Unraveling Microglial Spatial Organization in the Developing Human Brain with DeepCellMap, a Deep Learning Approach Coupled to Spatial Statistics

Abstract

Mapping cellular organization in the developing brain presents significant challenges due to the multidimensional nature of the data, characterized by complex spatial patterns that are difficult to interpret without high-throughput tools. We developed DeepCellMap, a deep-learning-assisted tool that integrates multi-scale image processing with advanced spatial and clustering statistics. This pipeline was designed to map microglial organization during normal and pathological brain development but can be adapted to any cell type. Using DeepCellMap, we capture the morphological diversity of microglia, identify strong coupling between proliferative and phagocytic phenotypes, and show that distinct spatial clusters rarely overlap as human brain development progresses. Additionally, we uncover a novel association between microglia and blood vessels in fetal brains exposed to maternal SARS-CoV-2. These findings offer insights into whether various microglial phenotypes form networks in the developing brain to occupy space, and in conditions involving haemorrhages, whether microglia respond to, or influence changes in blood vessel integrity. DeepCellMap is available as open-source software and is a powerful tool for extracting spatial statistics and analyzing cellular organization in large tissue sections, accommodating various imaging modalities. This platform could open new avenues for studying brain development and related pathologies.