High-resolution Microscopy Images Research Articles

Real-Time Analysis of Lipid Droplet Morpho-Chemical Dynamics in Living Human Hepatocytes via Phase-Guided Raman Sampling.

Lipid droplets (LDs) are highly dynamic organelles, undertaking many important functions such as maintaining lipid metabolism and cellular homeostasis. Traditional methods to analyze LD dynamics focus on morphological changes, while chemical dynamics cannot be easily probed with traditional analytical chemistry techniques. To overcome this challenge, we show here how our phase-guided Raman sampling method, where high-resolution phase microscopy images direct a Raman sampling beam, can perform label-free, multimodal characterization of LD dynamics in living cells at both the single-cell and single-LD levels with submicron accuracy and high temporal resolution. We demonstrate the study of the morphological-compositional dynamics of human hepatocellular carcinoma cells (PLC cells) under different environmental conditions and with and without fatty acid supplementation, providing insight into LD heterogeneity and heterogeneity of response. Finally, we introduce a measurement method for the dynamics of cell-average LD composition, which can quickly and accurately characterize the lipid dynamics at the single-cell level with <30 s temporal resolution. The results here show the promise of the phase-guided Raman sampling method for dynamic morpho-chemical profiling of organelle populations.

Image inpainting for periodic discrete density defects via frequency analysis and an adaptive transformer-GAN network

Image inpainting based on deep learning has made significant progress in addressing regular and coherent irregular defects. However, little has been studied on periodic discrete density (PDD) defects that are prevalent in microscopic images obtained by advanced instruments like transmission electron microscopes (TEM) and scanning tunneling microscopes (STM). The PDD defects usually introduce low-frequency noise in the fast Fourier transform (FFT) images, preventing the extraction of useful information particularly in the low-frequency regions. Despite its significant impact, no method has been reported to date to efficiently remove the PDD-induced noise from the FFT of high-resolution microscopic images. In this study, we introduced a novel GAN-based two-stage network (FGTNet), a novel coarse-to-fine inpainting framework, which is built upon the architecture of Generative Adversarial Networks (GAN) and transformer blocks. By integrating the information from both frequency and spatial domains, contextual structures are preserved and high-frequency details are generated in our method. We also proposed an adaptive-window transformer block (A-LeWin) to enhance the spatial feature representation and to fully use the information around the defects. To validate our approach, we constructed a specialized microscopic image dataset with 2730 training samples and 105 testing samples. For comparison, we also extended the experiments to the public Describable Texture Dataset (DTD) and coherence defects that are often discussed in the field of image inpainting. The experiment results indicate that our method performs well on six pixel-level and perceptual-level metrics, and shows the best performance and visual effect of coherent texture.

From two segments and beyond: Investigating the onset of regeneration in Syllis malaquini.

Annelids feature a diverse range of regenerative abilities, but complete whole-body regeneration is less common, particularly in the context of the head and anterior body regeneration. This study provides a detailed morphological description of Syllis malaquini regenerative abilities. By replicating previous experiments and performing diverse surgical procedures, we explored the capacity of this species for whole-body regeneration. We detailed the precise timing of regeneration of particular structures such as the eyes, proventricle, pharyngeal tooth, nuchal organs, and body pigmentation after amputation. Our high-resolution scanning electron microscopy and confocal laser-scanning microscopy images provide details of the blastema region, revealing that while anal opening remains in connection to the exterior environment, oral opening is formed "de novo" during blastema differentiation. Additionally, we performed amputations to isolate fragments consisting of one, two, and three segments from the intestinal trunk region. We found that S. malaquini requires at least two to three segments to successfully regenerate the whole body. In addition, we verified a variable capacity to regenerate depending upon the gut region, with structures of the foregut greatly impairing some steps of the regenerative process. Our work notably addresses the gap in knowledge concerning gut formation and its impact on regenerative capabilities. Ongoing research is crucial to unravel the role of gut tissue specificity and plasticity during regeneration in annelids, and particularly in syllids.

Integrated Model for Segmentation of Glomeruli in Kidney Images

Kidney diseases, especially those that affect the glomeruli, have become more common worldwide in recent years. Accurate and early detection of glomeruli is critical for accurately diagnosing kidney problems and determining the most effective treatment options. Our study proposed an advanced model, FResMRCNN, an enhanced version of Mask R-CNN, for automatically detecting and segmenting the glomeruli in PAS-stained human kidney images. The model integrates the power of FPN with a ResNet101 backbone, which was selected after assessing seven different backbone architectures. The integration of FPN and ResNet101 into the FResMRCNN model improves glomeruli detection and segmentation accuracy and stability by representing multi-scale features. We trained and tested our model using the HuBMAP Kidney dataset, which contains high-resolution PAS-stained microscopy images. During the study, the effectiveness of our proposed model is examined by generating bounding boxes and predicted masks of glomeruli. The performance of the FResMRCNN model is evaluated using three performance metrics, including the Dice coefficient, Jaccard index, and binary cross-entropy loss, which show promising results in accurately segmenting glomeruli.

WoodYOLO: A Novel Object Detector for Wood Species Detection in Microscopic Images

Wood species identification plays a crucial role in various industries, from ensuring the legality of timber products to advancing ecological conservation efforts. This paper introduces WoodYOLO, a novel object detection algorithm specifically designed for microscopic wood fiber analysis. Our approach adapts the YOLO architecture to address the challenges posed by large, high-resolution microscopy images and the need for high recall in localization of the cell type of interest (vessel elements). Our results show that WoodYOLO significantly outperforms state-of-the-art models, achieving performance gains of 12.9% and 6.5% in F2 score over YOLOv10 and YOLOv7, respectively. This improvement in automated wood cell type localization capabilities contributes to enhancing regulatory compliance, supporting sustainable forestry practices, and promoting biodiversity conservation efforts globally.

Revisiting the taxonomy of Korean Ischnochiton species (Polyplacophora, Ischnochitonidae) based on a combined analysis of morphological and molecular data.

Chiton species belonging to the genus Ischnochiton J. E. Gray, 1847 are commonly found in intertidal rocky shores worldwide, with the exception of the northern Atlantic and Arctic oceans. Ischnochiton species are characterised by imbricate girdle scales that are uniform in size, rounded, sculpted with striae or occasionally smooth. However, their species-level taxonomy is complicated due to the high variation in their shell microstructures. Despite more than a hundred species reported worldwide, taxonomic studies of this group remain relatively unexplored in Korean waters, with only a few species recorded to date. In this study, we compared the microstructural characteristics of tegmentum sculpture, girdle scales and radula amongst four Korean Ischnochiton species using high-resolution microscopic images and a scanning electron microscope (SEM). Along with mtDNA cox1 sequence comparison, a comprehensive analysis of their morphology revealed that I.hayamii Owada, 2018 was identified for the first time in Korean waters. This species is morphologically distinguished by its small body size of adults, smooth lateral areas on valves and small perinotum scales sculptured with weak longitudinal ribs. Phylogenetic analysis of the mtDNA cox1 sequence provides distinct resolution at the species level, but interrelationships amongst Ischnochiton species remain unresolved. Results from the morphological and molecular analyses presented in this study offer valuable taxonomic information for accurate species identification amongst closely-related Ischnochiton species.

Enhanced MALDI-2 Sensitivity with Reflecting Post-Ionization Laser for High-Resolution MS Imaging Combined with Real-Time Microscope Imaging.

Laser-induced matrix-assisted laser desorption/ionization post-ionization (MALDI-2) could improve the MALDI sensitivity of biological metabolites by over 1 order of magnitude. Herein, we demonstrate that MALDI-2 sensitivity can be further enhanced with reflecting post-ionization laser that multiplies the intersection times between laser and MALDI plume. This method, which we named MALDI-2+, typically brought over 2 times sensitivity improvement from conventional MALDI-2. Advancing in sensitivity thereby prompted us to pursue higher mass spectrometry imaging (MSI) spatial resolution. A dedicated T-shaped ion guide was designed to allow perpendicular incidence of ablation laser in reflection geometry MALDI. Although 8-10 μm pixel was used in MALDI imaging due to the limited precision of the motorized stage, the laser spot diameter could be down to 2.5 μm for potentially higher spatial resolution. In addition, this ion source enabled real-time and high-quality microscope imaging from backward of the sample plate. Beneficially, we were able to monitor the actual laser spot condition in real time as well as obtain high-resolution microscopic sample images that inherently register with MSI images. All of these benefits have been demonstrated by analyzing standard samples and imaging of cells. We believe that the enhancement in sensitivity, spatial resolution, and microscope capacity of our design could facilitate spatial omics studies.

Intraoperative margin assessment with near real time pathology during partial gland ablation of prostate cancer: A feasibility study

BackgroundIn-field or in-margin recurrence after partial gland cryosurgical ablation (PGCA) of prostate cancer (PCa) remains a limitation of the paradigm. Stimulated Raman histology (SRH) is a novel microscopic technique allowing real time, label-free, high-resolution microscopic images of unprocessed, un-sectioned tissue which can be interpreted by humans or artificial intelligence (AI). We evaluated surgical team and AI interpretation of SRH for real-time pathologic feedback in the planning and treatment of PCa with PGCA. MethodsAbout 12 participants underwent prostate mapping biopsies during PGCA of their PCa between January and June 2022. Prostate biopsies were immediately scanned in a SRH microscope at 20 microns depth using 2 Raman shifts to create SRH images which were interpreted by the surgical team intraoperatively to guide PGCA, and retrospectively assessed by AI. The cores were then processed, hematoxylin and eosin stained as per normal pathologic protocols and used for ground truth pathologic assessment. ResultsSurgical team interpretation of SRH intraoperatively revealed 98.1% accuracy, 100% sensitivity, 97.3% specificity for identification of PCa, while AI showed a 97.9% accuracy, 100% sensitivity and 97.5% specificity for identification of clinically significant PCa. 3 participants’ PGCA treatments were modified after SRH visualized PCa adjacent to an expected MRI predicted tumor margin or at an untreated cryosurgical margin. ConclusionSRH allows for accurate rapid identification of PCa in PB by a surgical team interpretation or AI. PCa tumor mapping and margin assessment during PGCA appears to be feasible and accurate. Further studies evaluating impact on clinical outcomes are warranted.

Deep Learning Assisted High Resolution Microscopy Image Processing for Phase Segmentation in Functional Composite Materials

In the domain of battery research, the processing of high-resolution microscopy images is a challenging task, as it involves dealing with complex images and requires a prior understanding of the components involved. The utilization of deep learning methodologies for image analysis has attracted considerable interest in recent years, with multiple investigations employing such techniques for image segmentation and analysis within the realm of battery research. However, the automated analysis of high-resolution microscopy images for detecting phases and components in composite materials is still an underexplored area.The presentation discusses the formulation of a sophisticated deep learning-assisted workflow tailored for the meticulous processing of high throughput, high-resolution microscopy images to detect, map and analyze the evolution of periodic components from a stack of high-resolution Transmission Electron Microscopy (TEM) image. The developed methodology employs deep learning techniques and utilizes Fast Fourier Transform (FFT) patterns extracted from TEM images to analyze feature positions and ascertain periodic components. The approach incorporates innovative strategies to process high-resolution images, capitalizing on the symmetry within FFT patterns to enhance model performance. This methodology streamlines the detection and mapping of components while the intensity profiles derived from the frames provide valuable insights into the evolution of periodic components within the sample during the imaging period.High-resolution images obtained through a beam damage analysis investigation of lithium fluoride (LiF), a prevalent constituent within the solid-electrolyte interphase (SEI) of cycled lithium metal anodes, were employed to assess the program's scalability and robustness. The study elucidated decomposition products and their spatial distribution. Furthermore, the intensity profile of periodic components detected across multiple frames aided in evaluating the beam damage mechanism of the LiF component.Our research has resulted in an open-source Python GUI program that the research community can freely access and experiment with. Figure 1

Chemical imaging unveils mitochondria as the major site of medicinal biguanide accumulation within cells

Metformin (MET), a commonly prescribed medication for managing type 2 diabetes, has demonstrated various beneficial effects beyond its primary anti-diabetic efficacy. However, the mechanism underlying MET activity and its distribution within organelles remain largely unknown. In this study, we integrate multiple technologies, including chemical labeling, immunostaining, and high-resolution microscopy imaging, to visualize the accumulation of MET in organelles of cultured cells. To achieve this objective, an alkynylated MET probe is developed that preserves biological activity similar to biguanide drugs. As determined by biorthogonal chemical labeling and imaging, the MET probe selectively localizes to substructures within cells, contrasting with its probe control. Furthermore, the MET probe can be competitively and efficiently washed out through biguanide administration, demonstrating the specific activity of this probe in monitoring the cellular dynamics of biguanide drugs. Our results indicate that the MET probe can reach near-saturated concentrations within 2 h and is rapidly eliminated within an additional 2 h once the exogenous source of the drug is removed. Furthermore, we reveal that the MET probe primarily accumulates in mitochondria, particularly within the mitochondrial matrix, and has a minor presence in other organelles, such as lysosomes and endosomes. Together, this study provides the first view of the subcellular localization of MET and lays the foundation for future investigations on its molecular targets and mechanisms of action in promoting human health.

Aerosol dosimetry in the whole conducting zone of a murine left-lung using CF-PD and LSFM images

Aerosol dosimetry in respiratory airways is relevant for pulmonary drug delivery and inhalation toxicology. Consequently, computational fluid-particle dynamics (CF-PD) modelling of pulmonary aerosol delivery is an active research field. Additionally, mice are the most commonly used animals in medical research. Technological advances have provided information on whole mice lung morphologies with unprecedented high resolution. Therefore, in this study, we used high-resolution light sheet fluorescent microscopy (LSFM) images of a healthy C57BL/6 mouse lung with a constant air flow rate of 72 ml/min, to extract an anatomical 3-dimensional (3D) geometry of the entire airway tree of the left lung from the primary bronchi to the most distal bronchioles excluding the trachea. The airways were segmented based on an order- and generation-based method. Also, to compare the morphological data and regional deposition, a generation-based investigation including 25 generations was employed in the present model. One-way coupling of CF-PD modeling was applied to model an intubated and mechanically-ventilated mouse. Maximum values of the velocity and vorticity magnitude of 3.2 m/s and 200,000 1/s were reached in the second order, respectively, and maximum pressure and wall shear stress levels were 30 Pa and 3.5 Pa, respectively. Finally, order- and generation-based particle deposition efficiency and dose per lung area were obtained for the particle size range of 1 μm ≤ dp ≤ 10 μm yielding pronounced hotspot deposition patterns mainly near the proximal bifurcations. The results showed a positive correlation between deposition efficiency and particle size due to a size-dependent increase in inertial and gravitational effects. Maximum regional deposition and normalized dose was seen for 10 μm particles in the 1st order of the murine left lung. Smaller peak sizes of deposition efficiency were seen in the third and fourth orders of the mouse left lung due to almost complete loss of the largest particles in lower order airways. It also justifies the close to zero deposition efficiency in the highest orders (fifth to sixth). Both lung morphology as well as total and regional aerosol deposition showed reasonably good agreement with empirical data from the literature. The present CF-PD model with accurate realistic lung morphology, improves our knowledge of airway aerosol deposition hotspots. The obtained modeling method and the qualitative results can be implemented on human airways.

Fast and robust feature-based stitching algorithm for microscopic images

The limited field of view of high-resolution microscopic images hinders the study of biological samples in a single shot. Stitching of microscope images (tiles) captured by the whole-slide imaging (WSI) technique solves this problem. However, stitching is challenging due to the repetitive textures of tissues, the non-informative background part of the slide, and the large number of tiles that impact performance and computational time. To address these challenges, we proposed the Fast and Robust Microscopic Image Stitching (FRMIS) algorithm, which relies on pairwise and global alignment. The speeded up robust features (SURF) were extracted and matched within a small part of the overlapping region to compute the transformation and align two neighboring tiles. In cases where the transformation could not be computed due to an insufficient number of matched features, features were extracted from the entire overlapping region. This enhances the efficiency of the algorithm since most of the computational load is related to pairwise registration and reduces misalignment that may occur by matching duplicated features in tiles with repetitive textures. Then, global alignment was achieved by constructing a weighted graph where the weight of each edge is determined by the normalized inverse of the number of matched features between two tiles. FRMIS has been evaluated on experimental and synthetic datasets from different modalities with different numbers of tiles and overlaps, demonstrating faster stitching time compared to existing algorithms such as the Microscopy Image Stitching Tool (MIST) toolbox. FRMIS outperforms MIST by 481% for bright-field, 259% for phase-contrast, and 282% for fluorescence modalities, while also being robust to uneven illumination.

A deep learning-based model for detecting Leishmania amastigotes in microscopic slides: a new approach to telemedicine

BackgroundLeishmaniasis, an illness caused by protozoa, accounts for a substantial number of human fatalities globally, thereby emerging as one of the most fatal parasitic diseases. The conventional methods employed for detecting the Leishmania parasite through microscopy are not only time-consuming but also susceptible to errors. Therefore, the main objective of this study is to develop a model based on deep learning, a subfield of artificial intelligence, that could facilitate automated diagnosis of leishmaniasis.MethodsIn this research, we introduce LeishFuNet, a deep learning framework designed for detecting Leishmania parasites in microscopic images. To enhance the performance of our model through same-domain transfer learning, we initially train four distinct models: VGG19, ResNet50, MobileNetV2, and DenseNet 169 on a dataset related to another infectious disease, COVID-19. These trained models are then utilized as new pre-trained models and fine-tuned on a set of 292 self-collected high-resolution microscopic images, consisting of 138 positive cases and 154 negative cases. The final prediction is generated through the fusion of information analyzed by these pre-trained models. Grad-CAM, an explainable artificial intelligence technique, is implemented to demonstrate the model’s interpretability.ResultsThe final results of utilizing our model for detecting amastigotes in microscopic images are as follows: accuracy of 98.95 1.4%, specificity of 98 2.67%, sensitivity of 100%, precision of 97.91 2.77%, F1-score of 98.92 1.43%, and Area Under Receiver Operating Characteristic Curve of 99 1.33.ConclusionThe newly devised system is precise, swift, user-friendly, and economical, thus indicating the potential of deep learning as a substitute for the prevailing leishmanial diagnostic techniques.

MicronuclAI: Automated quantification of micronuclei for assessment of chromosomal instability.

Chromosomal instability (CIN) is a hallmark of cancer that drives metastasis, immune evasion and treatment resistance. CIN results from chromosome mis-segregation events during anaphase, as excessive chromatin is packaged in micronuclei (MN), that can be enumerated to quantify CIN. Despite recent advancements in automation through computer vision and machine learning, the assessment of CIN remains a predominantly manual and time-consuming task, thus hampering important work in the field. Here, we present micronuclAI , a novel pipeline for automated and reliable quantification of MN of varying size, morphology and location from DNA-only stained images. In micronucleAI , single-cell crops are extracted from high-resolution microscopy images with the help of segmentation masks, which are then used to train a convolutional neural network (CNN) to output the number of MN associated with each cell. The pipeline was evaluated against manual single-cell level counts by experts and against routinely used MN ratio within the complete image. The classifier was able to achieve a weighted F1 score of 0.937 on the test dataset and the complete pipeline can achieve close to human-level performance on various datasets derived from multiple human and murine cancer cell lines. The pipeline achieved a root-mean-square deviation (RMSE) value of 0.0041, an R 2 of 0.87 and a Pearson's correlation of 0.938 on images obtained at 10X magnification. We tested the approach in otherwise isogenic cell lines in which we genetically dialed up or down CIN rates, and also on a publicly available image data set (obtained at 100X) and achieved an RMSE value of 0.0159, an R 2 of 0.90, and a Pearson's correlation of 0.951. Given the increasing interest in developing therapies for CIN-driven cancers, this method provides an important, scalable, and rapid approach to quantifying CIN on routinely obtained images. We release a GUI-implementation for easy access and utilization of the pipeline.

Microscopic Image Dataset with Segmentation and Detection Labels for Microplastic Analysis in Sewage: Enhancing Research and Environmental Monitoring

We introduce a novel microscopic image dataset augmented with segmentation and detection labels specifically designed for microplastic analysis in sewage environments. Recognizing the increasing concern over microplastics—particles of synthetic polymers smaller than 5 mm—and their detrimental effects on marine ecosystems and human health, our research focuses on enhancing detection and analytical methodologies through advanced computer vision and deep learning techniques. The dataset comprises high-resolution microscopic images of microplastics collected from sewage, meticulously labeled for both segmentation and detection tasks, aiming to facilitate accurate and efficient identification and quantification of microplastic pollution. In addition to dataset development, we present example deep learning models optimized for segmentation and detection of microplastics within complex sewage samples. The models demonstrate significant potential in automating the analysis of microplastic contamination, offering a scalable solution to environmental monitoring challenges. Furthermore, we ensure the accessibility and reproducibility 12 of our research by making the dataset and model codes publicly available, accompanied by detailed 13 documentation on GitHub and LabelBox.

Synergizing Deep Learning-Enabled Preprocessing and Human-AI Integration for Efficient Automatic Ground Truth Generation.

The progress of incorporating deep learning in the field of medical image interpretation has been greatly hindered due to the tremendous cost and time associated with generating ground truth for supervised machine learning, alongside concerns about the inconsistent quality of images acquired. Active learning offers a potential solution to these problems of expanding dataset ground truth by algorithmically choosing the most informative samples for ground truth labeling. Still, this effort incurs the costs of human labeling, which needs minimization. Furthermore, automatic labeling approaches employing active learning often exhibit overfitting tendencies while selecting samples closely aligned with the training set distribution and excluding out-of-distribution samples, which could potentially improve the model's effectiveness. We propose that the majority of out-of-distribution instances can be attributed to inconsistent cross images. Since the FDA approved the first whole-slide image system for medical diagnosis in 2017, whole-slide images have provided enriched critical information to advance the field of automated histopathology. Here, we exemplify the benefits of a novel deep learning strategy that utilizes high-resolution whole-slide microscopic images. We quantitatively assess and visually highlight the inconsistencies within the whole-slide image dataset employed in this study. Accordingly, we introduce a deep learning-based preprocessing algorithm designed to normalize unknown samples to the training set distribution, effectively mitigating the overfitting issue. Consequently, our approach significantly increases the amount of automatic region-of-interest ground truth labeling on high-resolution whole-slide images using active deep learning. We accept 92% of the automatic labels generated for our unlabeled data cohort, expanding the labeled dataset by 845%. Additionally, we demonstrate expert time savings of 96% relative to manual expert ground-truth labeling.

Intravital observation of high-scattering and dense-labeling hepatic tissues using multi-photon fluorescence microscopy.

Achieving high-resolution and large-depth microscopic imaging in vivo under conditions characterized by high-scattering and dense-labeling, as commonly encountered in the liver, poses a formidable challenge. Here, through the optimization of multi-photon fluorescence excitation window, tailored to the unique optical properties of the liver, intravital microscopic imaging of hepatocytes and hepatic blood vessels with high spatial resolution was attained. It's worth noting that resolution degradation caused by tissue scattering of excitation light was mitigated by accounting for moderate tissue self-absorption. Leveraging high-quality multi-photon fluorescence microscopy, we discerned structural and functional alterations in hepatocytes during drug-induced acute liver failure. Furthermore, a reduction in indocyanine green metabolism rates associated with acute liver failure was observed using NIR-II fluorescence macroscopic imaging.

Increasing the Q-factor of resonant cantilevers in magnetic force microscopy through helium gas flow

To obtain high-resolution magnetic force microscopy (MFM) images, it is essential to have a cantilever with a high-quality factor. However, conventional vibrating cantilevers typically have quality factor values in the range of a few hundred, which limits their sensitivity for MFM measurements. To address this limitation, numerous studies have explored methods to enhance the quality factor in different environments, including vacuum, air, and liquid. This study introduces a novel approach for improving the quality factor using flowing helium gas. By selecting helium gas with a low viscosity coefficient, we successfully achieved a higher quality factor (Q-factor) of MFM microcantilever oscillations at room temperature in one atmosphere compared with the Q-factor in air. This provides a potential approach for achieving high-resolution MFM measurements under room temperature conditions. By optimizing the gas flow rate at room temperature in one atmosphere, we successfully obtained a higher MFM cantilever oscillation Q-factor and clearer MFM images compared with the air. The experimental results revealed a long and narrow resonant curve, and the quality factor significantly increased to 778.2, which is 3.8 times higher than that observed in air 205.4. Furthermore, systematic investigations demonstrated the capability of this approach to produce high-resolution MFM images of videotape track patterns under the optimized helium gas flow rate of 60 mm/s.

Deep learning for automated segmentation and counting of hypocotyl and cotyledon regions in mature Pinus radiata D. Don. somatic embryo images.

In commercial forestry and large-scale plant propagation, the utilization of artificial intelligence techniques for automated somatic embryo analysis has emerged as a highly valuable tool. Notably, image segmentation plays a key role in the automated assessment of mature somatic embryos. However, to date, the application of Convolutional Neural Networks (CNNs) for segmentation of mature somatic embryos remains unexplored. In this study, we present a novel application of CNNs for delineating mature somatic conifer embryos from background and residual proliferating embryogenic tissue and differentiating various morphological regions within the embryos. A semantic segmentation CNN was trained to assign pixels to cotyledon, hypocotyl, and background regions, while an instance segmentation network was trained to detect individual cotyledons for automated counting. The main dataset comprised 275 high-resolution microscopic images of mature Pinus radiata somatic embryos, with 42 images reserved for testing and validation sets. The evaluation of different segmentation methods revealed that semantic segmentation achieved the highest performance averaged across classes, achieving F1 scores of 0.929 and 0.932, with IoU scores of 0.867 and 0.872 for the cotyledon and hypocotyl regions respectively. The instance segmentation approach demonstrated proficiency in accurate detection and counting of the number of cotyledons, as indicated by a mean squared error (MSE) of 0.79 and mean absolute error (MAE) of 0.60. The findings highlight the efficacy of neural network-based methods in accurately segmenting somatic embryos and delineating individual morphological parts, providing additional information compared to previous segmentation techniques. This opens avenues for further analysis, including quantification of morphological characteristics in each region, enabling the identification of features of desirable embryos in large-scale production systems. These advancements contribute to the improvement of automated somatic embryogenesis systems, facilitating efficient and reliable plant propagation for commercial forestry applications.

Vascularized organoid-on-a-chip: design, imaging, and analysis.

Vascularized organoid-on-a-chip (VOoC) models achieve substance exchange in deep layers of organoids and provide a more physiologically relevant system in vitro. Common designs for VOoC primarily involve two categories: self-assembly of endothelial cells (ECs) to form microvessels and pre-patterned vessel lumens, both of which include the hydrogel region for EC growth and allow for controlled fluid perfusion on the chip. Characterizing the vasculature of VOoC often relies on high-resolution microscopic imaging. However, the high scattering of turbid tissues can limit optical imaging depth. To overcome this limitation, tissue optical clearing (TOC) techniques have emerged, allowing for 3D visualization of VOoC in conjunction with optical imaging techniques. The acquisition of large-scale imaging data, coupled with high-resolution imaging in whole-mount preparations, necessitates the development of highly efficient analysis methods. In this review, we provide an overview of the chip designs and culturing strategies employed for VOoC, as well as the applicable optical imaging and TOC methods. Furthermore, we summarize the vascular analysis techniques employed in VOoC, including deep learning. Finally, we discuss the existing challenges in VOoC and vascular analysis methods and provide an outlook for future development.