Significantly Enhanced Room-Temperature Ferromagnetism in Multiferroic EuFeO3-δ Thin Films.

Regulating the magnetic properties of multiferroics lays the foundation for their prospective application in spintronic devices. Single-phase multiferroics, such as rare-earth ferrites, are promising candidates; however, they typically exhibit weak magnetism at room temperature (RT). Here, we significantly boosted the RT ferromagnetism of a representative ferrite, EuFeO3, by oxygen defect engineering. Polarized neutron reflectometry and magnetometry measurements reveal that saturation magnetization reaches 0.04 µB/Fe, which is approximately 5 times higher than its bulk phase. Combining the annular bright-field images with theoretical assessment, we unravel the underlying mechanism for magnetic enhancement, in which the decrease in Fe-O-Fe bond angles caused by oxygen vacancies (VO) strengthens magnetic interactions and tilts Fe spins. Furthermore, the internal relationship between magnetism and VO was established by illustrating how the magnetic structure and magnitude change with VO configuration and concentration. Our strategy for regulating magnetic properties can be applied to numerous functional oxide materials.

Improved concordance of challenging human epidermal growth factor receptor 2 dual in-situ hybridisation cases with the use of a digital image analysis algorithm in breast cancer.

AIMS: Accurate assessment of human epidermal growth factor receptor 2 (HER2) expression by HER2 immunohistochemistry and in-situ hybridisation (ISH) is critical for the management of patients with breast cancer. The revised 2018 ASCO/CAP guidelines define 5 groups based on HER2 expression and copy number. Manual pathologist quantification by light microscopy of equivocal and less common HER2 ISH groups (groups 2-4) can be challenging, and there are no data on interobserver variability in reporting of these cases. We sought to determine whether a digital algorithm could improve interobserver variability in the assessment of difficult HER2 ISH cases. METHODS AND RESULTS: HER2 ISH was evaluated in a cohort enriched for less common HER2 patterns using standard light microscopy versus analysis of whole slide images using the Roche uPath HER2 dual ISH image analysis algorithm. Standard microscopy demonstrated significant interobserver variability with a Fleiss's kappa value of 0.471 (fair-moderate agreement) improving to 0.666 (moderate-good) with the use of the algorithm. For HER2 group designation (groups 1-5), there was poor-moderate reliability between pathologists by microscopy [intraclass correlation coefficient (ICC) = 0.526], improving to moderate-good agreement (ICC = 0.763) with the use of the algorithm. In subgroup analysis, the algorithm improved concordance particularly in groups 2, 4 and 5. Time to enumerate cases was also significantly reduced. CONCLUSION: This work demonstrates the potential of a digital image analysis algorithm to improve the concordance of pathologist HER2 amplification status reporting in less common HER2 groups. This has the potential to improve therapy selection and outcomes for patients with HER2-low and borderline HER2-amplified breast cancers.

Auer rods and faggot cells: A review of the history, significance and mimics of two morphological curiosities of enduring relevance.

Myeloid differentiation in blasts is distinguished by the presence of one or more needle-shaped crystalline structures called Auer rods. Auer rods manifest either alone or as faggot cells (containing bundles of Auer rods) in various types of acute myeloid leukemia (AML), myelodysplastic syndromes (MDS) and myelodysplastic/myeloproliferative neoplasms (MDS/MPN). Their presence largely portends a better prognosis in AML (as markers of maturation/differentiation) and upstages cases of MDS and MDS/MPN. Observation of these rods in residual blasts in treated cases of AML indicates an absence of remission. This article traces their historical discovery and examines their pathogenetic intricacies, as well as our current understanding of their relevance in myeloid neoplasms. Studies evaluating their prognostic impact in AML and MDS are catalogued. We also discuss a variety of other hematological and non-hematological neoplasms where structures potentially mistakable for Auer rods have been described. Even as the diagnostic approach to hematological malignancies has evolved from a morphology + cytochemistry + immunophenotyping-dependent one in the last century to a predominantly molecular genetics-based classification currently, and even as high-throughput sequencing and structural variation detection techniques surpass morphology in detecting clinically-relevant sub-categories of similar-appearing tumours, we review these curious microscopic structures that have withstood the test of time with respect to their diagnostic relevance.

Utility of fluorescence imitating brightfield imaging microscopy for the diagnosis of feline chronic enteropathy.

Fluorescence imitating brightfield imaging (FIBI) is a novel microscopy method that allows for real-time, nondestructive, slide-free tissue imaging of fresh, formalin-fixed, or paraffin-embedded tissue. The nondestructive nature of the technology permits tissue preservation for downstream analyses. The objective of this observational study was to assess the utility of FIBI compared with conventional hematoxylin and eosin (H&E)-stained histology slides in feline gastrointestinal histopathology. Formalin-fixed paraffin-embedded full-thickness small intestinal tissue specimens from 50 cases of feline chronic enteropathy were evaluated. The ability of FIBI to evaluate predetermined morphological features (epithelium, villi, crypts, lacteals, fibrosis, submucosa, and muscularis propria) and inflammatory cells was assessed on a 3-point scale (0 = FIBI cannot identify the feature; 1 = FIBI can identify the feature; 2 = FIBI can identify the feature with more certainty than H&E). H&E and FIBI images were also scored according to World Small Animal Veterinary Association (WSAVA) Gastrointestinal Standardization Group guidelines. FIBI identified morphological features with similar or, in some cases, higher confidence compared with H&E images. The identification of inflammatory cells was less consistent. FIBI and H&E images showed an overall poor agreement with regard to the assigned WSAVA scores. While FIBI showed an equal or better ability to identify morphological features in intestinal biopsies, its ability to identify inflammatory cells is currently inferior compared with H&E-based imaging. Future studies on the utility of FIBI as a diagnostic tool for noninflammatory histopathologic lesions are warranted.

Automated Grain Boundary Detection for Bright-Field Transmission Electron Microscopy Images via U-Net.

Quantification of microstructures is crucial for understanding processing-structure and structure-property relationships in polycrystalline materials. Delineating grain boundaries in bright-field transmission electron micrographs, however, is challenging due to complex diffraction contrast in images. Conventional edge detection algorithms are inadequate; instead, manual tracing is usually required. This study demonstrates the first successful machine learning approach for grain boundary detection in bright-field transmission electron micrographs. The proposed methodology uses a U-Net convolutional neural network trained on carefully constructed data from bright-field images and hand tracings available from prior studies, combined with targeted postprocessing algorithms to preserve fine features of interest. The image processing pipeline accurately estimates grain boundary positions, avoiding segmentation in regions with intragrain contrast and identifying low-contrast boundaries. Our approach is validated by directly comparing microstructural markers (i.e., grain centroids) identified in U-Net predictions with those identified in hand tracings; furthermore, the grain size distributions obtained from the two techniques show notable overlap when compared using t-test, Kolmogorov-Smirnov test, and Cramér-von Mises test. The technique is then successfully applied to interpret new microstructures having different image characteristics from the training data, with preliminary results from platinum and palladium microstructures presented, highlighting the versatility of our approach for grain boundary identification in bright-field micrographs.

A Weakly Supervised Learning Method for Cell Detection and Tracking Using Incomplete Initial Annotations.

The automatic detection of cells in microscopy image sequences is a significant task in biomedical research. However, routine microscopy images with cells, which are taken during the process whereby constant division and differentiation occur, are notoriously difficult to detect due to changes in their appearance and number. Recently, convolutional neural network (CNN)-based methods have made significant progress in cell detection and tracking. However, these approaches require many manually annotated data for fully supervised training, which is time-consuming and often requires professional researchers. To alleviate such tiresome and labor-intensive costs, we propose a novel weakly supervised learning cell detection and tracking framework that trains the deep neural network using incomplete initial labels. Our approach uses incomplete cell markers obtained from fluorescent images for initial training on the Induced Pluripotent Stem (iPS) cell dataset, which is rarely studied for cell detection and tracking. During training, the incomplete initial labels were updated iteratively by combining detection and tracking results to obtain a model with better robustness. Our method was evaluated using two fields of the iPS cell dataset, along with the cell detection accuracy (DET) evaluation metric from the Cell Tracking Challenge (CTC) initiative, and it achieved 0.862 and 0.924 DET, respectively. The transferability of the developed model was tested using the public dataset FluoN2DH-GOWT1, which was taken from CTC; this contains two datasets with reference annotations. We randomly removed parts of the annotations in each labeled data to simulate the initial annotations on the public dataset. After training the model on the two datasets, with labels that comprise 10% cell markers, the DET improved from 0.130 to 0.903 and 0.116 to 0.877. When trained with labels that comprise 60% cell markers, the performance was better than the model trained using the supervised learning method. This outcome indicates that the model's performance improved as the quality of the labels used for training increased.

Fast Noninvasive Morphometric Characterization of Free Human Sperms Using Deep Learning.

The selection of high-quality sperms is critical to intracytoplasmic sperm injection, which accounts for 70­80% of in vitro fertilization (IVF) treatments. So far, sperm screening is usually performed manually by clinicians. However, the performance of manual screening is limited in its objectivity, consistency, and efficiency. To overcome these limitations, we have developed a fast and noninvasive three-stage method to characterize morphology of freely swimming human sperms in bright-field microscopy images using deep learning models. Specifically, we use an object detection model to identify sperm heads, a classification model to select in-focus images, and a segmentation model to extract geometry of sperm heads and vacuoles. The models achieve an F1-score of 0.951 in sperm head detection, a z-position estimation error within ±1.5 µm in in-focus image selection, and a Dice score of 0.948 in sperm head segmentation, respectively. Customized lightweight architectures are used for the models to achieve real-time analysis of 200 frames per second. Comprehensive morphological parameters are calculated from sperm head geometry extracted by image segmentation. Overall, our method provides a reliable and efficient tool to assist clinicians in selecting high-quality sperms for successful IVF. It also demonstrates the effectiveness of deep learning in real-time analysis of live bright-field microscopy images.

High-Energy Electron Scattering in Thick Samples Evaluated by Bright-Field Transmission Electron Microscopy, Energy-Filtering Transmission Electron Microscopy, and Electron Tomography.

Energy-filtering transmission electron microscopy (TEM) and bright-field TEM can be used to extract local sample thickness $t$ and to generate two-dimensional sample thickness maps. Electron tomography can be used to accurately verify the local $t$. The relations of log-ratio of zero-loss filtered energy-filtering TEM beam intensity ($I_{{\rm ZLP}}$) and unfiltered beam intensity ($I_{\rm u}$) versus sample thickness $t$ were measured for five values of collection angle in a microscope equipped with an energy filter. Furthermore, log-ratio of the incident (primary) beam intensity ($I_{\rm p}$) and the transmitted beam $I_{{\rm tr}}$ versus $t$ in bright-field TEM was measured utilizing a camera before the energy filter. The measurements were performed on a multilayer sample containing eight materials and thickness $t$ up to 800 nm. Local thickness $t$ was verified by electron tomography. The following results are reported:• The maximum thickness $t_{{\rm max}}$ yielding a linear relation of log-ratio, $\ln ( {I_{\rm u}}/{I_{{\rm ZLP}}})$ and $\ln ( {I_{\rm p}}/{I_{{\rm tr}}} )$, versus $t$.• Inelastic mean free path ($\lambda _{{\rm in}}$) for five values of collection angle.• Total mean free path ($\lambda _{{\rm total}}$) of electrons excluded by an angle-limiting aperture.• $\lambda _{{\rm in}}$ and $\lambda _{{\rm total}}$ are evaluated for the eight materials with atomic number from $\approx$10 to 79.The results can be utilized as a guide for upper limit of $t$ evaluation in energy-filtering TEM and bright-field TEM and for optimizing electron tomography experiments.

Basis of Image Analysis for Evaluating Cell Biomaterial Interaction Using Brightfield Microscopy.

Medical imaging is a growing field that has stemmed from the need to conduct noninvasive diagnosis, monitoring, and analysis of biological systems. With the developments and advances in the medical field and the new techniques that are used in the intervention of diseases, very soon the prevalence of implanted biomedical devices will be even more significant. The implanted materials in a biological system are used in diverse fields, which require lengthy evaluation and validation processes. However, currently the evaluation of the toxicity of biomaterials has not been fully automated yet. Moreover, image analysis is an integral part of biomaterial research, but it is not within the core capacities of a significant portion of biomaterial scientists, which results in the use of predominantly ready-made tools. The detailed image analysis can be conducted once all the relevant parameters including the inherent characteristics of image acquisition techniques are considered. Herein, we cover the currently used image analysis-based techniques for assessment of biomaterial/cell interaction with a specific focus on unstained brightfield microscopy acquired mostly in but not limited to microfluidic systems, which serve as multiparametric sensing platforms for noninvasive experimental measurements. We present the major imaging acquisition techniques that enable point-of-care testing when incorporated with microfluidic cells, discuss the constraints enforced by the geometry of the system and the material that is analyzed, and the challenges that rise in the image analysis when unstained cell imaging is employed. Emerging techniques such as utilization of machine learning and cell-specific pattern recognition algorithms and potential future directions are discussed. Automation and optimization of biomaterial assessment can facilitate the discovery of novel biomaterials together with making the validation of biomedical innovations cheaper and faster.

Practical segmentation of nuclei in brightfield cell images with neural networks trained on fluorescently labelled samples.

Identifying nuclei is a standard first step when analysing cells in microscopy images. The traditional approach relies on signal from a DNA stain, or fluorescent transgene expression localised to the nucleus. However, imaging techniques that do not use fluorescence can also carry useful information. Here, we used brightfield and fluorescence images of fixed cells with fluorescently labelled DNA, and confirmed that three convolutional neural network architectures can be adapted to segment nuclei from the brightfield channel, relying on fluorescence signal to extract the ground truth for training. We found that U-Net achieved the best overall performance, Mask R-CNN provided an additional benefit of instance segmentation, and that DeepCell proved too slow for practical application. We trained the U-Net architecture on over 200 dataset variations, established that accurate segmentation is possible using as few as 16 training images, and that models trained on images from similar cell lines can extrapolate well. Acquiring data from multiple focal planes further helps distinguish nuclei in the samples. Overall, our work helps to liberate a fluorescence channel reserved for nuclear staining, thus providing more information from the specimen, and reducing reagents and time required for preparing imaging experiments.

Image Analysis Algorithm-Based Platform for Determining Micron and Higher Aggregate Size Distribution of Therapeutic IgG Using Brightfield and Fluorescence Microscope Images.

A platform for determining size distribution of micron (1-100 µm) and larger (> 100 µm) aggregates of therapeutic IgG has been established by using image processing algorithms for brightfield and fluorescence microscope images. The algorithm for brightfield images involved conversion to grayscale followed by pixel-based and size-based thresholding. Morphological operations were then applied and the size distribution of aggregates were extracted. Fluorescence images of the aggregates of mAb tagged by a fluorescent dye were captured using widefield fluorescence microscope, confocal laser scanning microscope, and Cytell Cell Imaging System and the images were processed using a series of denoising steps followed by thresholding and morphological operations. The samples were subjected to different stresses, among which the aggregates were visible in the microscope for sample subjected to bubbling, stirring, and temperature. The images of these aggregates were effectively denoised and the size distribution of aggregates was analyzed using the algorithm. The overall aggregate size distribution obtained by image processing ranged in the micron and higher size range. The size obtained from brightfield image processing was validated using images of liquid chromatography resins. Further, the aggregate size distribution obtained using image processing was compared with experimental techniques such as Mastersizer 2000 and Micro Flow Imaging. It was found that analysis of IgG aggregates using image processing could serve as an orthogonal methodology to the existing approaches.

Human glycocalyx shedding: Systematic review and critical appraisal.

BACKGROUND: The number of studies measuring breakdown products of the glycocalyx in plasma has increased rapidly during the past decade. The purpose of the present systematic review was to assess the current knowledge concerning the association between plasma concentrations of glycocalyx components and structural assessment of the endothelium. METHODS: We performed a literature review of Pubmed to determine which glycocalyx components change in a wide variety of human diseases and conditions. We also searched for evidence of a relationship between plasma concentrations and the thickness of the endothelial glycocalyx layer as obtained by imaging methods. RESULTS: Out of 3,454 publications, we identified 228 that met our inclusion criteria. The vast majority demonstrate an increase in plasma glycocalyx products. Sepsis and trauma are most frequently studied, and comprise approximately 40 publications. They usually report 3-4-foldt increased levels of glycocalyx degradation products, most commonly of syndecan-1. Surgery shows a variable picture. Cardiac surgery and transplantations are most likely to involve elevations of glycocalyx degradation products. Structural assessment using imaging methods show thinning of the endothelial glycocalyx layer in cardiovascular conditions and during major surgery, but thinning does not always correlate with the plasma concentrations of glycocalyx products. The few structural assessments performed do not currently support that capillary permeability is increased when the plasma levels of glycocalyx fragments in plasma are increased. CONCLUSIONS: Shedding of glycocalyx components is a ubiquitous process that occurs during both acute and chronic inflammation with no sensitivity or specificity for a specific disease or condition.

High-resolution imaging of organic pharmaceutical crystals by transmission electron microscopy and scanning moiré fringes.

Formulation processing of organic crystalline compounds can have a significant effect on drug properties, such as dissolution rate or tablet strength/hardness. Transmission electron microscopy (TEM) has the potential to resolve the atomic lattice of these crystalline compounds and, for example, identify the defect density on a particular crystal face, provided that the sensitivity of these crystals to irradiation by high-energy electrons can be overcome. Here, we acquire high-resolution (HR) lattice images of the compound furosemide using two different methods: low-dose HRTEM and bright-field (BF) scanning TEM (STEM) scanning moiré fringes (SMFs). Before acquiring HRTEM images of furosemide, a model system of crocidolite (asbestos) was used to determine the electron flux/fluence limits of low-dose HR imaging for our scintillator-based, complementary metal-oxide semiconductor (CMOS) electron camera by testing a variety of electron flux and total electron fluence regimes. An electron flux of 10 e- /(Å2 s) and total fluence of 10 e- /Å2 was shown to provide sufficient contrast and signal-to-noise ratio to resolve 0.30 nm lattice spacings in crocidolite at 300 kV. These parameters were then used to image furosemide which has a critical electron fluence for damage of ≥10 e- /Å2 at 300 kV. The resulting HRTEM image of a furosemide crystal shows only a small portion of the total crystal exhibiting lattice fringes, likely due to irradiation damage during acquisition close to the compound's critical fluence. BF-STEM SMF images of furosemide were acquired at a lower electron fluence (1.8 e- /Å2 ), while still indirectly resolving HR details of the (001) lattice. Several different SMFs were observed with minor variations in the size and angle, suggesting strain due to defects within the crystal. Overall BF-STEM SMFs appear to be more useful than BF-STEM or HRTEM (with a CMOS camera) for imaging the crystal lattice of very beam-sensitive materials since a lower electron fluence is required to reveal the lattice. BF-STEM SMFs may thus prove useful in improving the understanding of crystallization pathways in organic compounds, degradation in pharmaceutical formulations and the effect of defects on the dissolution rate of different crystal faces. Further work is, however, required to quantitatively determine properties such as the defect density or the amount of relative strain from a BF-STEM SMF image.

Negative depletion mediated brightfield circulating tumour cell identification strategy on microparticle-based microfluidic chip.

BACKGROUND: The most convenient circulating tumor cells (CTCs) identification method is direct analysis of cells under bright field microscopy by which CTCs can be comprehensive studied based on morphology, phenotype or even cellular function. However, universal cell markers and a standard tumour cell map do not exist, thus limiting the clinical application of CTCs. RESULTS: This paper focuses on an automatic and convenient negative depletion strategy for circulating tumour cell identification under bright field microscopy. In this strategy, immune microparticles (IMPs) are applied to negatively label white blood cells rather than the tumour cells, such that tumour cells can be directly distinguished under brightfield of the microscopy. In this way, all of the heterogeneous tumour cells and their phenotype properties can be retained for further cancer-related studies. In addition, a wedge-shaped microfluidic chip is constructed for heterogeneous CTC pre-purification and enrichment by size, thus significantly decreasing the interference of haematological cells. Additionally, all cell treatments are processed automatically, and the tumour cells can be rapidly counted and distinguished via customized cell analytical software, showing high detection efficiency and automation. This IMPs based negative cell labelling strategy can also be combined with other classic cell identification methods, thus demonstrating its excellent compatibility. CONCLUSION: This identification strategy features simple and harmless for tumour cells, as well as excellent accuracy and efficiency. And the low equipment demand and high automation level make it promise for extensive application in basic medical institutions.

Simple Shading Correction Method for Brightfield Whole Slide Imaging.

Whole slide imaging (WSI) refers to the process of creating a high-resolution digital image of a whole slide. Since digital images are typically produced by stitching image sequences acquired from different fields of view, the visual quality of the images can be degraded owing to shading distortion, which produces black plaid patterns on the images. A shading correction method for brightfield WSI is presented, which is simple but robust not only against typical image artifacts caused by specks of dust and bubbles, but also against fixed-pattern noise, or spatial variations in pixel values under uniform illumination. The proposed method comprises primarily of two steps. The first step constructs candidates of a shading distortion model from a stack of input image sequences. The second step selects the optimal model from the candidates. The proposed method was compared experimentally with two previous state-of-the-art methods, regularized energy minimization (CIDRE) and background and shading correction (BaSiC) and showed better correction scores, as smooth operations and constraints were not imposed when estimating the shading distortion. The correction scores, averaged over 40 image collections, were as follows: proposed method, 0.39 ± 0.099; CIDRE method, 0.67 ± 0.047; BaSiC method, 0.55 ± 0.038. Based on the quantitative evaluations, we can confirm that the proposed method can correct not only shading distortion, but also fixed-pattern noise, compared with the two previous state-of-the-art methods.

Direct Atomic-Level Imaging of Zeolites: Oxygen, Sodium in Na-LTA and Iron in Fe-MFI.

Zeolites are becoming more versatile in their chemical functions through rational design of their frameworks. Therefore, direct imaging of all atoms at the atomic scale, basic units (Si, Al, and O), heteroatoms in the framework, and extra-framework cations, is needed. TEM provides local information at the atomic level, but the serious problem of electron-beam damage needs to be overcome. Herein, all framework atoms, including oxygen and most of the extra-framework Na cations, are successfully observed in one of the most electron-beam-sensitive and lowest framework density zeolites, Na-LTA. Zeolite performance, for instance in catalysis, is highly dependent on the location of incorporated heteroatoms. Fe single atomic sites in the MFI framework have been imaged for the first time. The approach presented here, combining image analysis, electron diffraction, and DFT calculations, can provide essential structural keys for tuning catalytically active sites at the atomic level.

Iterative unsupervised domain adaptation for generalized cell detection from brightfield z-stacks.

BACKGROUND: Cell counting from cell cultures is required in multiple biological and biomedical research applications. Especially, accurate brightfield-based cell counting methods are needed for cell growth analysis. With deep learning, cells can be detected with high accuracy, but manually annotated training data is required. We propose a method for cell detection that requires annotated training data for one cell line only, and generalizes to other, unseen cell lines. RESULTS: Training a deep learning model with one cell line only can provide accurate detections for similar unseen cell lines (domains). However, if the new domain is very dissimilar from training domain, high precision but lower recall is achieved. Generalization capabilities of the model can be improved with training data transformations, but only to a certain degree. To further improve the detection accuracy of unseen domains, we propose iterative unsupervised domain adaptation method. Predictions of unseen cell lines with high precision enable automatic generation of training data, which is used to train the model together with parts of the previously used annotated training data. We used U-Net-based model, and three consecutive focal planes from brightfield image z-stacks. We trained the model initially with PC-3 cell line, and used LNCaP, BT-474 and 22Rv1 cell lines as target domains for domain adaptation. Highest improvement in accuracy was achieved for 22Rv1 cells. F1-score after supervised training was only 0.65, but after unsupervised domain adaptation we achieved a score of 0.84. Mean accuracy for target domains was 0.87, with mean improvement of 16 percent. CONCLUSIONS: With our method for generalized cell detection, we can train a model that accurately detects different cell lines from brightfield images. A new cell line can be introduced to the model without a single manual annotation, and after iterative domain adaptation the model is ready to detect these cells with high accuracy.

Generic Isolated Cell Image Generator.

Building automated cancer screening systems based on image analysis is currently a hot topic in computer vision and medical imaging community. One of the biggest challenges of such systems, especially those using state-of-the-art deep learning techniques, is that they usually require a large amount of training data to be accurate. However, in the medical field, the confidentiality of the data and the need for medical expertise to label them significantly reduce the amount of training data available. A common practice to overcome this problem is to apply data set augmentation techniques to artificially increase the size of the training data set. Classical data set augmentation methods such as geometrical or color transformations are efficient but still produce a limited amount of new data. Hence, there has been interest in data set augmentation methods using generative models able to synthesize a wider variety of new data. VitaDX is actually developing an automated bladder cancer screening system based on the analysis of cell images contained in urinary cytology digital slides. Currently, the number of available labeled cell images is limited and therefore exploitation of the full potential of deep learning techniques is not possible. In an attempt to increase the number of labeled cell images, a new generic generator for 2D cell images has been developed and is described in this article. This framework combines previous works on cell image generation and a recent style transfer method referred to as doodle-style transfer in this article. To the best of our knowledge, we are the first to use a doodle-style transfer method for synthetic cell image generation. This framework is quite modular and could be applied to other cell image generation problems. A statistical evaluation has shown that features of real and synthetic cell images followed roughly the same distribution. Finally, the realism of the synthetic cell images has been assessed through a visual evaluation performed with the help of medical experts. © 2019 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.

Precise Pollen Grain Detection in Bright Field Microscopy Using Deep Learning Techniques.

The determination of daily concentrations of atmospheric pollen is important in the medical and biological fields. Obtaining pollen concentrations is a complex and time-consuming task for specialized personnel. The automatic location of pollen grains is a handicap due to the high complexity of the images to be processed, with polymorphic and clumped pollen grains, dust, or debris. The purpose of this study is to analyze the feasibility of implementing a reliable pollen grain detection system based on a convolutional neural network architecture, which will be used later as a critical part of an automated pollen concentration estimation system. We used a training set of 251 videos to train our system. As the videos record the process of focusing the samples, this system makes use of the 3D information presented by several focal planes. Besides, a separate set of 135 videos (containing 1234 pollen grains of 11 pollen types) was used to evaluate detection performance. The results are promising in detection (98.54% of recall and 99.75% of precision) and location accuracy (0.89 IoU as the average value). These results suggest that this technique can provide a reliable basis for the development of an automated pollen counting system.

Microfluidic Based Optical Microscopes on Chip.

Last decade's advancements in optofluidics allowed obtaining an ever increasing integration of different functionalities in lab on chip devices to culture, analyze, and manipulate single cells and entire biological specimens. Despite the importance of optical imaging for biological sample monitoring in microfluidics, imaging is traditionally achieved by placing microfluidics channels in standard bench-top optical microscopes. Recently, the development of either integrated optical elements or lensless imaging methods allowed optical imaging techniques to be implemented in lab on chip systems, thus increasing their automation, compactness, and portability. In this review, we discuss known solutions to implement microscopes on chip that exploit different optical methods such as bright-field, phase contrast, holographic, and fluorescence microscopy.