COMBINe: Automated Detection and Classification of Neurons and Astrocytes in Tissue Cleared Mouse Brains

Tissue clearing renders entire organs transparent to enable combination with light sheet fluorescence microscopy and accelerate whole tissue imaging. Yet, challenges remain in analyzing the large resulting 3D datasets that consist of terabytes of images and information on millions of labeled cells. Previous work has established pipelines for automated analysis of tissue cleared mouse brains. However, they have focused on single color channels and/or detection of nuclear localized signals, in relatively low-resolution images. To address this gap, we present an automated workflow to map labeled neurons and astrocytes in the genetically distinct Mosaic Analysis with Double Markers (MADM) mouse forebrains. We named the workflow COMBINe (Cell detectiOn in Mouse BraIN) as it combines modules from multiple pipelines. With RetinaNet in its core, we quantitatively analyzed the regional and subregional effects of MADM-based deletion of the Epidermal growth factor receptor on neuronal and astrocyte populations in the mouse forebrain.