Supervised Texture-Based Classification for 3DEM

Dense 3DEM data recovered by Serial Block Face Imaging (SBFI), Serial Section Transmission Electron Microscopy (ssTEM), and Focused Ion Beam Scanning Electron Microscopy (FIB-SEM) present challenging image segmentation needs. Typically a biologist wants to isolate membranes, organelles, extracellular matrix components, etc. Traditional image processing may struggle to faithfully follow such features. The variance in electron density from blocks of tissue stained with heavy metals provides ample signal for machine learning methods, though. Here, we demonstrate supervised image classification based on image texture as implemented in Amira Software.