Transmission x-ray microscopy at the Advanced Photon Source has become an increasingly popular technique owing to its non-destructive nature and ability to probe large volumes of material at unprecedented spatial and temporal resolutions. This need has become even more critical with the recent advent of 4D characterization (the fourth dimension being time), which has been instrumental in investigating several fundamental phenomena such as initiation, and propagation of failure at high temperatures, dendritic solidification,and more recently, microstructural evolution of nanoscale precipitates at high temperatures in aluminum alloys. Critical to understanding these phenomena is the segmentation of large volumes of data, presently performed manually in an error prone and time-consuming process. Argonne researchers, in collaboration with researchers at Arizona State University, have developed new automated segmentation methods using a convolutional neural network architecture based on a deep learning approach. The ability of this new approach to robustly process ultra-large volumes of data in relatively small time frames can exponentially accelerate tomographic data analysis