X-ray computed microtomography (μCT) is an innovative and nondestructive versatile technique that has been used extensively to investigate bio-based systems in multiple application areas. Emerging progress in this field has brought countless studies using μCT characterization, revealing three-dimensional (3D) material structures and quantifying features such as defects, pores, secondary phases, filler dispersions, and internal interfaces. Recently, x-ray computed tomography (CT) beamlines coupled to synchrotron light sources have also enabled computed nanotomography (nCT) and four-dimensional (4D) characterization, allowing in situ, in vivo, and in operando characterization from the micro- to nanostructure. This increase in temporal and spatial resolutions produces a deluge of data to be processed, including real-time processing, to provide feedback during experiments. To overcome this issue, deep learning techniques have risen as a powerful tool that permits the automation of large amounts of data processing, availing the maximum beamline capabilities. In this context, this review outlines applications, synchrotron capabilities, and data-driven processing, focusing on the urgency of combining computational tools with experimental data. We bring a recent overview on this topic to researchers and professionals working not only in this and related areas but also to readers starting their contact with x-ray CT techniques and deep learning.