An End-to-end System for Automatic Characterization of Iba1 Immunopositive Microglia in Whole Slide Imaging

A deep convolutional neural network for efficient microglia detection

Microglial cells are a type of glial cells that make up 10-15% of all brain cells, and they play a significant role in neurodegenerative disorders and cardiovascular diseases. Despite their vital role in these diseases, developing fully automated microglia counting methods from immunohistological images is challenging. Current image analysis methods are inefficient and lack accuracy in detecting microglia due to their morphological heterogeneity. This study presents development and validation of a fully automated and efficient microglia detection method using the YOLOv3 deep learning-based algorithm. We applied this method to analyse the number of microglia in different spinal cord and brain regions of rats exposed to opioid-induced hyperalgesia/tolerance. Our numerical tests showed that the proposed method outperforms existing computational and manual methods with high accuracy, achieving 94% precision, 91% recall, and 92% F1-score. Furthermore, our tool is freely available and adds value to exploring different disease models. Our findings demonstrate the effectiveness and efficiency of our new tool in automated microglia detection, providing a valuable asset for researchers in neuroscience.

Regulation of microglia polarization after cerebral ischemia

Stroke ranks second as a leading cause of death and permanent disability globally. Microglia, innate immune cells in the brain, respond rapidly to ischemic injury, triggering a robust and persistent neuroinflammatory reaction throughout the disease's progression. Neuroinflammation plays a critical role in the mechanism of secondary injury in ischemic stroke and is a significant controllable factor. Microglia activation takes on two general phenotypes: the pro-inflammatory M1 type and the anti-inflammatory M2 type, although the reality is more complex. The regulation of microglia phenotype is crucial to controlling the neuroinflammatory response. This review summarized the key molecules and mechanisms of microglia polarization, function, and phenotypic transformation following cerebral ischemia, with a focus on the influence of autophagy on microglia polarization. The goal is to provide a reference for the development of new targets for the treatment for ischemic stroke treatment based on the regulation of microglia polarization.

A novel automated morphological analysis of Iba1+ microglia using a deep learning assisted model

There is growing evidence for the key role of microglial functional state in brain pathophysiology. Consequently, there is a need for efficient automated methods to measure the morphological changes distinctive of microglia functional states in research settings. Currently, many commonly used automated methods can be subject to sample representation bias, time consuming imaging, specific hardware requirements and difficulty in maintaining an accurate comparison across research environments. To overcome these issues, we use commercially available deep learning tools Aiforia^® Cloud (Aifoira Inc., Cambridge, MA, United States) to quantify microglial morphology and cell counts from histopathological slides of Iba1 stained tissue sections. We provide evidence for the effective application of this method across a range of independently collected datasets in mouse models of viral infection and Parkinson's disease. Additionally, we provide a comprehensive workflow with training details and annotation strategies by feature layer that can be used as a guide to generate new models. In addition, all models described in this work are available within the Aiforia^® platform for study-specific adaptation and validation.

Cyclic multiplex fluorescent immunohistochemistry and machine learning reveal distinct states of astrocytes and microglia in normal aging and Alzheimer's disease

BACKGROUND

Astrocytes and microglia react to Aβ plaques, neurofibrillary tangles, and neurodegeneration in the Alzheimer's disease (AD) brain. Single-nuclei and single-cell RNA-seq have revealed multiple states or subpopulations of these glial cells but lack spatial information. We have developed a methodology of cyclic multiplex fluorescent immunohistochemistry on human postmortem brains and image analysis that enables a comprehensive morphological quantitative characterization of astrocytes and microglia in the context of their spatial relationships with plaques and tangles.

METHODS

Single FFPE sections from the temporal association cortex of control and AD subjects were subjected to 8 cycles of multiplex fluorescent immunohistochemistry, including 7 astroglial, 6 microglial, 1 neuronal, Aβ, and phospho-tau markers. Our analysis pipeline consisted of: (1) image alignment across cycles; (2) background subtraction; (3) manual annotation of 5172 ALDH1L1+ astrocytic and 6226 IBA1+ microglial profiles; (4) local thresholding and segmentation of profiles; (5) machine learning on marker intensity data; and (6) deep learning on image features.

RESULTS

Spectral clustering identified three phenotypes of astrocytes and microglia, which we termed "homeostatic," "intermediate," and "reactive." Reactive and, to a lesser extent, intermediate astrocytes and microglia were closely associated with AD pathology (≤ 50 µm). Compared to homeostatic, reactive astrocytes contained substantially higher GFAP and YKL-40, modestly elevated vimentin and TSPO as well as EAAT1, and reduced GS. Intermediate astrocytes had markedly increased EAAT2, moderately increased GS, and intermediate GFAP and YKL-40 levels. Relative to homeostatic, reactive microglia showed increased expression of all markers (CD68, ferritin, MHC2, TMEM119, TSPO), whereas intermediate microglia exhibited increased ferritin and TMEM119 as well as intermediate CD68 levels. Machine learning models applied on either high-plex signal intensity data (gradient boosting machines) or directly on image features (convolutional neural networks) accurately discriminated control vs. AD diagnoses at the single-cell level.

CONCLUSIONS

Cyclic multiplex fluorescent immunohistochemistry combined with machine learning models holds promise to advance our understanding of the complexity and heterogeneity of glial responses as well as inform transcriptomics studies. Three distinct phenotypes emerged with our combination of markers, thus expanding the classic binary "homeostatic vs. reactive" classification to a third state, which could represent "transitional" or "resilient" glia.

MORPHIOUS: an unsupervised machine learning workflow to detect the activation of microglia and astrocytes

Background

In conditions of brain injury and degeneration, defining microglial and astrocytic activation using cellular markers alone remains a challenging task. We developed the MORPHIOUS software package, an unsupervised machine learning workflow which can learn the morphologies of non-activated astrocytes and microglia, and from this information, infer clusters of microglial and astrocytic activation in brain tissue.

Methods

MORPHIOUS combines a one-class support vector machine with the density-based spatial clustering of applications with noise (DBSCAN) algorithm to identify clusters of microglial and astrocytic activation. Here, activation was triggered by permeabilizing the blood–brain barrier (BBB) in the mouse hippocampus using focused ultrasound (FUS). At 7 day post-treatment, MORPHIOUS was applied to evaluate microglial and astrocytic activation in histological tissue. MORPHIOUS was further evaluated on hippocampal sections of TgCRND8 mice, a model of amyloidosis that is prone to microglial and astrocytic activation.

Results

MORPHIOUS defined two classes of microglia, termed focal and proximal, that are spatially adjacent to the activating stimulus. Focal and proximal microglia demonstrated activity-associated features, including increased levels of ionized calcium-binding adapter molecule 1 expression, enlarged soma size, and deramification. MORPHIOUS further identified clusters of astrocytes characterized by activity-related changes in glial fibrillary acidic protein expression and branching. To validate these classifications following FUS, co-localization with activation markers were assessed. Focal and proximal microglia co-localized with the transforming growth factor beta 1, while proximal astrocytes co-localized with Nestin. In TgCRND8 mice, microglial and astrocytic activation clusters were found to correlate with amyloid-β plaque load. Thus, by only referencing control microglial and astrocytic morphologies, MORPHIOUS identified regions of interest corresponding to microglial and astrocytic activation.

Conclusions

Overall, our algorithm is a reliable and sensitive method for characterizing microglial and astrocytic activation following FUS-induced BBB permeability and in animal models of neurodegeneration.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12974-021-02376-9.

Brain Immunoinformatics: A Symmetrical Link between Informatics, Wet Lab and the Clinic

Breakthrough advances in informatics over the last decade have thoroughly influenced the field of immunology. The intermingling of machine learning with wet lab applications and clinical results has hatched the newly defined immunoinformatics society. Immunoinformatics of the central neural system, referred to as neuroimmunoinformatics (NII), investigates symmetrical and asymmetrical interactions of the brain-immune interface. This interdisciplinary overview on NII is addressed to bioscientists and computer scientists. We delineate the dominating trajectories and field-shaping achievements and elaborate on future directions using bridging language and terminology. Computation, varying from linear modeling to complex deep learning approaches, fuels neuroimmunology through three core directions. Firstly, by providing big-data analysis software for high-throughput methods such as next-generation sequencing and genome-wide association studies. Secondly, by designing models for the prediction of protein morphology, functions, and symmetrical and asymmetrical protein–protein interactions. Finally, NII boosts the output of quantitative pathology by enabling the automatization of tedious processes such as cell counting, tracing, and arbor analysis. The new classification of microglia, the brain’s innate immune cells, was an NII achievement. Deep sequencing classifies microglia in “sensotypes” to accurately describe the versatility of immune responses to physiological and pathological challenges, as well as to experimental conditions such as xenografting and organoids. NII approaches complex tasks in the brain-immune interface, recognizes patterns and allows for hypothesis-free predictions with ultimate targeted individualized treatment strategies, and personalizes disease prognosis and treatment response.

Lipopolysaccharide-induced maternal immune activation modulates microglial CX3CR1 protein expression and morphological phenotype in the hippocampus and dentate gyrus, resulting in cognitive inflexibility during late adolescence

Inflammation during pregnancy can disturb brain development and lead to disorders in the progeny, including autism spectrum disorder and schizophrenia. However, the mechanism by which a prenatal, short-lived increase of cytokines results in adverse neurodevelopmental outcomes remains largely unknown. Microglia-the brain's resident immune-cells-stand as fundamental cellular mediators, being highly sensitive and responsive to immune signals, which also play key roles during normal development. The fractalkine signaling axis is a neuron-microglia communication mechanism used to regulate neurogenesis and network formation. Previously, we showed hippocampal reduction of fractalkine receptor (Cx3cr1) mRNA at postnatal day (P) 15 in male offspring exposed to maternal immune activation induced with lipopolysaccharide (LPS) during late gestation, which was concomitant to an increased dendritic spine density in the dentate gyrus, a neurogenic niche. The current study sought to evaluate the origin and impact of this reduced hippocampal Cx3cr1 mRNA expression on microglia and cognition. We found that microglial total cell number and density are not affected in the dorsal hippocampus and dentate gyrus, respectively, but that the microglial CX3CR1 protein is decreased in the hippocampus of LPS-male offspring at P15. Further characterization of microglial morphology in the dentate gyrus identified a more ameboid phenotype in LPS-exposed offspring, predominantly in males, at P15. We thus explored maternal plasma and fetal brain cytokines to understand the mechanism behind microglial priming, showing a robust immune activation in the mother at 2 and 4 hrs after LPS administration, while only IL-10 tended towards upregulation at 2 hrs after LPS in fetal brains. To evaluate the functional long-term consequences, we assessed learning and cognitive flexibility behavior during late adolescence, finding that LPS affects only the latter with a male predominance on perseveration. A CX3CR1 gene variant in humans that results in disrupted fractalkine signaling has been recently associated with an increased risk for neurodevelopmental disorders. We show that an acute immune insult during late gestation can alter fractalkine signaling by reducing the microglial CX3CR1 protein expression, highlighting neuron-microglial fractalkine signaling as a relevant target underlying the outcomes of environmental risk factors on neurodevelopmental disorders.

Post-traumatic Neuroinflammation: Relevance to Pediatrics

Both detrimental and beneficial effects of post-traumatic neuroinflammation have become a major research focus as they offer the potential for immediate as well as delayed targeted reparative therapies. Understanding the complex interactions of central and peripheral immunocompetent cells as well as their mediators on brain injury and recovery is complicated by the temporal, regional, and developmental differences in their response to injuries. Microglia, the brain-resident macrophages, have become central in these investigations as they serve a major surveillance function, have the ability to react swiftly to injury, recruit various cellular and chemical mediators, and monitor the reparative/degenerative processes. In this review we describe selected aspects of this burgeoning literature, describing the critical role of cytokines and chemokines, microglia, advances in neuroimaging, genetics and fractal morphology analysis, our research efforts in this area, and selected aspects of pediatric post-traumatic neuroinflammation.

Classification of Microglial Morphological Phenotypes Using Machine Learning

Microglia are the brain's immunocompetent macrophages with a unique feature that allows surveillance of the surrounding microenvironment and subsequent reactions to tissue damage, infection, or homeostatic perturbations. Thereby, microglia's striking morphological plasticity is one of their prominent characteristics and the categorization of microglial cell function based on morphology is well established. Frequently, automated classification of microglial morphological phenotypes is performed by using quantitative parameters. As this process is typically limited to a few and especially manually chosen criteria, a relevant selection bias may compromise the resulting classifications. In our study, we describe a novel microglial classification method by morphological evaluation using a convolutional neuronal network on the basis of manually selected cells in addition to classical morphological parameters. We focused on four microglial morphologies, ramified, rod-like, activated and amoeboid microglia within the murine hippocampus and cortex. The developed method for the classification was confirmed in a mouse model of ischemic stroke which is already known to result in microglial activation within affected brain regions. In conclusion, our classification of microglial morphological phenotypes using machine learning can serve as a time-saving and objective method for post-mortem characterization of microglial changes in healthy and disease mouse models, and might also represent a useful tool for human brain autopsy samples.

A novel retinal ganglion cell quantification tool based on deep learning

Glaucoma is a disease associated with the loss of retinal ganglion cells (RGCs), and remains one of the primary causes of blindness worldwide. Major research efforts are presently directed towards the understanding of disease pathogenesis and the development of new therapies, with the help of rodent models as an important preclinical research tool. The ultimate goal is reaching neuroprotection of the RGCs, which requires a tool to reliably quantify RGC survival. Hence, we demonstrate a novel deep learning pipeline that enables fully automated RGC quantification in the entire murine retina. This software, called RGCode (Retinal Ganglion Cell quantification based On DEep learning), provides a user-friendly interface that requires the input of RBPMS-immunostained flatmounts and returns the total RGC count, retinal area and density, together with output images showing the computed counts and isodensity maps. The counting model was trained on RBPMS-stained healthy and glaucomatous retinas, obtained from mice subjected to microbead-induced ocular hypertension and optic nerve crush injury paradigms. RGCode demonstrates excellent performance in RGC quantification as compared to manual counts. Furthermore, we convincingly show that RGCode has potential for wider application, by retraining the model with a minimal set of training data to count FluoroGold-traced RGCs.

Automated segmentation and analysis of retinal microglia within ImageJ

Microglia are immune cells of the central nervous system capable of distinct phenotypic changes and migration in response to injury. These changes most notably include the retraction of fine dendritic structures and adoption of a globular, phagocytic morphology. Due to their characteristic responses, microglia frequently act as histological indicators of injury progression. While algorithms seeking to automate microglia counts and morphological analysis are becoming increasingly popular, few exist that are adequate for use within the retina and manual analysis remains prevalent. To address this, we propose a novel segmentation routine, implemented within FIJI-ImageJ, to perform automated segmentation and cell counting of retinal microglia. We show that our routine could perform cell counts with accuracy similar to manual observers using the I307N Rho model. Tracking cell position relative to retinal vasculature, we observed population migration towards the photoreceptor layer beginning 12 h post light damage. Using feature selection with Chi² and principal component analysis, we resolved cells along a morphological gradient, demonstrating that extracted features were sufficiently descriptive to capture subtle morphological changes within cell populations in I307N Rho and Balb/c TLR2^-/- retinal degeneration models. Taken together, we introduce a novel automated routine capable of efficient image processing and segmentation. Using data retrieved following segmentation, we perform morphological analysis simultaneously on whole populations of cells, rather than individually. Our algorithm was built entirely with open-source software, for use on retinal microglia.

Imaging the Neuroimmune Dynamics Across Space and Time

The immune system is essential for maintaining homeostasis, as well as promoting growth and healing throughout the brain and body. Considering that immune cells respond rapidly to changes in their microenvironment, they are very difficult to study without affecting their structure and function. The advancement of non-invasive imaging methods greatly contributed to elucidating the physiological roles performed by immune cells in the brain across stages of the lifespan and contexts of health and disease. For instance, techniques like two-photon in vivo microscopy were pivotal for studying microglial functional dynamics in the healthy brain. Through these observations, their interactions with neurons, astrocytes, blood vessels and synapses were uncovered. High-resolution electron microscopy with immunostaining and 3D-reconstruction, as well as super-resolution fluorescence microscopy, provided complementary insights by revealing microglial interventions at synapses (phagocytosis, trogocytosis, synaptic stripping, etc.). In addition, serial block-face scanning electron microscopy has provided the first 3D reconstruction of a microglial cell at nanoscale resolution. This review will discuss the technical toolbox that currently allows to study microglia and other immune cells in the brain, as well as introduce emerging methods that were developed and could be used to increase the spatial and temporal resolution of neuroimmune imaging. A special attention will also be placed on positron emission tomography and the development of selective functional radiotracers for microglia and peripheral macrophages, considering their strong potential for research translation between animals and humans, notably when paired with other imaging modalities such as magnetic resonance imaging.