Light microscopy of tissue slides is an important tool for analyzing human diseases including cancer. In this work, we focus on classifying patches from a immunohistochemically stained tissue microarray (TMA) of vulvar cancer. We propose a novel ensemble-based deep learning technique to classify patches of tissue as cancerous, stroma, both, or none. Our ensemble model consists of a pre-trained data-efficient image transformer (DeiT) module to extract features of patches followed by a transformer block and graph convolutional networks (GCN). Transformer blocks aid the sequential learning of the extracted features from DeiT while the graph convolutional network (GCN) extracts neighborhood information. Our approach combines both methods for classification. In the evaluation, we show that our approach outperforms state-of-the-art architectures for the addressed application. We also show that is applicable when only small amounts of labelled data are available.

Mesenchymal stromal/stem cells (MSCs) have great capacity for immune regulation. MSCs provide protective paracrine effects, which are partially exerted by extracellular vesicles (EVs). It has been reported that MSCs-derived EVs (MSC-EVs) contain soluble factors, such as cytokines, chemokines, growth factors and even microRNAs, which confer them similar anti-inflammatory and regenerative effects to MSCs. Moreover, MSCs modulate microglia activation through a dual mechanism of action that relies both on cell contact and secreted factors. Microglia cells are the central nervous system immune cells and the main mediators of the inflammation leading to neurodegenerative disorders. Here, we investigated whether MSC-EVs affect the activation of microglia cells by β-amyloid aggregates. We show that the presence of MSC-EVs can prevent the upregulation of pro-inflammatory mediators such as tumor necrosis factor (TNF)-α and nitric oxide (NO). Both are up-regulated in neurodegenerative diseases representing chronic inflammation, as in Alzheimer's disease. We demonstrate that MSC-EVs are internalized by the microglia cells. Further, our study supports the use of MSC-EVs as a promising therapeutic tool to treat neuroinflammatory diseases.Significance StatementIt has been reported that mesenchymal stromal/stem cells and MSC-derived small extracellular vesicles have therapeutic effects in the treatment of various degenerative and inflammatory diseases. Extracellular vesicles are loaded with proteins, lipids and RNA and act as intercellular communication mediators. Here we show that extracellular vesicles can be taken up by murine microglial cells. In addition, they partially reduce the activation of microglial cells against β-amyloid aggregates. This inhibition of microglia activation may present an effective strategy for the control/therapy of neurodegenerative diseases such as Alzheimer's disease.

Passive immunotherapy is a very promising approach for the treatment of Alzheimer's disease (AD). Among the different antibodies under development, those targeting post-translationally modified Aβ peptides might combine efficient reduction in beta-amyloid accompanied by lower sequestration in peripheral compartments and thus anticipated and reduced treatment-related side effects. In that regard, we recently demonstrated that the antibody-mediated targeting of isoD7-modified Aβ peptides leads to the attenuation of AD-like amyloid pathology in 5xFAD mice. In order to assess novel strategies to enhance the efficacy of passive vaccination approaches, we investigated the role of CD33 for Aβ phagocytosis in transgenic mice treated with an isoD7-Aβ antibody. We crossbred 5xFAD transgenic mice with CD33 knock out (CD33KO) mice and compared the amyloid pathology in the different genotypes of the crossbreds. The knockout of CD33 in 5xFAD mice leads to a significant reduction in Aβ plaques and concomitant rescue of behavioral deficits. Passive immunotherapy of 5xFAD/CD33KO showed a significant increase in plaque-surrounding microglia compared to 5xFAD treated with the antibody. Additionally, we observed a stronger lowering of Aβ plaque load after passive immunotherapy in 5xFAD/CD33KO mice. The data suggest an additive effect of passive immunotherapy and CD33KO in terms of lowering Aβ pathology. Hence, a combination of CD33 antagonists and monoclonal antibodies might represent a strategy to enhance efficacy of passive immunotherapy in AD.

Correlative microscopy experiments require the co-registration of the image data acquired by different micro-analytical techniques. Major challenges are the potentially very different fields-of-view and resolutions as well as the multi-modality of the data. To provide microscopists with an easy-to-use software for two-dimensional image co-registration we have developed Correlia, an open source software based on ImageJa/Fiji,b which is fully tailored for the registration of multi-modal microscopy data. It can handle data-sets of in principle arbitrary extent and uses classical approaches, i.e., rigid registration tools or B-spline based deformation models for the correction of both, global and local misalignments, such that a fast registration output is provided. Here we describe some of the basics of Correlia focusing on its application: firstly, registration workflows are outlined on artificial data. In the second part these recipes are applied to register correlative data acquired on an algal biofilm and a soil sample.

In today’s clinical routine, malignant changes in the prostate’s structure are evaluated based on the Gleason grading system. An inevitable variability of the histopathological grading and thus a lack of reproducibility have led to a wide variety of computer-aided approaches including form-descriptor and deep learning based solutions. A common problem for any of those approaches lies in the domain-specific conditions, which consist in the small size of datasets, the high resolution and stain-fluctuation of the images, the missing capability of including useful follow-up data as well as the lack of region-level annotations and a high label-noise. Hence, in this work we analyze how the advantages of deep learning can be used for the malignancy grading of histopathological whole-slide images of the prostate, without relying too much on annotations and large-scale datasets. Our novel framework combines a clustering based stain normalization with a chain of an autoencoder, a principal component analysis, a support vector machine, and further deep learning and statistical models. Using this approach the classification accuracy could be improved by 5–10% when compared to conventional approaches. In addition, first results in combining biochemical and follow-up data with images for the prediction of the biochemical relapse time could be shown. The proposed framework has been built and validated using 500 cases taken from The Cancer Genome Atlas (TCGA: https://www.cancer.gov/tcga). Our work presents novel and promising approaches for the assessment of the prostate carcinoma’s malignancy and the severity of the risk using deep learning, as well as pending problems and limitations.

BACKGROUND:We present an image dataset related to automated segmentation and counting of macrophages in diffuse large B-cell lymphoma (DLBCL) tissue sections. For the classification of DLBCL subtypes, as well as for providing a prognosis of the clinical outcome, the analysis of the tumor microenvironment and, particularly, of the different types and functions of tumor-associated macrophages is indispensable. Until now, however, most information about macrophages has been obtained either in a completely indirect way by gene expression profiling or by manual counts in immunohistochemically (IHC) fluorescence-stained tissue samples while automated recognition of single IHC stained macrophages remains a difficult task. In an accompanying publication, a reliable approach to this problem has been established, and a large set of related images has been generated and analyzed. RESULTS:Provided image data comprise (i) fluorescence microscopy images of 44 multiple immunohistostained DLBCL tumor subregions, captured at 4 channels corresponding to CD14, CD163, Pax5, and DAPI; (ii) "cartoon-like" total variation-filtered versions of these images, generated by Rudin-Osher-Fatemi denoising; (iii) an automatically generated mask of the evaluation subregion, based on information from the DAPI channel; and (iv) automatically generated segmentation masks for macrophages (using information from CD14 and CD163 channels), B-cells (using information from Pax5 channel), and all cell nuclei (using information from DAPI channel). CONCLUSIONS:A large set of IHC stained DLBCL specimens is provided together with segmentation masks for different cell populations generated by a reference method for automated image analysis, thus featuring considerable reuse potential.

The correlation of different microscopic imaging techniques alongside with microanalytical methods is crucial to better understand biological processes on a subcellular level. For that, micrographs and chemical maps exhibiting both, very different spatial resolution and field-of-view but also a highly multimodal content has to be co-registered. We developed theImageJ/Fijiplug-inCorreliathat provides an environment for handling multimodal correlative microscopy data. Several linear and nonlinear registration methods using either feature or area-based similarity measures can flexibly be cascaded to align and warp 2D microscopy data sets. The registration of data sets containing light- and electron micrographs as well as chemical maps acquired by secondary-ion mass spectroscopy and energy-dispersive X-ray spectroscopy is demonstrated.Correliais an open-source tool developed particularly for the registration and analysis of highly multimodal 2D correlative microscopy data. Lay Description If a microscopic object is imaged correlatively by two or more different microscopes the acquired micrographs will have to be overlaid accurately using an image-registration software. In cases of relatively similar image content creating such an overlay is straight-forward but what if the fields-of-view and resolutions of the micrographs differ significantly? What if there are distortions in a micrograph which have to be corrected before creating an overlay? What if furthermore a chemical map shall be overlaid that merely shows regions in which a certain chemical element is present? The rapidly increasing number of applications in correlative microscopy is calling for an easy-to-use and flexible image registration software that can deal with these challenges. Having that in mind, we developedCorrelia, anImageJ/Fijiplug-in that provides an environment for handling multimodal 2D correlative microscopy data-sets. It allows for creating overlays using different registration algorithms that can flexibly be cascaded. In this paper we describe what is happening 'under the hood' and give two example data-sets from microbiology which were registered usingCorrelia.Correliais open source software and available from - including introductory examples, as the authors would like to encourage other scientists to process their individual correlative microscopy data using Correlia.

Prostate cancer (PCa) is the dominating malignant tumor for men worldwide and across all ethnic groups. If a carcinoma is being suspected, e.g. due to blood levels, trans-rectal punch biopsies of the prostate will be accomplished, while in case of higher stages of the disease the complete prostate is being surgically removed (radical prostatectomy). In both cases prostate tissue will be prepared into histological sections on glass microscope slides according to certain laboratory protocols, and is finally microscopically inspected by a trained histopathologist. Even though this method is well established, it can lead to various problems because of objectivity deficiencies. In this paper, we present a proof of concept of using Artificial Neural Networks (ANN) for automatically analyzing prostate cancer tissue and rating its malignancy using tissue microarrays (TMAs) of sampled benign and malignant tissue.

We present an approach to compute the number of holes in binary images using the Vertex Chain Code (VCC); the VCC was developed for representing and analyzing 2D shapes composed of cells. Using this code, it is possible to relate the outer to inner vertices of any 2D shape and to find interesting properties. Now, in this paper, we describe more properties of the VCC, such as the computation of the connected regions in a hole, the analysis of complementary chains, the computation of the number of holes in a binary shape or image, the computation of the Euler number, and the detection of convex and concave shapes. Finally, in order to illustrate the capabilities of proposed methods, we present the computation of topological properties of examples of objects of the real world.

For analysis of the tumor microenvironment in diffuse large B-cell lymphoma (DLBCL) tissue samples, it is desirable to obtain information about counts and distribution of different macrophage subtypes. Until now, macrophage counts are mostly inferred from gene expression analysis of whole tissue sections, providing only indirect information. Direct analysis of immunohistochemically (IHC) fluorescence stained tissue samples is confronted with several difficulties, e.g. high variability of shape and size of target macrophages and strongly inhomogeneous intensity of staining. Consequently, application of commercial software is largely restricted to very rough analysis modes, and most macrophage counts are still obtained by manual counting in microarrays or high power fields, thus failing to represent the heterogeneity of tumor microenvironment adequately. We describe a Rudin-Osher-Fatemi (ROF) filter based segmentation approach for whole tissue samples, combining floating intensity thresholding and rule-based feature detection. Method is validated against manual counts and compared with two commercial software kits (Tissue Studio 64, Definiens AG, and Halo, Indica Labs) and a straightforward machine-learning approach in a set of 50 test images. Further, the novel method and both commercial packages are applied to a set of 44 whole tissue sections. Outputs are compared with gene expression data available for the same tissue samples. Finally, the ROF based method is applied to 44 expert-specified tumor subregions for testing selection and subsampling strategies. Among all tested methods, the novel approach is best correlated with manual count (0.9297). Automated detection of evaluation subregions proved to be fully reliable. Comparison with gene expression data obtained for the same tissue samples reveals only moderate to low correlation levels. Subsampling within tumor subregions is possible with results almost identical to full sampling. Mean macrophage size in tumor subregions is 152.5±111.3 μm2. ROF based approach is successfully applied to detection of IHC stained macrophages in DLBCL tissue samples. The method competes well with existing commercial software kits. In difference to them, it is fully automated, externally repeatable, independent on training data and completely documented. Comparison with gene expression data indicates that image morphometry constitutes an independent source of information about antibody-polarized macrophage occurence and distribution.

The nonneoplastic microenvironment is abundant in follicular lymphoma. Its composition has been reported to be associated with the course of the disease. Lack of animal models hampers studies of interaction between lymphoma and bystander cells. We aimed to identify indicators of cellular interaction exemplified by nonrandom distribution of cell types within neoplastic follicles. Physiological germinal centers and follicles in follicular lymphoma were stained to identify macrophages, all T, follicular T-helper, dendritic and B cells. Density of cell types and cell distribution (spatial point pattern) were analyzed by digital image analysis. The density of all T, follicular T-helper and dendritic cells was higher in the dark zone than in the light zone of physiological germinal centers. Densities of cell types in follicular lymphoma were intermediate between the light and the dark zone. All cell types analyzed showed a completely random spatial distribution pattern within the dark and the light zone, respectively. In follicular lymphoma B cells and macrophages displayed complete spatial randomness. In contrast, all T cells, follicular T-helper cells and dendritic cells showed clustering of each individual cell type within a radius of 6–10 μm in the lymphoma. We conclude that the distribution of nonneoplastic cells within follicles of follicular lymphoma is not random. T cells and dendritic cells form clusters within the follicles, suggestive of sites of interaction between microenvironment and lymphoma cells. These clusters might help to understand the interaction of lymphoma cells with the microenvironment and might provide a structure for therapeutic intervention.

A goal of Life Child is to study the development of children and adolescents. The growth of fingers and other palm compartments in this age group has been received little attraction so far. Usually, finger lengths are measured manually even when 2D palm images have been produced. This is often cumbersome for very large studies. In this paper, we introduce an approach to automatically segement palm and finger compartments of scanned 2D palm scans. The scans were taken by a single document scanner with the goal to measure finger lengths. Our algorithms are rotation invariant, automatically recognize hand objects in images using a skin color model, determine the finger segments for that the length from the fingertip to the crease is derived. We outline steps of the image processing pipeline and show first evaluation results

Large doses of recombinant growth factors formulated in solution form directly injected into the body is usual clinical practice in treating second-degree scald injuries, with promising results, but this approach creates side effects; furthermore, it may not allow appropriate levels of the factor to be sensed by the target injured tissue/organ in the specific time frame, owing to complications arising from regeneration. In this research, two delivery methods (infusion pumping and local topical application) were applied to deliver recombinant human erythropoietin (rHuEPO) for skin regeneration. First, rHuEPO was given in deep second-degree scald injury sites in mice by infusion pump. Vascularization was remarkably higher in the rHuEPO pumping group than in controls. Second, local topical application of rHuEPO gel was given in deep second-degree scald injury sites in rats. Histological analysis showed that epithelialization rate was significantly higher in the rHuEPO gel-treated group than in controls. Immunohistochemical studies showed that the rHuEPO gel-treated group showed remarkably higher expression of skin regeneration makers than the control group. An accurate method for visualization and quantification of blood vessel networks in target areas has still not been developed up to this point, because of technical difficulties in detecting such thin blood vessels. A method which utilizes a series of steps to enhance the image, removes noise from image background, and tracks the vessels edges for vessel segmentation and quantification has been used in this study. Using image analysis methods, we were able to detect the microvascular networks of newly formed blood vessels (less than 500 μm thickness), which participate in the healing process, providing not only nutrition and oxygen to grow tissues but also necessary growth factors to grow tissue cells for complete skin regeneration. The rHuEPO-treated group showed higher expression of stem cell markers (CD 31, CD 90, CD 71, and nestin), which actively contribute to in-wound-healing processes for new hair follicle generation as well as skin regeneration. Collectively, both rHuEPO group pumping into the systemic circulation system, and injection into the local injury area, prompted mice and rats to form new blood vessel networks in scald injury sites, which significantly participate in the scald healing process. These results may lead to the development of novel treatments for scald wounds.

A proof-of-principle study was accomplished assessing the descriptive potential of two simple geometric measures (shape descriptors) applied to sets of segmented glands within images of 125 prostate cancer tissue sections. Respective measures addressing glandular shapes were (i) inverse solidity and (ii) inverse compactness. Using a classifier based on logistic regression, Gleason grades 3 and 4/5 could be differentiated with an accuracy of approx. 95%. Results suggest not only good discriminatory properties, but also robustness against gland segmentation variations. False classifications in part were caused by inadvertent Gleason grade assignments, as a-posteriori re-inspections had turned out.

Drug addiction is a chronic, relapsing disease caused by neurochemical and molecular changes in the brain. In this human autopsy study qualitative and quantitative changes of glial fibrillary acidic protein (GFAP)-positive astrocytes in the hippocampus of 26 lethally intoxicated drug addicts and 35 matched controls are described. The morphological characterization of these cells reflected alterations representative for astrogliosis. But, neither quantification of GFAP-positive cells nor the Western blot analysis indicated statistical significant differences between drug fatalities versus controls. However, by semi-quantitative scoring a significant shift towards higher numbers of activated astrocytes in the drug group was detected. To assess morphological changes quantitatively, graph-based representations of astrocyte morphology were obtained from single cell images captured by confocal laser scanning microscopy. Their underlying structures were used to quantify changes in astroglial fibers in an automated fashion. This morphometric analysis yielded significant differences between the investigated groups for four different measures of fiber characteristics (Euclidean distance, graph distance, number of graph elements, fiber skeleton distance), indicating that, e.g., astrocytes in drug addicts on average exhibit significant elongation of fiber structures as well as two-fold increase in GFAP-positive fibers as compared with those in controls. In conclusion, the present data show characteristic differences in morphology of hippocampal astrocytes in drug addicts versus controls and further supports the involvement of astrocytes in human pathophysiology of drug addiction. The automated quantification of astrocyte morphologies provides a novel, testable way to assess the fiber structures in a quantitative manner as opposed to standard, qualitative descriptions.

Two new versions of the Euler-Poincaré formula are proposed considering two new defined cuboids: the tetra-voxel and the octo-voxel, without losing information on the number of vertices and edges. The well-known relationship between contact and enclosing surface concepts, as well as the relationships between vertices, edges and enclosing surfaces, allowed us to compute an innovative algorithm for obtaining alternative versions of the Euler-Poincaré formula. This is a very important topological descriptor of 3D binary images. We considered not only topological but geometric aspects. Our method was compared to other proposals, obtaining that our proposed contact surface-based method offers more advantages.

Much effort has been directed towards the optimization of the capture of in vivo hepatocytes from their microenvironment. Some methods of capture include an ex vivo cellular model in a bioreactor based liver module, a micropatterned module, a microfluidic 3D chip, coated plates, and other innovative approaches for the functional maintenance of primary hepatocytes. However, none of the above methods meet US Food and Drug Administration (FDA) guidelines, which recommend and encourage that the duration of a toxicity assay of a drug should be a minimum of 14 days, to a maximum of 90 days for a general toxicity assay. Existing innovative reports have used undefined extracellular matrices like matrigel, rigid collagen, or serum supplementations, which are often problematic, unacceptable in preclinical and clinical applications, and can even interfere with experimental outcomes. We have overcome these challenges by using integrated nanostructured self-assembling peptides and a special combination of growth factors and cytokines to establish a proof of concept to mimic the in vivo hepatocyte microenvironment pattern in vitro for predicting the in vivo drug hepatotoxicity in a scalable bioartificial liver module. Hepatocyte functionality (albumin, urea) was measured at days 10, 30, 60, and 90 and we observed stable albumin secretion and urea function throughout the culture period. In parallel, drug metabolizing enzyme biomarkers such as ethoxyresorufin-O-deethylase, the methylthiazol tetrazolium test, and the lactate dehydrogenase test were carried out at days 10, 30, 60, and 90. We noticed excellent mitochondrial status and membrane stability at 90 days of culture. Since alpha glutathione S-transferase (GST) is highly sensitive and a specific marker of hepatocyte injury, we observed significantly low alpha GST levels on all measured days (10, 30, 60, and 90). Finally, we performed the image analysis of mitochondria-cultured hepatocytes at day 90 in different biophysical parameters using confocal microscopy. We applied an automatic algorithm-based method for 3D visualization to show the classic representation of the mitochondrial distribution in double hepatocytes. An automated morphological measurement was conducted on the mitochondrial distribution in the cultured hepatocytes. Our proof of concept of a scalable bioartificial liver modular device meets FDA guidelines and may function as an alternative model of animal experimentation for pharmacological and toxicological studies involving drug metabolism, enzyme induction, transplantation, viral hepatitis, hepatocyte regeneration, and can also be used in other existing bioreactor modules for long-term culture for up to 90 days or more.

As revealed by optical coherence tomography (OCT), the shape of the fovea may vary greatly among individuals. However, none of the hitherto available mathematical descriptions comprehensively reproduces all individual characteristics such as foveal depth, slope, naso-temporal asymmetry, and others. Here, a novel mathematical approach is presented to obtain a very accurate model of the complete 3D foveal surface of an individual, by utilizing recent developments in OCT. For this purpose, a new formula was developed serving as a simple but very flexible way to represent a given fovea. An extensive description of the used model parameters, as well as, of the complete method of reconstructing a foveal surface from OCT data, is presented. Noteworthy, the formula analytically provides characteristic foveal parameters and thus allows for extensive quantification. The present approach was verified on 432 OCT scans and has proved to be able to capture the whole range of asymmetric foveal shapes with high accuracy (i.e. a mean fit error of 1.40 μm).

Purpose: Prostate cancer is routinely graded according to the Gleason grading scheme. This scheme is predominantly based on the textural appearance of aberrant glandular structures. Gleason grade is difficult to standardize and often leads to discussion due to interrater and intrarater disagreement. Thus, we investigated whether digital image based automated quantitative histomorphometry could be used to achieve a more standardized, reproducible classification outcome.Materials and Methods: In a proof of principle study we developed a method to evaluate digitized histological images of single prostate cancer regions in hematoxylin and eosin stained sections. Preprocessed color images were subjected to color deconvolution, followed by the binarization of obtained hematoxylin related image channels. Highlighted neoplastic epithelial gland related objects were morphometrically assessed by a classifier based on 2 calculated quantitative and objective geometric measures, that is inverse solidity and inverse compactness. The procedure was then applied to the prostate cancer probes of 125 patients. Each probe was independently classified for Gleason grade 3, 4 or 5 by an experienced pathologist blinded to image analysis outcome.Results: Together inverse compactness and inverse solidity were adequate discriminatory features for a powerful classifier that distinguished Gleason grade 3 from grade 4/5 histology. The classifier was robust on sensitivity analysis.Conclusions: Results suggest that quantitative and interpretable measures can be obtained from image based analysis, permitting algorithmic differentiation of prostate Gleason grades. The method must be validated in a large independent series of specimens.