Super-resolution fluorescence microscopy methods enable the characterization of nanostructures in living and fixed biological tissues. However, they require the adjustment of multiple imaging parameters while attempting to satisfy conflicting objectives, such as maximizing spatial and temporal resolution while minimizing light exposure. To overcome the limitations imposed by these trade-offs, post-acquisition algorithmic approaches have been proposed for resolution enhancement and image-quality improvement. Here we introduce the task-assisted generative adversarial network (TA-GAN), which incorporates an auxiliary task (for example, segmentation, localization) closely related to the observed biological nanostructure characterization. We evaluate how the TA-GAN improves generative accuracy over unassisted methods, using images acquired with different modalities such as confocal, bright-field, stimulated emission depletion and structured illumination microscopy. The TA-GAN is incorporated directly into the acquisition pipeline of the microscope to predict the nanometric content of the field of view without requiring the acquisition of a super-resolved image. This information is used to automatically select the imaging modality and regions of interest, optimizing the acquisition sequence by reducing light exposure. Data-driven microscopy methods like the TA-GAN will enable the observation of dynamic molecular processes with spatial and temporal resolutions that surpass the limits currently imposed by the trade-offs constraining super-resolution microscopy.

Deep learning enables fast, gentle STED microscopy

STED microscopy is widely used to image subcellular structures with super-resolution. Here, we report that restoring STED images with deep learning can mitigate photobleaching and photodamage by reducing the pixel dwell time by one or two orders of magnitude. Our method allows for efficient and robust restoration of noisy 2D and 3D STED images with multiple targets and facilitates long-term imaging of mitochondrial dynamics.

Restoration of metabolic functional metrics from label-free, two-photon cervical tissue images using multiscale deep-learning-based denoising algorithms

Label-free, two-photon imaging captures morphological and functional metabolic tissue changes and enables enhanced understanding of numerous diseases. However, this modality suffers from low signal arising from limitations imposed by the maximum permissible dose of illumination and the need for rapid image acquisition to avoid motion artifacts. Recently, deep learning methods have been developed to facilitate the extraction of quantitative information from such images. Here, we employ deep neural architectures in the synthesis of a multiscale denoising algorithm optimized for restoring metrics of metabolic activity from low-SNR, two-photon images. Two-photon excited fluorescence (TPEF) images of reduced nicotinamide adenine dinucleotide (phosphate) (NAD(P)H) and flavoproteins (FAD) from freshly excised human cervical tissues are used. We assess the impact of the specific denoising model, loss function, data transformation, and training dataset on established metrics of image restoration when comparing denoised single frame images with corresponding six frame averages, considered as the ground truth. We further assess the restoration accuracy of six metrics of metabolic function from the denoised images relative to ground truth images. Using a novel algorithm based on deep denoising in the wavelet transform domain, we demonstrate optimal recovery of metabolic function metrics. Our results highlight the promise of denoising algorithms to recover diagnostically useful information from low SNR label-free two-photon images and their potential importance in the clinical translation of such imaging.

Keyframe-aided resolution enhancement network for dynamic super-resolution structured illumination microscopy

Deep learning has been used to reconstruct super-resolution structured illumination microscopy (SR-SIM) images with wide-field or fewer raw images, effectively reducing photobleaching and phototoxicity. However, the dependability of new structures or sample observation is still questioned using these methods. Here, we propose a dynamic SIM imaging strategy: the full raw images are recorded at the beginning to reconstruct the SR image as a keyframe, then only wide-field images are recorded. A deep-learning-based reconstruction algorithm, named KFA-RET, is developed to reconstruct the rest of the SR images for the whole dynamic process. With the structure at the keyframe as a reference and the temporal continuity of biological structures, KFA-RET greatly enhances the quality of reconstructed SR images while reducing photobleaching and phototoxicity. Moreover, KFA-RET has a strong transfer capability for observing new structures that were not included during network training.

Noise Suppression With Similarity-Based Self-Supervised Deep Learning

Image denoising is a prerequisite for downstream tasks in many fields. Low-dose and photon-counting computed tomography (CT) denoising can optimize diagnostic performance at minimized radiation dose. Supervised deep denoising methods are popular but require paired clean or noisy samples that are often unavailable in practice. Limited by the independent noise assumption, current self-supervised denoising methods cannot process correlated noises as in CT images. Here we propose the first-of-its-kind similarity-based self-supervised deep denoising approach, referred to as Noise2Sim, that works in a nonlocal and nonlinear fashion to suppress not only independent but also correlated noises. Theoretically, Noise2Sim is asymptotically equivalent to supervised learning methods under mild conditions. Experimentally, Nosie2Sim recovers intrinsic features from noisy low-dose CT and photon-counting CT images as effectively as or even better than supervised learning methods on practical datasets visually, quantitatively and statistically. Noise2Sim is a general self-supervised denoising approach and has great potential in diverse applications.

Architecture and dynamics of a desmosome-endoplasmic reticulum complex

The endoplasmic reticulum (ER) forms a dynamic network that contacts other cellular membranes to regulate stress responses, calcium signalling and lipid transfer. Here, using high-resolution volume electron microscopy, we find that the ER forms a previously unknown association with keratin intermediate filaments and desmosomal cell-cell junctions. Peripheral ER assembles into mirror image-like arrangements at desmosomes and exhibits nanometre proximity to keratin filaments and the desmosome cytoplasmic plaque. ER tubules exhibit stable associations with desmosomes, and perturbation of desmosomes or keratin filaments alters ER organization, mobility and expression of ER stress transcripts. These findings indicate that desmosomes and the keratin cytoskeleton regulate the distribution, function and dynamics of the ER network. Overall, this study reveals a previously unknown subcellular architecture defined by the structural integration of ER tubules with an epithelial intercellular junction.

Single-frame deep-learning super-resolution microscopy for intracellular dynamics imaging

Single-molecule localization microscopy (SMLM) can be used to resolve subcellular structures and achieve a tenfold improvement in spatial resolution compared to that obtained by conventional fluorescence microscopy. However, the separation of single-molecule fluorescence events that requires thousands of frames dramatically increases the image acquisition time and phototoxicity, impeding the observation of instantaneous intracellular dynamics. Here we develop a deep-learning based single-frame super-resolution microscopy (SFSRM) method which utilizes a subpixel edge map and a multicomponent optimization strategy to guide the neural network to reconstruct a super-resolution image from a single frame of a diffraction-limited image. Under a tolerable signal density and an affordable signal-to-noise ratio, SFSRM enables high-fidelity live-cell imaging with spatiotemporal resolutions of 30 nm and 10 ms, allowing for prolonged monitoring of subcellular dynamics such as interplays between mitochondria and endoplasmic reticulum, the vesicle transport along microtubules, and the endosome fusion and fission. Moreover, its adaptability to different microscopes and spectra makes it a useful tool for various imaging systems.

IMC-Denoise: a content aware denoising pipeline to enhance Imaging Mass Cytometry

Imaging Mass Cytometry (IMC) is an emerging multiplexed imaging technology for analyzing complex microenvironments using more than 40 molecularly-specific channels. However, this modality has unique data processing requirements, particularly for patient tissue specimens where signal-to-noise ratios for markers can be low, despite optimization, and pixel intensity artifacts can deteriorate image quality and downstream analysis. Here we demonstrate an automated content-aware pipeline, IMC-Denoise, to restore IMC images deploying a differential intensity map-based restoration (DIMR) algorithm for removing hot pixels and a self-supervised deep learning algorithm for shot noise image filtering (DeepSNiF). IMC-Denoise outperforms existing methods for adaptive hot pixel and background noise removal, with significant image quality improvement in modeled data and datasets from multiple pathologies. This includes in technically challenging human bone marrow; we achieve noise level reduction of 87% for a 5.6-fold higher contrast-to-noise ratio, and more accurate background noise removal with approximately 2 × improved F1 score. Our approach enhances manual gating and automated phenotyping with cell-scale downstream analyses. Verified by manual annotations, spatial and density analysis for targeted cell groups reveal subtle but significant differences of cell populations in diseased bone marrow. We anticipate that IMC-Denoise will provide similar benefits across mass cytometric applications to more deeply characterize complex tissue microenvironments.

Optofluidic imaging meets deep learning: from merging to emerging

Propelled by the striking advances in optical microscopy and deep learning (DL), the role of imaging in lab-on-a-chip has dramatically been transformed from a silo inspection tool to a quantitative "smart" engine. A suite of advanced optical microscopes now enables imaging over a range of spatial scales (from molecules to organisms) and temporal window (from microseconds to hours). On the other hand, the staggering diversity of DL algorithms has revolutionized image processing and analysis at the scale and complexity that were once inconceivable. Recognizing these exciting but overwhelming developments, we provide a timely review of their latest trends in the context of lab-on-a-chip imaging, or coined optofluidic imaging. More importantly, here we discuss the strengths and caveats of how to adopt, reinvent, and integrate these imaging techniques and DL algorithms in order to tailor different lab-on-a-chip applications. In particular, we highlight three areas where the latest advances in lab-on-a-chip imaging and DL can form unique synergisms: image formation, image analytics and intelligent image-guided autonomous lab-on-a-chip. Despite the on-going challenges, we anticipate that they will represent the next frontiers in lab-on-a-chip imaging that will spearhead new capabilities in advancing analytical chemistry research, accelerating biological discovery, and empowering new intelligent clinical applications.

Real-time denoising enables high-sensitivity fluorescence time-lapse imaging beyond the shot-noise limit

A fundamental challenge in fluorescence microscopy is the photon shot noise arising from the inevitable stochasticity of photon detection. Noise increases measurement uncertainty and limits imaging resolution, speed and sensitivity. To achieve high-sensitivity fluorescence imaging beyond the shot-noise limit, we present DeepCAD-RT, a self-supervised deep learning method for real-time noise suppression. Based on our previous framework DeepCAD, we reduced the number of network parameters by 94%, memory consumption by 27-fold and processing time by a factor of 20, allowing real-time processing on a two-photon microscope. A high imaging signal-to-noise ratio can be acquired with tenfold fewer photons than in standard imaging approaches. We demonstrate the utility of DeepCAD-RT in a series of photon-limited experiments, including in vivo calcium imaging of mice, zebrafish larva and fruit flies, recording of three-dimensional (3D) migration of neutrophils after acute brain injury and imaging of 3D dynamics of cortical ATP release. DeepCAD-RT will facilitate the morphological and functional interrogation of biological dynamics with a minimal photon budget.

Three-dimensional reconstructing undersampled photoacoustic microscopy images using deep learning

Spatial sampling density and data size are important determinants of the imaging speed of photoacoustic microscopy (PAM). Therefore, undersampling methods that reduce the number of scanning points are typically adopted to enhance the imaging speed of PAM by increasing the scanning step size. Since undersampling methods sacrifice spatial sampling density, by considering the number of data points, data size, and the characteristics of PAM that provides three-dimensional (3D) volume data, in this study, we newly reported deep learning-based fully reconstructing the undersampled 3D PAM data. The results of quantitative analyses demonstrate that the proposed method exhibits robustness and outperforms interpolation-based reconstruction methods at various undersampling ratios, enhancing the PAM system performance with 80-times faster-imaging speed and 800-times lower data size. The proposed method is demonstrated to be the closest model that can be used under experimental conditions, effectively shortening the imaging time with significantly reduced data size for processing.

Deep learning enables fast, gentle STED microscopy

STED microscopy is widely used to image subcellular structures with super-resolution. Here, we report that denoising STED images with deep learning can mitigate photobleaching and photodamage by reducing the pixel dwell time by one or two orders of magnitude. Our method allows for efficient and robust restoration of noisy 2D and 3D STED images with multiple targets and facilitates long-term imaging of mitochondrial dynamics.

BCM3D 2.0: accurate segmentation of single bacterial cells in dense biofilms using computationally generated intermediate image representations

Accurate detection and segmentation of single cells in three-dimensional (3D) fluorescence time-lapse images is essential for observing individual cell behaviors in large bacterial communities called biofilms. Recent progress in machine-learning-based image analysis is providing this capability with ever-increasing accuracy. Leveraging the capabilities of deep convolutional neural networks (CNNs), we recently developed bacterial cell morphometry in 3D (BCM3D), an integrated image analysis pipeline that combines deep learning with conventional image analysis to detect and segment single biofilm-dwelling cells in 3D fluorescence images. While the first release of BCM3D (BCM3D 1.0) achieved state-of-the-art 3D bacterial cell segmentation accuracies, low signal-to-background ratios (SBRs) and images of very dense biofilms remained challenging. Here, we present BCM3D 2.0 to address this challenge. BCM3D 2.0 is entirely complementary to the approach utilized in BCM3D 1.0. Instead of training CNNs to perform voxel classification, we trained CNNs to translate 3D fluorescence images into intermediate 3D image representations that are, when combined appropriately, more amenable to conventional mathematical image processing than a single experimental image. Using this approach, improved segmentation results are obtained even for very low SBRs and/or high cell density biofilm images. The improved cell segmentation accuracies in turn enable improved accuracies of tracking individual cells through 3D space and time. This capability opens the door to investigating time-dependent phenomena in bacterial biofilms at the cellular level.