This is a method for training a multi-slice U-Net for multi-class segmentation of cryo-electron tomograms using a portion of one tomogram as a training input. We describe how to infer this network to other tomograms and how to extract segmentations for further analyses, such as subtomogram averaging and filament tracing.
Heebner, J. E., Purnell, C., Hylton, R. K., Marsh, M., Grillo, M. A., Swulius, M. T. Deep Learning-Based Segmentation of Cryo-Electron Tomograms. J. Vis. Exp. (189), e64435, doi:10.3791/64435 (2022).