AI-directed voxel extraction and volume EM identify intrusions as sites of mitochondrial contact

ABSTRACT Membrane contact sites (MCS) establish organelle interactomes in cells to enable communication and exchange of materials. Volume electron microscopy (vEM) is ideally suited for MCS analyses, but semantic segmentation of large vEM datasets remains challenging. Recent adoption of artificial intelligence (AI) for segmentation has greatly enhanced our analysis capabilities. However, we show that organelle boundaries, which are important for defining MCS, are the least confident predictions made by AI. We outline a segmentation strategy termed AI-directed Voxel Extraction (AIVE), that combines AI predictions with image electron signals to confidently segment membrane boundaries irrespective of the AI model used. We demonstrate the precision conferred by AIVE by applying it to the quantitative analysis of organelle interactomes from multiple FIB-SEM datasets. Through AIVE, we discover a previously unknown category of mitochondrial contact that we term the mitochondrial intrusion. We hypothesise that intrusions serve as anchors that stabilize MCS and promote organelle communication.