ECS-Net: Extracellular space segmentation with contrastive and shape-aware loss by using cryo-electron microscopy imaging

The transport of molecules within the brain extracellular space (ECS) plays a pivotal role in governing sleep patterns, memory formation, and the aging process in organisms. Isolating and delineating the ECS is crucial for constructing accurate models of molecular dynamics within the intricate neuronal networks. However, the segmentation of the ECS has proven to be a formidable challenge due to its complex morphology, and there is a notable lack of comprehensive studies on such a topic. In this study, we have constructed an exclusive dataset for ECS segmentation, utilizing an advanced imaging technique enabled by cryo-electron microscopy. We introduce ECS-Net, a dedicated segmentation pipeline that integrates contrastive learning approach and shape-aware function. The contrastive learning strategy is employed to effectively differentiate the extracellular space from surrounding neural elements, while the shape-aware function is designed to bolster the model’s sensitivity to the distinctive structures of the ECS. The experimental results indicate that ECS-Net significantly outperforms existing methods in ECS segmentation, achieving an F1-score (F1) that is 2.91% higher and an Intersection-over-union (IOU) that is 4.62% superior on the ECSseg-1 dataset. Moreover, our model exhibits robust generalization capabilities when applied to an independent validation dataset. In summary, this study marks the establishment of the first cascaded network tailored for brain ECS segmentation. Our method is poised to enhance the analysis of ECS structures within an extensive dataset, thereby offering a substantial contribution to the broader biomedical research community. •Constructing a cascaded network named ECS-Net for further refining the structure segmentation of extracellular space.•Presenting a contrastive learning module to solve the imbalance between inter-class and intra-class segmentation.•Presenting a shape-aware function module to hierarchically weight the size, width, and other information of the target structure.•Collecting and annotating an extracellular space segmentation dataset. On the dataset, our method achieves excellent performance.