Extended Data Fig. 5: Validation of ERnet on publicly available datasets of ER images. | Nature Methods

Extended Data Fig. 5: Validation of ERnet on publicly available datasets of ER images.

From: ERnet: a tool for the semantic segmentation and quantitative analysis of endoplasmic reticulum topology

Extended Data Fig. 5

ERnet recovers network topologies from ER recorded with different imaging techniques and cell types, including mammalian and plant cells. (a)–(g) Raw images (grayscale images, left hand side) and corresponding results from ERnet image segmentation (colour images, right hand side). Tubules (cyan), sheets (yellow), and sheet-based tubules, SBTs (magenta) are clearly recovered in all cases studied. (a-b) are from the dataset provided by Pain et al.13 and represent ER present in plant cells recorded with AiryScan confocal imaging; 33 different images from this dataset were reanalysed by ERnet and compared with the results from AnalyzER; (c-f) are from the dataset provided by Qiao et al., 2021 (COS-7 cells, recorded with SIM); 18 different images from this dataset were tested by ERnet; (g) is from the dataset provided by Qin et al., 2020 (COS-7 cells, recorded with SIM); 2 different images from this dataset were tested by ERnet; (h) ER morphology metrics for all structures identified by ERnet. See Source Data Extended Data Fig. 5.

Source data

Back to article page