Rapid video-based deep learning of cognate versus non-cognate T cell-dendritic cell interactions

Identification of cognate interactions between antigen-specific T cells and dendritic cells (DCs) is essential to understanding immunity and tolerance, and for developing therapies for cancer and autoimmune diseases. Conventional techniques for selecting antigen-specific T cells are time-consuming and limited to pre-defined antigenic peptide sequences. Here, we demonstrate the ability to use deep learning to rapidly classify videos of antigen-specific CD8+ T cells. The trained model distinguishes distinct interaction dynamics (in motility and morphology) between cognate and non-cognate T cells and DCs over 20 to 80 min. The model classified high affinity antigen-specific CD8+ T cells from OT-I mice with an area under the curve (AUC) of 0.91, and generalized well to other types of high and low affinity CD8+ T cells. The classification accuracy achieved by the model was consistently higher than simple image analysis techniques, and conventional metrics used to differentiate between cognate and non-cognate T cells, such as speed. Also, we demonstrated that experimental addition of anti-CD40 antibodies improved model prediction. Overall, this method demonstrates the potential of video-based deep learning to rapidly classify cognate T cell-DC interactions, which may also be potentially integrated into high-throughput methods for selecting antigen-specific T cells in the future.

Integration of 3D Volumetric Computed Tomography Scan Image Data with Conventional Well Logs for Detection of Petrophysical Rock Classes

Summary Core measurements are used for rock classification and improved formation evaluation in both cored and noncored wells. However, the acquisition of such measurements is time-consuming, delaying rock classification efforts for weeks or months after core retrieval. On the other hand, well-log-based rock classification fails to account for rapid spatial variation of rock fabric encountered in heterogeneous and anisotropic formations due to the vertical resolution of conventional well logs. Interpretation of computed tomography (CT) scan data has been identified as an attractive and high-resolution alternative for enhancing rock texture detection, classification, and formation evaluation. Acquisition of CT scan data is accomplished shortly after core retrieval, providing high-resolution data for use in petrophysical workflows in relatively short periods of time. Typically, CT scan data are used as two-dimensional (2D) cross-sectional images, which is not suitable for quantification of three-dimensional (3D) rock fabric variation, which can increase the uncertainty in rock classification using image-based rock-fabric-related features. The methods documented in this paper aim to quantify rock-fabric-related features from whole-core 3D CT scan image stacks and slabbed whole-core photos using image analysis techniques. These quantitative features are integrated with conventional well logs and routine core analysis (RCA) data for fast and accurate detection of petrophysical rock classes. The detected rock classes are then used for improved formation evaluation. To achieve the objectives, we conducted a conventional formation evaluation. Then, we developed a workflow for preprocessing of whole-core 3D CT-scan image stacks and slabbed whole-core photos. Subsequently, we used image analysis techniques and tailor-made algorithms for the extraction of image-based rock-fabric-related features. Then, we used the image-based rock-fabric-related features for image-based rock classification. We used the detected rock classes for the development of class-based rock physics models to improve permeability estimates. Finally, we compared the detected image-based rock classes against other rock classification techniques and against image-based rock classes derived using 2D CT scan images. We applied the proposed workflow to a data set from a siliciclastic sequence with rapid spatial variations in rock fabric and pore structure. We compared the results against expert-derived lithofacies, conventional rock classification techniques, and rock classes derived using 2D CT scan images. The use of whole-core 3D CT scan image-stacks-based rock-fabric-related features accurately captured changes in the rock properties within the evaluated depth interval. Image-based rock classes derived by integration of whole-core 3D CT scan image-stacks-based and slabbed whole-core photos-based rock-fabric-related features agreed with expert-derived lithofacies. Furthermore, the use of the image-based rock classes in the formation evaluation of the evaluated depth intervals improved estimates of petrophysical properties such as permeability compared to conventional formation-based permeability estimates. A unique contribution of the proposed workflow compared to the previously documented rock classification methods is the derivation of quantitative features from whole-core 3D CT scan image stacks, which are conventionally used qualitatively. Furthermore, image-based rock-fabric-related features extracted from whole-core 3D CT scan image stacks can be used as a tool for quick assessment of recovered whole core for tasks such as locating best zones for extraction of core plugs for core analysis and flagging depth intervals showing abnormal well-log responses.

PERFORMANCE EVALUATION OF RAILWAY BALLAST DEGRADATION USING THE MORPHOLOGICAL PROPERTIES

Ballast degradation through attrition and breakage during operations affects the structural performance of the railway track system. In an attempt to study railway ballast degradation changes due to train cyclic loading at micro-scale. This study quantified and compared the changes that occur on ballast particles due to ballast degradation using LAA test and image analysis techniques. TB/T 2328.14-2008 gradation use by china railways was adopted. Series of LAA tests were conducted to accelerate the ballast particle breakage and abrasion, in a sequence of 250 turns of the LAA test drum, after which the changes in gradation and morphological properties were quantified. The morphological properties were quantified using imaging techniques (Aggregate Image measurement system (AIMS)). At the end of the study, the overall results showed that ballast degradation has a strong correlation with the ballast particle's morphological properties. The relationships and the indices of morphological changes can be used for numerical modeling and simulations using discrete element method (DEM) to study the performance of ballast at different degradation levels.

Smartphone Application for Determining the Segregation Index of Lightweight Aggregate Concrete

Due to the low density of the aggregates and the longer mixing times, lightweight aggregate concrete (LWAC) is susceptible to segregation of the aggregates. Several studies have proposed different methods to estimate the segregation of concrete because segregation affects strength and durability in structures. Image analysis techniques have become very popular for quickly analysing different materials and, together with the widespread use of mobile applications, can make it much easier for engineers to obtain parameters that identify concrete segregation. The aim of this work was the development of a mobile application to photograph the section of a concrete specimen and indicate the segregation values. A simple, fast, and effective application was implemented, and the results were validated with other previously published results, which can facilitate the task of engineers and researchers to determine the segregation of concrete.

An Comprehensive Survey on Applications of Precision Agriculture in the Context of Weed Classification, Leave Disease Detection, Yield Prediction and UAV Image Analysis

Advancement in technologies such as Machine vision, Machine Learning, Deep Learning algorithms enables them to extend its horizon in different applications including precision agriculture. The objective of this work is to study the various works pertaining to precision agriculture under four categories, weed classification, disease detection in leaves, yield prediction and image analysis techniques in UAV. In case of the weed classification, both classifying weeds from the crops and classifying the different types of weeds are analysed. In disease detection, only the diseases that occur in the leaves of different plants are considered and studied. It is continued with the state of art models that predicts yields of different crops. The last part of the work concentrates on analysing the images captured UAV in the context of precision agriculture. This work would pave a way for getting a deep insight about the state of art models related to the above specified applications of precision agriculture and the methods of analysing the UAV images.

Considerations for Whole-Slide Analysis of Murine Xenografts Experiments

Histochemistry of tumor sections is a widely employed technique utilized to examine cell death in preclinical xenograft animal models of cancer. However, this is under the assumption that tumors are homogeneous, leading to practices such as automatic cell counting across the entire section. We have noted that in our experiments the core of the tumor is largely or partially necrotic, and lacks evidence of vascularization (in contrast to the outer areas of the tumor). We note that this can bias and confound immunohistochemical analyses that do not take care to sample areas of interest in a way to take this into account. Design-based stereology with image analysis techniques is an alternative process that could be used to measure the volume of the necrotic region compared to the volume of the whole tumor.

High Content Image Analysis as a Tool to Morphologically Distinguish Macrophage Activation and Determine Its Importance for Foamy Alveolar Macrophage Responses

IntroductionLung diseases are an increasing global health burden affecting millions of people worldwide. Only a few new inhaled medicines have reached the market in the last 30 years, in part due to foamy alveolar macrophage (FAM) responses observed in pre-clinical rat studies. The induction mechanism and signaling pathways involved in the development of highly vacuolated ‘foamy’ phenotype is not known. Furthermore, it has not been determined if these observations are adaptive or adverse responses.AimTo determine if high content image analysis techniques can distinguish between alveolar macrophage activation (LPS/IFN-γ activated and IL-4 activated macrophages) and if this could be applied to understanding the generation of ‘foamy’ macrophage phenotypes.MethodsNR8383 rat alveolar macrophages were stimulated with a mix of cytokines (LPS/IFN-γ or IL-4) for 24 h. The cells were further exposed to FAM inducing-compounds amiodarone and staurosporine. Following 24 h incubation, phagocytosis and lipid accumulation were measured using flow cytometry and high content image analysis techniques. The alveolar macrophages responses after exposure to cytokines were assessed by evaluation: (i) cell surface and biochemical markers such as: nitric oxide production, arginase-1 activity and MRC-1 receptor expression (ii) cellular morphology (iii) cellular functionality (phagocytic activity and lipids accumulation).ResultsMacrophages activated with LPS/IFN-γ showed distinct morphological (increased vacuolation) features and functionality (increased lipidosis, decreased phagocytic activity). Foamy macrophage phenotypes induced by amiodarone also displayed characteristics of proinflammatory macrophages (significantly increased nitric oxide production, increased vacuolation and lipidosis and decreased phagocytosis). In contrast, staurosporine treatment resulted in increased NO production, as well as arginase-1 activity.ConclusionHigh content image analysis was able to determine distinct differences in morphology between non-activated and LPS/IFN-γ activated macrophages, characterized by increased vacuolation and lipidosis. When exposed to compounds that induce a FAM phenotype, healthy non-activated macrophages displayed proinflammatory (amiodarone) or pro-apoptotic (staurosporine) characteristics but these responses were independent of a change in activation status. This technique could be applied in early drug discovery safety assessment to identify immune responses earlier and increase the understanding of alveolar macrophage responses to new molecules challenge in development of new inhalation therapies, which in turn will enhance decision-making in an early safety assessment of novel drug candidates.