Instance segmentation of mitochondria in electron microscopy images with a generalist deep learning model trained on a diverse dataset

Mitochondria are extremely pleomorphic organelles. Automatically annotating each one accurately and pre-cisely in any 2D or volume electron microscopy (EM) image is an unsolved computational challenge. Current deep learning-based approaches train models on images that provide limited cellular contexts, precluding generality. To address this, we amassed a highly heterogeneous-1.5 3 106 image 2D unlabeled cellular EM dataset and segmented-135,000 mitochondrial instances therein. MitoNet, a model trained on these re-sources, performs well on challenging benchmarks and on previously unseen volume EM datasets containing tens of thousands of mitochondria. We release a Python package and napari plugin, empanada, to rapidly run inference, visualize, and proofread instance segmentations. A record of this paper's transparent peer review process is included in the supplemental information.