3D high resolution generative deep-learning network for fluorescence microscopy imaging.

Microscopic fluorescence imaging serves as a basic tool in many research areas including biology, medicine, and chemistry. With the help of optical clearing, large volume imaging of a mouse brain and even a whole body has been enabled. However, constrained by the physical principles of optical imaging, volume imaging has to balance imaging resolution and speed. Here, we develop a new, to the best of our knowledge, 3D deep learning network based on a dual generative adversarial network (dual-GAN) framework for recovering high-resolution (HR) volume images from high speed acquired low-resolution (LR) volume images. The proposed method does not require a precise image registration process and meanwhile guarantees the predicted HR volume image faithful to its corresponding LR volume image. The results demonstrated that our method can recover ${20} {\times} /1.0\text-{\rm NA}$20×/1.0-NA volume images from coarsely registered ${5} {\times} /0.16\text-{\rm NA}$5×/0.16-NA volume images collected by light-sheet microscopy. This method would provide great potential in applications which require high resolution volume imaging.

NeuroGPS-Tree: automatic reconstruction of large-scale neuronal populations with dense neurites.

The reconstruction of neuronal populations, a key step in understanding neural circuits, remains a challenge in the presence of densely packed neurites. Here we achieved automatic reconstruction of neuronal populations by partially mimicking human strategies to separate individual neurons. For populations not resolvable by other methods, we obtained recall and precision rates of approximately 80%. We also demonstrate the reconstruction of 960 neurons within 3 h.

Large-scale localization of touching somas from 3D images using density-peak clustering.

BACKGROUND: Soma localization is an important step in computational neuroscience to map neuronal circuits. However, locating somas from large-scale and complicated datasets is challenging. The challenges primarily originate from the dense distribution of somas, the diversity of soma sizes and the inhomogeneity of image contrast. RESULTS: We proposed a novel localization method based on density-peak clustering. In this method, we introduced two quantities (the local density ρ of each voxel and its minimum distance δ from voxels of higher density) to describe the soma imaging signal, and developed an automatic algorithm to identify the soma positions from the feature space (ρ, δ). Compared with other methods focused on high local density, our method allowed the soma center to be characterized by high local density and large minimum distance. The simulation results indicated that our method had a strong ability to locate the densely positioned somas and strong robustness of the key parameter for the localization. From the analysis of the experimental datasets, we demonstrated that our method was effective at locating somas from large-scale and complicated datasets, and was superior to current state-of-the-art methods for the localization of densely positioned somas. CONCLUSIONS: Our method effectively located somas from large-scale and complicated datasets. Furthermore, we demonstrated the strong robustness of the key parameter for the localization and its effectiveness at a low signal-to-noise ratio (SNR) level. Thus, the method provides an effective tool for the neuroscience community to quantify the spatial distribution of neurons and the morphologies of somas.

Network pharmacological analysis on the mechanism of Linggui Zhugan decoction for nonalcoholic fatty liver disease.

Nonalcoholic fatty liver disease (NAFLD), represents a chronic progressive disease that imposes a significant burden on patients and the healthcare system. Linggui Zhugan decoction (LGZGD) plays a substantial role in treating NAFLD, but its exact molecular mechanism is unknown. Using network pharmacology, this study aimed to investigate the mechanism of action of LGZGD in treating NAFLD. Active ingredients and targets were identified through the integration of data from the TCMSP, GEO, GeneCards, and OMIM databases. Cytoscape 3.9.1 software, in conjunction with the STRING platform, was employed to construct network diagrams and screen core targets. The enrichment analysis of gene ontology and the Kyoto Encyclopedia of Genes and Genomes pathways were conducted by using the R. Molecular docking of the active ingredients and core targets was performed with AutoDock Vina software. We obtained 93 and 112 active ingredients and potential targets using the bioinformatic analysis of LGZGD in treating NAFLD. The primary ingredients of LGZGD included quercetin, kaempferol, and naringenin. The core targets were identified AKT1, MYC, HSP90AA1, HIF1A, ESR1, TP53, and STAT3. Gene ontology function enrichment analysis revealed associations with responses to nutrient and oxygen levels, nuclear receptor activity, and ligand-activated transcription factor activity. Kyoto Encyclopedia of Genes and Genomes signaling pathway analysis implicated the involvement of the PI3K-Akt, IL-17, TNF, Th17 cell differentiation, HIF-1, and TLR signaling pathways. Molecular docking studies indicated strong binding affinities between active ingredients and targets. LGZGD intervenes in NAFLD through a multi-ingredient, multi-target, and multi-pathway approach. Treatment with LGZGD can improve insulin resistance, oxidative stress, inflammation, and lipid metabolism associated with NAFLD.

A Clinical Bacterial Dataset for Deep Learning in Microbiological Rapid On-Site Evaluation.

Microbiological Rapid On-Site Evaluation (M-ROSE) is based on smear staining and microscopic observation, providing critical references for the diagnosis and treatment of pulmonary infectious disease. Automatic identification of pathogens is the key to improving the quality and speed of M-ROSE. Recent advancements in deep learning have yielded numerous identification algorithms and datasets. However, most studies focus on artificially cultured bacteria and lack clinical data and algorithms. Therefore, we collected Gram-stained bacteria images from lower respiratory tract specimens of patients with lung infections in Chinese PLA General Hospital obtained by M-ROSE from 2018 to 2022 and desensitized images to produce 1705 images (4,912 × 3,684 pixels). A total of 4,833 cocci and 6,991 bacilli were manually labelled and differentiated into negative and positive. In addition, we applied the detection and segmentation networks for benchmark testing. Data and benchmark algorithms we provided that may benefit the study of automated bacterial identification in clinical specimens.

Does acupuncture improve the metabolic outcomes of obese/overweight children and adolescents?: A systematic review and meta-analysis.

BACKGROUND: Although increasing evidence has revealed the efficacy of acupuncture in obesity/overweight, actual improvement in metabolism in children and adolescents is unclear. Therefore, we conducted a meta-analysis to evaluate this correlation. METHODS: A comprehensive search was conducted using multiple databases, including Medline, Cochrane, Embase, Web of Science, Chinese Biomedical Literature Database, China National Knowledge Infrastructure, Chinese Scientific Journal Database, and Wan-fang Data, to identify relevant randomized controlled trials published before February 1, 2023. General information and data for the descriptive and quantitative analyses were extracted. RESULTS: Fifteen randomized controlled trials of 1288 obese/overweight children and teenagers were included. All the trials were conducted in China and South Korea. Regarding quality assessment, no other significant risk of bias was found. The acupuncture groups were more likely to have improved metabolic indicators of obesity/overweight than the control groups, in terms of body mass index (standardized mean difference [SMD] = -0.45, 95% confidence interval [CI]: -0.69 to -0.21, I2 = 71.4%), body weight (SMD = -0.48, 95% CI: -0.92 to -0.05, I2 = 84.9%), and serum leptin (SMD = -0.34, 95% CI: -0.58 to -0.10, I2 = 91.8%). The subgroup analysis showed that for body mass index, the results were consistent regardless of the intervention duration, body acupuncture or auricular acupuncture combined with other interventions. CONCLUSION: Our results suggest that acupuncture is effective in improving metabolic outcomes of obese/overweight children and adolescents. Owing to the limited number of trials included in this study, the results should be interpreted with caution.

PALMER: a method capable of parallel localization of multiple emitters for high-density localization microscopy.

Developing methods for high-density localization of multiple emitters is a promising approach for enhancing the temporal resolution of localization microscopy while maintaining a desired spatial resolution, but the widespread use of this approach is thus far mainly obstructed by the slow image analysis speed. Here we present a high-density localization method based on the combination of Graphics Processing Unit (GPU) parallel computation, multiple-emitter fitting, and model recommendation via Bayesian Information Criterion (BIC). This method, called PALMER, exhibits satisfactory localization accuracy comparable with the previous reported SSM_BIC method, while executes more than two orders of magnitudes faster. Meanwhile, compared to the conventional localization microscopy which is based on sparse emitter localization, high-density localization microscopy based the PALMER method allows a speed gain of up to ~14-fold in obtaining a super-resolution image with the same Nyquist resolution.

Minimizing Probability Graph Connectivity Cost for Discontinuous Filamentary Structures Tracing in Neuron Image.

Neuron tracing from optical image is critical in understanding brain function in diseases. A key problem is to trace discontinuous filamentary structures from noisy background, which is commonly encountered in neuronal and some medical images. Broken traces lead to cumulative topological errors, and current methods were hard to assemble various fragmentary traces for correct connection. In this paper, we propose a graph connectivity theoretical method for precise filamentary structure tracing in neuron image. First, we build the initial subgraphs of signals via a region-to-region based tracing method on CNN predicted probability. CNN technique removes noise interference, whereas its prediction for some elongated fragments is still incomplete. Second, we reformulate the global connection problem of individual or fragmented subgraphs under heuristic graph restrictions as a dynamic linear programming function via minimizing graph connectivity cost, where the connected cost of breakpoints are calculated using their probability strength via minimum cost path. Experimental results on challenging neuronal images proved that the proposed method outperformed existing methods and achieved similar results of manual tracing, even in some complex discontinuous issues. Performances on vessel images indicate the potential of the method for some other tubular objects tracing.

Dual supervised sampling networks for real-time segmentation of cervical cell nucleus.

The morphology of the cervical cell nucleus is the most important consideration for pathological cell identification. And a precise segmentation of the cervical cell nucleus determines the performance of the final classification for most traditional algorithms and even some deep learning-based algorithms. Many deep learning-based methods can accurately segment cervical cell nuclei but will cost lots of time, especially when dealing with the whole-slide image (WSI) of tens of thousands of cells. To address this challenge, we propose a dual-supervised sampling network structure, in which a supervised-down sampling module uses compressed images instead of original images for cell nucleus segmentation, and a boundary detection network is introduced to supervise the up-sampling process of the decoding layer for accurate segmentation. This strategy dramatically reduces the convolution calculation in image feature extraction and ensures segmentation accuracy. Experimental results on various cervical cell datasets demonstrate that compared with UNet, the inference speed of the proposed network is increased by 5 times without losing segmentation accuracy. The codes and datasets are available at https://github.com/ldrunning/DSSNet.

Super-resolution Segmentation Network for Reconstruction of Packed Neurites.

Neuron reconstruction can provide the quantitative data required for measuring the neuronal morphology and is crucial in brain research. However, the difficulty in reconstructing dense neurites, wherein massive labor is required for accurate reconstruction in most cases, has not been well resolved. In this work, we provide a new pathway for solving this challenge by proposing the super-resolution segmentation network (SRSNet), which builds the mapping of the neurites in the original neuronal images and their segmentation in a higher-resolution (HR) space. During the segmentation process, the distances between the boundaries of the packed neurites are enlarged, and only the central parts of the neurites are segmented. Owing to this strategy, the super-resolution segmented images are produced for subsequent reconstruction. We carried out experiments on neuronal images with a voxel size of 0.2 µm × 0.2 µm × 1 µm produced by fMOST. SRSNet achieves an average F1 score of 0.88 for automatic packed neurites reconstruction, which takes both the precision and recall values into account, while the average F1 scores of other state-of-the-art automatic tracing methods are less than 0.70.

High-density localization of active molecules using Structured Sparse Model and Bayesian Information Criterion.

Localization-based super-resolution microscopy (or called localization microscopy) rely on repeated imaging and localization of active molecules, and the spatial resolution enhancement of localization microscopy is built upon the sacrifice of its temporal resolution. Developing algorithms for high-density localization of active molecules is a promising approach to increase the speed of localization microscopy. Here we present a new algorithm called SSM_BIC for such purpose. The SSM_BIC combines the advantages of the Structured Sparse Model (SSM) and the Bayesian Information Criterion (BIC). Through simulation and experimental studies, we evaluate systematically the performance between the SSM_BIC and the conventional Sparse algorithm in high-density localization of active molecules. We show that the SSM_BIC is superior in processing single molecule images with weak signal embedded in strong background.

Foreground Estimation in Neuronal Images With a Sparse-Smooth Model for Robust Quantification.

3D volume imaging has been regarded as a basic tool to explore the organization and function of the neuronal system. Foreground estimation from neuronal image is essential in the quantification and analysis of neuronal image such as soma counting, neurite tracing and neuron reconstruction. However, the complexity of neuronal structure itself and differences in the imaging procedure, including different optical systems and biological labeling methods, result in various and complex neuronal images, which greatly challenge foreground estimation from neuronal image. In this study, we propose a robust sparse-smooth model (RSSM) to separate the foreground and the background of neuronal image. The model combines the different smoothness levels of the foreground and the background, and the sparsity of the foreground. These prior constraints together contribute to the robustness of foreground estimation from a variety of neuronal images. We demonstrate the proposed RSSM method could promote some best available tools to trace neurites or locate somas from neuronal images with their default parameters, and the quantified results are similar or superior to the results that generated from the original images. The proposed method is proved to be robust in the foreground estimation from different neuronal images, and helps to improve the usability of current quantitative tools on various neuronal images with several applications.

Automated Neuron Tracing Using Content-Aware Adaptive Voxel Scooping on CNN Predicted Probability Map.

Neuron tracing, as the essential step for neural circuit building and brain information flow analyzing, plays an important role in the understanding of brain organization and function. Though lots of methods have been proposed, automatic and accurate neuron tracing from optical images remains challenging. Current methods often had trouble in tracing the complex tree-like distorted structures and broken parts of neurite from a noisy background. To address these issues, we propose a method for accurate neuron tracing using content-aware adaptive voxel scooping on a convolutional neural network (CNN) predicted probability map. First, a 3D residual CNN was applied as preprocessing to predict the object probability and suppress high noise. Then, instead of tracing on the binary image produced by maximum classification, an adaptive voxel scooping method was presented for successive neurite tracing on the probability map, based on the internal content properties (distance, connectivity, and probability continuity along direction) of the neurite. Last, the neuron tree graph was built using the length first criterion. The proposed method was evaluated on the public BigNeuron datasets and fluorescence micro-optical sectioning tomography (fMOST) datasets and outperformed current state-of-art methods on images with neurites that had broken parts and complex structures. The high accuracy tracing proved the potential of the proposed method for neuron tracing on large-scale.

StainNet: A Fast and Robust Stain Normalization Network.

Stain normalization often refers to transferring the color distribution to the target image and has been widely used in biomedical image analysis. The conventional stain normalization usually achieves through a pixel-by-pixel color mapping model, which depends on one reference image, and it is hard to achieve accurately the style transformation between image datasets. In principle, this difficulty can be well-solved by deep learning-based methods, whereas, its complicated structure results in low computational efficiency and artifacts in the style transformation, which has restricted the practical application. Here, we use distillation learning to reduce the complexity of deep learning methods and a fast and robust network called StainNet to learn the color mapping between the source image and the target image. StainNet can learn the color mapping relationship from a whole dataset and adjust the color value in a pixel-to-pixel manner. The pixel-to-pixel manner restricts the network size and avoids artifacts in the style transformation. The results on the cytopathology and histopathology datasets show that StainNet can achieve comparable performance to the deep learning-based methods. Computation results demonstrate StainNet is more than 40 times faster than StainGAN and can normalize a 100,000 × 100,000 whole slide image in 40 s.

GTree: an Open-source Tool for Dense Reconstruction of Brain-wide Neuronal Population.

Recent technological advancements have facilitated the imaging of specific neuronal populations at the single-axon level across the mouse brain. However, the digital reconstruction of neurons from a large dataset requires months of manual effort using the currently available software. In this study, we develop an open-source software called GTree (global tree reconstruction system) to overcome the above-mentioned problem. GTree offers an error-screening system for the fast localization of submicron errors in densely packed neurites and along with long projections across the whole brain, thus achieving reconstruction close to the ground truth. Moreover, GTree integrates a series of our previous algorithms to significantly reduce manual interference and achieve high-level automation. When applied to an entire mouse brain dataset, GTree is shown to be five times faster than widely used commercial software. Finally, using GTree, we demonstrate the reconstruction of 35 long-projection neurons around one injection site of a mouse brain. GTree is also applicable to large datasets (10 TB or higher) from various light microscopes.

Robust whole slide image analysis for cervical cancer screening using deep learning.

Computer-assisted diagnosis is key for scaling up cervical cancer screening. However, current recognition algorithms perform poorly on whole slide image (WSI) analysis, fail to generalize for diverse staining and imaging, and show sub-optimal clinical-level verification. Here, we develop a progressive lesion cell recognition method combining low- and high-resolution WSIs to recommend lesion cells and a recurrent neural network-based WSI classification model to evaluate the lesion degree of WSIs. We train and validate our WSI analysis system on 3,545 patient-wise WSIs with 79,911 annotations from multiple hospitals and several imaging instruments. On multi-center independent test sets of 1,170 patient-wise WSIs, we achieve 93.5% Specificity and 95.1% Sensitivity for classifying slides, comparing favourably to the average performance of three independent cytopathologists, and obtain 88.5% true positive rate for highlighting the top 10 lesion cells on 447 positive slides. After deployment, our system recognizes a one giga-pixel WSI in about 1.5 min.

Ultra-fast, high-precision image analysis for localization-based super resolution microscopy.

Localization-based super resolution microscopy holds superior performances in live cell imaging, but its widespread use is thus far mainly hindered by the slow image analysis speed. Here we show a powerful image analysis method based on the combination of the maximum likelihood algorithm and a Graphics Processing Unit (GPU). Results indicate that our method is fast enough for real-time processing of experimental images even from fast EMCCD cameras working at full frame rate without compromising localization precision or field of view. This newly developed method is also capable of revealing movements from the images immediately after data acquisition, which is of great benefit to live cell imaging.

Weakly Supervised Learning of 3D Deep Network for Neuron Reconstruction.

Digital reconstruction or tracing of 3D tree-like neuronal structures from optical microscopy images is essential for understanding the functionality of neurons and reveal the connectivity of neuronal networks. Despite the existence of numerous tracing methods, reconstructing a neuron from highly noisy images remains challenging, particularly for neurites with low and inhomogeneous intensities. Conducting deep convolutional neural network (CNN)-based segmentation prior to neuron tracing facilitates an approach to solving this problem via separation of weak neurites from a noisy background. However, large manual annotations are needed in deep learning-based methods, which is labor-intensive and limits the algorithm's generalization for different datasets. In this study, we present a weakly supervised learning method of a deep CNN for neuron reconstruction without manual annotations. Specifically, we apply a 3D residual CNN as the architecture for discriminative neuronal feature extraction. We construct the initial pseudo-labels (without manual segmentation) of the neuronal images on the basis of an existing automatic tracing method. A weakly supervised learning framework is proposed via iterative training of the CNN model for improved prediction and refining of the pseudo-labels to update training samples. The pseudo-label was iteratively modified via mining and addition of weak neurites from the CNN predicted probability map on the basis of their tubularity and continuity. The proposed method was evaluated on several challenging images from the public BigNeuron and Diadem datasets, to fMOST datasets. Owing to the adaption of 3D deep CNNs and weakly supervised learning, the presented method demonstrates effective detection of weak neurites from noisy images and achieves results similar to those of the CNN model with manual annotations. The tracing performance was significantly improved by the proposed method on both small and large datasets (>100 GB). Moreover, the proposed method proved to be superior to several novel tracing methods on original images. The results obtained on various large-scale datasets demonstrated the generalization and high precision achieved by the proposed method for neuron reconstruction.

Brain-Wide Shape Reconstruction of a Traced Neuron Using the Convex Image Segmentation Method.

Neuronal shape reconstruction is a helpful technique for establishing neuron identity, inferring neuronal connections, mapping neuronal circuits, and so on. Advances in optical imaging techniques have enabled data collection that includes the shape of a neuron across the whole brain, considerably extending the scope of neuronal anatomy. However, such datasets often include many fuzzy neurites and many crossover regions that neurites are closely attached, which make neuronal shape reconstruction more challenging. In this study, we proposed a convex image segmentation model for neuronal shape reconstruction that segments a neurite into cross sections along its traced skeleton. Both the sparse nature of gradient images and the rule that fuzzy neurites usually have a small radius are utilized to improve neuronal shape reconstruction in regions with fuzzy neurites. Because the model is closely related to the traced skeleton point, we can use this relationship for identifying neurite with crossover regions. We demonstrated the performance of our model on various datasets, including those with fuzzy neurites and neurites with crossover regions, and we verified that our model could robustly reconstruct the neuron shape on a brain-wide scale.

Identifying Weak Signals in Inhomogeneous Neuronal Images for Large-Scale Tracing of Sparsely Distributed Neurites.

Tracing neurites constitutes the core of neuronal morphology reconstruction, a key step toward neuronal circuit mapping. Modern optical-imaging techniques allow observation of nearly complete mouse neuron morphologies across brain regions or even the whole brain. However, high-level automation reconstruction of neurons, i.e., the reconstruction with a few of manual edits requires discrimination of weak foreground points from the inhomogeneous background. We constructed an identification model, where empirical observations made from neuronal images were summarized into rules for designing feature vectors that to classify foreground and background, and a support vector machine (SVM) was used to learn these feature vectors. We embedded this constructed SVM classifier into a previously developed tool, SparseTracer, to obtain SparseTracer-Learned Feature Vector (ST-LFV). ST-LFV can trace sparsely distributed neurites with weak signals (contrast-to-noise ratio < 1.5) against an inhomogeneous background in datasets imaged by widely used light-microscopy techniques like confocal microscopy and two-photon microscopy. Moreover, 12 sub-blocks were extracted from different brain regions. The average recall and precision rates were 99% and 97%, respectively. These results indicated that ST-LFV is well suited for weak signal identification with varying image characteristics. We also applied ST-LFV to trace long-range neurites from images where neurites are sparsely distributed but their image intensities are weak in some cases. When tracing this long-range neurites, manual edit was required once to obtain results equivalent to the ground truth, compared with 20 times of manual edits required by SparseTracer. This improvement in the level of automatic reconstruction indicates that ST-LFV has the potential to rapidly reconstruct sparsely distributed neurons at the large scale.