Deep Learning Method for Estimating Germ-layer Regions of Early Differentiated Human Induced Pluripotent Stem Cells on Micropattern Using Bright-field Microscopy Image.

DeepHCS<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" altimg="si1.svg"><mml:msup><mml:mrow/><mml:mrow><mml:mo>+</mml:mo><mml:mo>+</mml:mo></mml:mrow></mml:msup></mml:math>: Bright-field to fluorescence microscopy image conversion using multi-task learning with adversarial losses for label-free high-content screening

Multistage morphological segmentation of bright-field and fluorescent microscopy images

Diffraction imaging flow cytometry is a new biological cell research method developed recently, which can get abundant information of 3D morphology inside the cell without staining. However, the pattern of diffraction image is non-intuitive, and cannot be directly classified by the observer. On the contrary, the bright field images obtained by microscope are clear enough to be directly perceived through the senses by researchers. This paper will introduce a new flow cell imaging design incorporating the merits of these two kinds of methods that can obtain diffraction image and bright field image of the same cell simultaneously, which is based on the infinite microscopic architecture with two optical paths. The first path gets the diffraction image by defocusing the shared object lens, meanwhile, the second path gets the bright-field microscopic image by adjustable lens compensating for the defocus. In the new system diffraction and microscopic images of yeasts were captured with illumination of 532nm laser and 450nm LED respectively. Two classification models were set up for recognition of yeast-budding-state with diffraction images and microscopic images independently by using GLCM (Grayscale Co-occurrence Matrix) feature extraction method, which got the highest 97% accuracy of classification with diffraction images compared to the 94% with microscopic images.

The detection and segmentation of adherent eukaryotic cells from brightfield microscopy images represent challenging tasks in the image analysis field. This paper presents a free and open-source image analysis package which fully automates the tasks of cell detection, cell boundary segmentation, and nucleus segmentation in brightfield images. The package also performs image registration between brightfield and fluorescence images. The algorithms were evaluated on a variety of biological cell lines and compared against manual and fluorescence-based ground truths. When tested on HT1080 and HeLa cells, the cell detection step was able to correctly identify over 80% of cells, whilst the cell boundary segmentation step was able to segment over 75% of the cell body pixels, and the nucleus segmentation step was able to correctly identify nuclei in over 75% of the cells. The algorithms for cell detection and nucleus segmentation are novel to the field, whilst the cell boundary segmentation algorithm is contrast-invariant, which makes it more robust on these low-contrast images. Together, this suite of algorithms permit brightfield microscopy image processing without the need for additional fluorescence images. Finally our sephaCe application, which is available at http://www.sephace.com, provides a novel method for integrating these methods with any motorised microscope, thus facilitating the adoption of these techniques in biological research labs.

1. The optical transparency of unstained live cell specimens limits the extent to which information can be recovered from bright-field microscopic images because these specimens generally lack visible amplitude-modulating components. However, visualization of the phase modulation that occurs when light traverses these specimens can provide additional information. 2. Optical phase microscopy and derivatives of this technique, such as differential interference contrast (DIC) and Hoffman modulation contrast (HMC), have been used widely in the study of cellular materials. With these techniques, enhanced contrast is achieved, which is useful in viewing specimens, but does not allow quantitative information to be extracted from the phase content available in the images. 3. An innovative computational approach to phase microscopy, which provides mathematically derived information about specimen phase-modulating characteristics, has been described recently. Known as quantitative phase microscopy (QPM), this method derives quantitative phase measurements from images captured using a bright-field microscope without phase- or interference-contrast optics. 4. The phase map generated from the bright-field images by the QPM method can be used to emulate other contrast image modes (including DIC and HMC) for qualitative viewing. Quantitative phase microscopy achieves improved discrimination of cellular detail, which permits more rigorous image analysis procedures to be undertaken compared with conventional optical methods. 5. The phase map contains information about cell thickness and refractive index and can allow quantification of cellular morphology under experimental conditions. As an example, the proliferative properties of smooth muscle cells have been evaluated using QPM to track growth and confluency of cell cultures. Quantitative phase microscopy has also been used to investigate erythrocyte cell volume and morphology in different osmotic environments. 6. Quantitative phase microscopy is a valuable, new, non-destructive, non-interventional experimental tool for structural and functional cellular investigations.

Microscopy is a widely used method in biological research to observe the morphology and structure of cells. Amongst the plethora of microscopy techniques, fluorescent labeling with dyes or antibodies is the most popular method for revealing specific cellular organelles. However, fluorescent labeling also introduces new challenges to cellular observation, as it increases the workload, and the process may result in nonspecific labeling. Recent advances in deep visual learning have shown that there are systematic relationships between fluorescent and bright-field images, thus facilitating image translation between the two. In this article, we propose the cross-attention conditional generative adversarial network (XAcGAN) model. It employs state-of-the-art GANs (GANs) to solve the image translation task. The model uses supervised learning and combines attention-based networks to explore spatial information during translation. In addition, we demonstrate the successful application of XAcGAN to infer the health state of translated nuclei from bright-field microscopy images. The results show that our approach achieves excellent performance both in terms of image translation and nuclei state inference.

A search for apatite crystals in the gap zone of collagen fibrils in bone using dark-field illumination.

The automatic subcellular localisation of proteins in living cells is a critical step in determining their function. The evaluation of fluorescence images constitutes a common method of localising these proteins. For this, additional knowledge about the position of the considered cells within an image is required. In an automated system, it is advantageous to recognise these cells in bright-field microscope images taken in parallel with the regarded fluorescence micrographs. Unfortunately, currently available cell recognition methods are only of limited use within the context of protein localisation, since they frequently require microscopy techniques that enable images of higher contrast (e.g. phase contrast microscopy or additional dyes) or can only be employed with too low magnifications. Therefore, this article introduces a novel approach to the robust automatic recognition of unstained living cells in bright-field microscope images. Here, the focus is on the automatic segmentation of cells.

Accurate segmentation of zebrafish from bright-field microscope images is crucial to many applications in the life sciences. Early zebrafish stages are used, and in these stages the zebrafish is partially transparent. This transparency leads to edge ambiguity as is typically seen in the larval stages. Therefore, segmentation of zebrafish objects from images is a challenging task in computational bio-imaging. Popular computational methods fail to segment the relevant edges, which subsequently results in inaccurate measurements and evaluations. Here we present a hybrid method to accomplish accurate and efficient segmentation of zebrafish specimens from bright-field microscope images. We employ the mean shift algorithm to augment the colour representation in the images. This improves the discrimination of the specimen to the background and provides a segmentation candidate retaining the overall shape of the zebrafish. A distance-regularised level set function is initialised from this segmentation candidate and fed to an improved level set method, such that we can obtain another segmentation candidate which preserves the explicit contour of the object. The two candidates are fused using heuristics, and the hybrid result is refined to represent the contour of the zebrafish specimen. We have applied the proposed method on two typical datasets. From experiments, we conclude that the proposed hybrid method improves both efficiency and accuracy of the segmentation of the zebrafish specimen. The results are going to be used for high-throughput applications with zebrafish.

Investigation of cell structure is hardly imaginable without bright-field microscopy. Numerous modifications such as depth-wise scanning or videoenhancement make this method being state-of-the-art. This raises a question what maximal information can be extracted from ordinary (but well acquired) bright-field images in a model-free way. Here we introduce a method of a physically correct extraction of features for each pixel when these features resemble a transparency spectrum. The method is compatible with existent ordinary bright-field microscopes and requires mathematically sophisticated data processing. Unsupervised clustering of the spectra yields reasonable semantic segmentation of unstained living cells without any a priori information about their structures. Despite the lack of reference data (to prove strictly that the proposed feature vectors coincide with transparency), we believe that this method is the right approach to an intracellular (semi)quantitative and qualitative chemical analysis.

Pollen morphology, involving the physical characteristics of pollen grains from seed plants during reproduction, plays an important role in plant biology, ecology, and evolution. High pollen concentrations in the air can degrade air quality and exacerbate respiratory conditions such as asthma. Understanding pollen morphology and its implications for air quality is significant for mitigating respiratory health risks. Conventionally, fluorescence microscopy is used for pollen imaging, but photobleaching, quenching, and phototoxicity affect the surface morphology and do not provide quantitative data on the pollen grains. For this study, we used bright field (BF) imaging and quantitative phase imaging (QPI), a label-free interferometric microscopy method, to look at differences in the shape of pollen. BF imaging provides information about the shape and size of the different pollens but has a limitation of low contrast. To obtain high-contrast images and quantitative data on the pollen grains without any exogenous agents, we employed QPI and BF imaging in the present study. QPI enables the extraction of detailed information regarding the cell wall, aperture, and thickness of pollen while also maintaining their natural state without the need for chemical treatments. In the present work, we sampled the ambient air from May 2023 to January 2024 on the IIT Delhi campus. Subsequently, QPI and BF imaging have been done for pollen identification and phase analysis of arboreal and non-arboreal pollen. Further, by utilizing the information obtained from BF microscopy and QPI, different species of pollen have been identified, and a pollen calendar has been prepared for exhibiting pollen season throughout the year. To the best of the authors’ knowledge, they have conducted the QPI of airborne pollen grains for the first time; this technique holds great potential for characterizing airborne pollens without the need for staining or sample preparation.

A platform for determining size distribution of micron (1-100μm) and larger (> 100μm) 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.

&lt;p&gt;Single molecule in situ hybridization for circSLC8A1 in prostate adenocarcinoma. Brightfield microscopy image at 200X magnification of DESMIN immunohistochemical staining (left panel). Brightfield and fluorescent microscopy images of circSLC8A1 at 200X magnification. A signal from circSLC8A1 can be observed in muscle cells, whereas the cancer cells were negative (right panel).&lt;/p&gt;

&lt;p&gt;Single molecule in situ hybridization for circSLC8A1 in prostate adenocarcinoma. Brightfield microscopy image at 200X magnification of DESMIN immunohistochemical staining (left panel). Brightfield and fluorescent microscopy images of circSLC8A1 at 200X magnification. A signal from circSLC8A1 can be observed in muscle cells, whereas the cancer cells were negative (right panel).&lt;/p&gt;

&lt;p&gt;Single molecule in situ hybridization for circSLC8A1 in prostate adenocarcinoma. Brightfield microscopy image at 200X magnification of DESMIN immunohistochemical staining (left panel). Brightfield and fluorescent microscopy images of circSLC8A1 at 200X magnification. A signal from circSLC8A1 can be observed in muscle cells, whereas the cancer cells were negative (right panel).&lt;/p&gt;