Most histological analysis of tissue microstructure is inherently 2D. In this work, we implement a deep learning approach to extract 3D microstructural measures from 2D microscopy images. Specifically, we train a neural network to estimate 3D fiber orientation distributions from myelin-stained micrographs. We apply this technique to an entirely unseen brain, which suggests the potential to use this methodology on consecutive 2D slices to investigate 3D structural connectivity using “myelin-stained-tractography” at resolutions much higher than possible with current diffusion MRI practices. There is potential to use similar techniques to estimate a number of 3D metrics from common 2D histological contrasts.