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

μGlia-Flow, an automatic workflow for microglia segmentation and classification

BACKGROUND

Microglia are important immune cells in the central nervous system, playing a key role in various pathological processes. The morphological diversity of microglia is closely linked to the development of brain diseases, yet accurate segmentation and automatic classification of microglia remain challenging.

NEW METHOD

We proposed a workflow, μGlia-Flow, which integrates both segmentation and classification for microglia analysis. The Frangi filtering algorithm was employed for branch segmentation, and an edge-guided attention TransUNet (EGA-Net) was used for soma segmentation. A Vision Transformer (ViT) network was applied to classify different morphologies.

RESULTS

The Frangi filtering algorithm produces more complete branches with smoother edges and clearer structures. The EGA-Net improves Dice and IoU scores by 4.02 % and 6.75 %, respectively. ViT achieves over 99 % precision in classification. Post-processing reveals decreasing complexity during activation, validating the accuracy of μGlia-Flow.

COMPARISON WITH EXISTING METHODS

μGlia-Flow introduces deep learning, significantly improving segmentation accuracy and addressing the parameter dependency of existing classification methods.

CONCLUSION

we present an automatic workflow for segmenting and classifying microglia, providing a powerful tool for different morphology analysis.

StainAI: quantitative mapping of stained microglia and insights into brain-wide neuroinflammation and therapeutic effects in cardiac arrest

Microglia, the brain's resident macrophages, participate in development and influence neuroinflammation, which is characteristic of multiple brain pathologies. Diverse insults cause microglia to alter their morphology from "resting" to "activated" shapes, which vary with stimulus type, brain location, and microenvironment. This morphologic diversity commonly restricts microglial analyses to specific regions and manual methods. We introduce StainAI, a deep learning tool that leverages 20x whole-slide immunohistochemistry images for rapid, high-throughput analysis of microglial morphology. StainAI maps microglia to a brain atlas, classifies their morphology, quantifies morphometric features, and computes an activation score for any region of interest. As a proof of principle, StainAI was applied to a rat model of pediatric asphyxial cardiac arrest, accurately classifying millions of microglia across multiple slices, surpassing current methods by orders of magnitude, and identifying both known and novel activation patterns. Extending its application to a non-human primate model of simian immunodeficiency virus infection further demonstrated its generalizability beyond rodent datasets, providing new insights into microglial responses across species. StainAI offers a scalable, high-throughput solution for microglial analysis from routine immunohistochemistry images, accelerating research in microglial biology and neuroinflammation.

Targeted therapy and deep learning insights into microglia modulation for spinal cord injury

Spinal cord injury (SCI) is a devastating condition that can cause significant motor and sensory impairment. Microglia, the central nervous system's immune sentinels, are known to be promising therapeutic targets in both SCI and neurodegenerative diseases. The most effective way to deliver medications and control microglial inflammation is through nanovectors; however, because of the variability in microglial morphology and the lack of standardized techniques, it is still difficult to precisely measure their activation in preclinical models. This problem is especially important in SCI, where the intricacy of the glia response following traumatic events necessitates the use of a sophisticated method to automatically discern between various microglial cell activation states that vary over time and space as the secondary injury progresses. We address this issue by proposing a deep learning-based technique for quantifying microglial activation following drug-loaded nanovector treatment in a preclinical SCI model. Our method uses a convolutional neural network to segment and classify microglia based on morphological characteristics. Our approach's accuracy and efficiency are demonstrated through evaluation on a collection of histology pictures from injured and intact spinal cords. This robust computational technique has potential for analyzing microglial activation across various neuropathologies and demonstrating the usefulness of nanovectors in modifying microglia in SCI and other neurological disorders. It has the ability to speed development in this crucial sector by providing a standardized and objective way to compare therapeutic options.

Using focused ultrasound to modulate microglial structure and function

Transcranial focused ultrasound (FUS) has the unique ability to target regions of the brain with high spatial precision, in a minimally invasive manner. Neuromodulation studies have shown that FUS can excite or inhibit neuronal activity, demonstrating its tremendous potential to improve the outcome of neurological diseases. Recent evidence has also shed light on the emerging promise that FUS has, with and without the use of intravenously injected microbubbles, in modulating the blood-brain barrier and the immune cells of the brain. As the resident immune cells of the central nervous system, microglia are at the forefront of the brain's maintenance and immune defense. Notably, microglia are highly dynamic and continuously survey the brain parenchyma by extending and retracting their processes. This surveillance activity aids microglia in performing key physiological functions required for brain activity and plasticity. In response to stressors, microglia rapidly alter their cellular and molecular profile to help facilitate a return to homeostasis. While the underlying mechanisms by which both FUS and FUS + microbubbles modify microglial structure and function remain largely unknown, several studies in adult mice have reported changes in the expression of the microglia/macrophage marker ionized calcium binding adaptor molecule 1, and in their phagocytosis, notably of protein aggregates, such as amyloid beta. In this review, we discuss the demonstrated and putative biological effects of FUS and FUS + microbubbles in modulating microglial activities, with an emphasis on the key cellular and molecular changes observed in vitro and in vivo across models of brain health and disease. Understanding how this innovative technology can modulate microglia paves the way for future therapeutic strategies aimed to promote beneficial physiological microglial roles, and prevent or treat maladaptive responses.

Microglial morphometric analysis: so many options, so little consistency

Quantification of microglial activation through morphometric analysis has long been a staple of the neuroimmunologist's toolkit. Microglial morphological phenomics can be conducted through either manual classification or constructing a digital skeleton and extracting morphometric data from it. Multiple open-access and paid software packages are available to generate these skeletons via semi-automated and/or fully automated methods with varying degrees of accuracy. Despite advancements in methods to generate morphometrics (quantitative measures of cellular morphology), there has been limited development of tools to analyze the datasets they generate, in particular those containing parameters from tens of thousands of cells analyzed by fully automated pipelines. In this review, we compare and critique the approaches using cluster analysis and machine learning driven predictive algorithms that have been developed to tackle these large datasets, and propose improvements for these methods. In particular, we highlight the need for a commitment to open science from groups developing these classifiers. Furthermore, we call attention to a need for communication between those with a strong software engineering/computer science background and neuroimmunologists to produce effective analytical tools with simplified operability if we are to see their wide-spread adoption by the glia biology community.

A comparison of machine learning approaches for the quantification of microglial cells in the brain of mice, rats and non-human primates

Microglial cells are brain-specific macrophages that swiftly react to disruptive events in the brain. Microglial activation leads to specific modifications, including proliferation, morphological changes, migration to the site of insult, and changes in gene expression profiles. A change in inflammatory status has been linked to many neurodegenerative diseases such as Parkinson's disease and Alzheimer's disease. For this reason, the investigation and quantification of microglial cells is essential for better understanding their role in disease progression as well as for evaluating the cytocompatibility of novel therapeutic approaches for such conditions. In the following study we implemented a machine learning-based approach for the fast and automatized quantification of microglial cells; this tool was compared with manual quantification (ground truth), and with alternative free-ware such as the threshold-based ImageJ and the machine learning-based Ilastik. We first trained the algorithms on brain tissue obtained from rats and non-human primate immunohistochemically labelled for microglia. Subsequently we validated the accuracy of the trained algorithms in a preclinical rodent model of Parkinson's disease and demonstrated the robustness of the algorithms on tissue obtained from mice, as well as from images provided by three collaborating laboratories. Our results indicate that machine learning algorithms can detect and quantify microglial cells in all the three mammalian species in a precise manner, equipotent to the one observed following manual counting. Using this tool, we were able to detect and quantify small changes between the hemispheres, suggesting the power and reliability of the algorithm. Such a tool will be very useful for investigation of microglial response in disease development, as well as in the investigation of compatible novel therapeutics targeting the brain. As all network weights and labelled training data are made available, together with our step-by-step user guide, we anticipate that many laboratories will implement machine learning-based quantification of microglial cells in their research.