Unsupervised Profiling of Microglial Arbor Morphologies and Distribution Using a Nonparametric Bayesian Approach

摘要

The morphologies of microglial arbors in brain tissue are important indicators of their state of activation, and their spatial distribution indicates patterns of tissue perturbation. This paper presents a non-parametric Bayesian approach to unsupervised quantitative profiling of microglial activation states, and mapping their 3-D spatial distributions across extended brain tissue regions imaged by mosaiced confocal microscopy. Our approach is to perform large-scale automated reconstruction of all the microglia using a learned label-consistent dictionary model for the microglial processes, and extract 136 arbor features per cell. We then fit an infinite Gaussian mixture model with collapsed Gibbs sampling to the arbor features, to discover arbor-morphological classes, their morphological ‘signatures’, and the associated covariance matrices all in an unsupervised manner. This nonparametric approach can handle clusters with arbitrarily shaped covariance matrices, perform automatic model selection, handle unbalanced clusters, and detect overlapping classes, without the need to specify the number of clusters. The results can be used for diverse investigational purposes, including: population-scale modeling, automated discovery of arbor classes and their distinguishing quantitative signatures and features, quantifying the nature and extent of the cellular heterogeneity, and spatial mapping of cellular arbor morphologies, and mapping tissue alterations.