MIA: An Open Source Standalone Deep Learning Application for Microscopic Image Analysis

In recent years the amount of data generated by imaging techniques has grown rapidly along with increasing computational power and the development of deep learning algorithms. To address the need for powerful automated image analysis tools for a broad range of applications in the biomedical sciences, we present the Microscopic Image Analyzer (MIA). MIA combines a graphical user interface that obviates the need for programming skills with state-of-the-art deep learning algorithms for segmentation, object detection, and classification. It runs as a standalone, platform-independent application and is compatible with commonly used open source software packages. The software provides a unified interface for easy image labeling, model training and inference. Furthermore the software was evaluated in a public competition and performed among the top three for all tested data sets. The source code is available on https://github.com/MIAnalyzer/MIA.

Zebrafish Vascular Quantification (ZVQ): a tool for quantification of three-dimensional zebrafish cerebrovascular architecture by automated image analysis

Zebrafish transgenic lines and light sheet fluorescence microscopy allow in-depth insights into three-dimensional vascular development in vivo. However, quantification of the zebrafish cerebral vasculature in 3D remains highly challenging. Here, we describe and test an image analysis workflow for 3D quantification of the total or regional zebrafish brain vasculature, called zebrafish vasculature quantification “ZVQ”. It provides the first landmark- or object-based vascular inter-sample registration of the zebrafish cerebral vasculature, producing Population Average Maps allowing rapid assessment of intra- and inter-group vascular anatomy. ZVQ also extracts a range of quantitative vascular parameters from a user-specified Region of Interest including volume, surface area, density, branching points, length, radius, and complexity. Application of ZVQ to thirteen experimental conditions, including embryonic development, pharmacological manipulations and morpholino induced gene knockdown, shows ZVQ is robust, allows extraction of biologically relevant information and quantification of vascular alteration, and can provide novel insights into vascular biology. To allow dissemination, the code for quantification, a graphical user interface, and workflow documentation are provided. Together, ZVQ provides the first open-source quantitative approach to assess the 3D cerebrovascular architecture in zebrafish.

Automated analysis of platelet microstructures using a feature length orientation space

The ability to measure elongated structures such as platelets and colonies, is an important step in the microstructural analysis of many materials. Widely used techniques and standards require extensive manual interaction making them slow, laborious, difficult to repeat and prone to human error. Automated approaches have been proposed but often fail when analysing complex microstructures. This paper addresses these challenges by proposing a new, automated image analysis technique, to reliably assess platelet microstructure. Tools from Mathematical Morphology are designed to probe the image and map the response onto a new feature-length orientation space (FLOS). This enables automated measurement of key microstructural features such as platelet width, orientation, globular volume fraction, and colony size. The method has a wide field of view, low dependency on input parameters, and does not require prior thresholding, common in other automated analysis techniques. Multiple datasets of complex Titanium alloys were used to evaluate the new techniques which are shown to match measurements from expert materials scientists using recognized standards, while drastically reducing measurement time and ensuring repeatability. The per-pixel measurement style of the technique also allows for the generation of useful colourmaps, that aid further analysis and provide evidence to increase user confidence in the quantitative measurements.

ARTIFICIAL INTELLIGENCE AND NEXT GENERATION PATHOLOGY: TOWARDS PERSONALIZED MEDICINE

Introduction. Over the past few decades, thanks to advances in algorithm development, the introduction of available computing power, and the management of large data sets, machine learning methods have become active in various fields of life. Among them, deep learning possesses a special place, which is used in many spheres of health care and is an integral part and prerequisite for the development of digital pathology. Objectives. The purpose of the review was to gather the data on existing image analysis technologies and machine learning tools developed for the whole-slide digital images in pathology. Methods: Analysis of the literature on machine learning methods used in pathology, staps of automated image analysis, types of neural networks, their application and capabilities in digital pathology was performed. Results. To date, a wide range of deep learning strategies have been developed, which are actively used in digital pathology, and demonstrated excellent diagnostic accuracy. In addition to diagnostic solutions, the integration of artificial intelligence into the practice of pathomorphological laboratory provides new tools for assessing the prognosis and prediction of sensitivity to different treatments. Conclusions: The synergy of artificial intelligence and digital pathology is a key tool to improve the accuracy of diagnostics, prognostication and personalized medicine facilitation

Automated Image Analysis to Map the Extent of Deep-Sea Mining Plumes Reveals a Larger Impacted Area Compared to Manual Analysis

Deep sea mining for poly-metallic nodules impacts the environment in many ways. A key potential hazard is the creation of a sediment plume from resuspending sediment during seabed mining. The resuspended matter disperses with currents but eventually resettles on the seabed. Resettling causes a blanketing of the seafloor environment, potentially causing harm to in-, epi- and hyperbenthic communities with possible cascading effects into food webs of deep sea habitats. Mapping the extent of such blanketing is thus an important factor in quantifying potential impacts of deep-sea mining.One technology that can assess seabed blanketing is optical imaging with cameras at square-kilometre scale. To efficiently analyse the resulting Terabytes of image data with minimized bias, automated image analysis is required. Moreover, effective quantitative monitoring of the blanketing requires ground truthing of the image data. Here, we present results from a camera-based monitoring of a deep-sea mining simulation combined with automated image analysis using the CoMoNoD method and low-cost seabed sediment traps for quantification of the blanketing thickness. We found that the impacted area was about 50 percent larger than previously determined by manual image annotation.

Usefulness of Automated Image Analysis for Recognition of the Fragile X Syndrome Gestalt in Congolese Subjects

Background Computer-aided software such as the facial image diagnostic aid (FIDA) and Face2Gene has been developed to perform pattern recognition of facial features with promising clinical results. The aim of this study was to test Face2Gene's recognition performance on Bantu Congolese subjects with Fragile X syndrome (FXS) as compared to Congolese subjects with intellectual disability but without FXS (non-FXS). Method Frontal facial photograph from 156 participants (14 patients with FXS and 142 controls) were uploaded. Automated face analysis was conducted by using the technology used in proprietary software tools called Face2Gene CLINIC and Face2Gene RESEARCH (version 17.6.2). To estimate the statistical power of the Face2Gene technology in distinguishing affected individuals from controls, a cross validation scheme was used. Results The similarity seen in the upper facial region (of males and females) is greater than the similarity seen in other parts of the face. Binary comparison of FXS subjects versus subjects with ID negative for Fragile X syndrome and FXS subjects versus subjects with Down syndrome reveal an area under the curve values of 0.955 (p=0.002) and 0.986 (p=0.003). Conclusion The Face2Gene algorithm is separating well between FXS and Non-FXS subjects.

Fatquant: An automated image analysis tool for identification of fat cells in heterogeneous hematoxylin and eosin tissue sections.

Hematoxylin and eosin (H and E) is one of the common histological staining techniques that provides information on the tissue cytoarchitecture. Adipose (fat) cells accumulation in pancreas has been shown to impact beta cell survival and its endocrine function. The current automated tools available for fat analysis are suited for white adipose tissue which is homogeneous and easier to segment unlike heterogeneous tissues such as pancreas where fat cells continue to play critical physiopathological functions. In the current study, we present an automated fat analysis tool, Fatquant, where mathematical formula to calculate diagonal of a square drawn inside circle is utilized for identification and analysis of fat cells in heterogeneous H and E tissue sections. Using histological images of pancreas from a publicly available database, we show an area accuracy overlap of 89-93% between manual versus automated algorithm based fat cell detection.

SynActJ: Easy-to-Use Automated Analysis of Synaptic Activity

Neuronal synapses are highly dynamic communication hubs that mediate chemical neurotransmission via the exocytic fusion and subsequent endocytic recycling of neurotransmitter-containing synaptic vesicles (SVs). Functional imaging tools allow for the direct visualization of synaptic activity by detecting action potentials, pre- or postsynaptic calcium influx, SV exo- and endocytosis, and glutamate release. Fluorescent organic dyes or synapse-targeted genetic molecular reporters, such as calcium, voltage or neurotransmitter sensors and synapto-pHluorins reveal synaptic activity by undergoing rapid changes in their fluorescence intensity upon neuronal activity on timescales of milliseconds to seconds, which typically are recorded by fast and sensitive widefield live cell microscopy. The analysis of the resulting time-lapse movies in the past has been performed by either manually picking individual structures, custom scripts that have not been made widely available to the scientific community, or advanced software toolboxes that are complicated to use. For the precise, unbiased and reproducible measurement of synaptic activity, it is key that the research community has access to bio-image analysis tools that are easy-to-apply and allow the automated detection of fluorescent intensity changes in active synapses. Here we present SynActJ (Synaptic Activity in ImageJ), an easy-to-use fully open-source workflow that enables automated image and data analysis of synaptic activity. The workflow consists of a Fiji plugin performing the automated image analysis of active synapses in time-lapse movies via an interactive seeded watershed segmentation that can be easily adjusted and applied to a dataset in batch mode. The extracted intensity traces of each synaptic bouton are automatically processed, analyzed, and plotted using an R Shiny workflow. We validate the workflow on time-lapse images of stimulated synapses expressing the SV exo-/endocytosis reporter Synaptophysin-pHluorin or a synapse-targeted calcium sensor, Synaptophysin-RGECO. We compare the automatic workflow to manual analysis and compute calcium-influx and SV exo-/endocytosis kinetics and other parameters for synaptic vesicle recycling under different conditions. We predict SynActJ to become an important tool for the analysis of synaptic activity and synapse properties.

RoPod, a customizable toolkit for non-invasive root imaging, reveals cell type-specific dynamics of plant autophagy

Autophagy is the major catabolic process in eukaryotes and a key regulator of plant fitness. It enables rapid response to stress stimuli, essential for plastic adaptation of plants to changes in the environment. Fluorescent reporters and confocal microscopy are among the most frequently used methods for assessing plant autophagic activity. However, detection of dynamic changes in the pathway activity has been hampered by stresses imposed on living plant tissues during sample mounting and imaging. Here we implemented RoPod, a toolkit optimized for minimally-invasive time-lapse imaging of Arabidopsis roots, to reveal a time-resolved response of plant autophagy to drug treatments typically used for pathway modulation and discovered previously overlooked cell type-specific changes in the pathway response. These results not only give an insight into the complex dynamics of plant autophagy, but also provide necessary information for choosing sampling time for the end-point assays currently employed in plant autophagy research. RoPods are inexpensive and easy-to-use devices that are based on commercial or custom designed chambers, compatible with inverted microscopes. We describe a detailed protocol for the fabrication and use of RoPods and provide a complete pipeline including semi-automated image analysis for root hair growth assays, demonstrating the broader applicability of the RoPod toolkit.