X-ray computed tomography is an extremely useful tool for the non-destructive analysis of additively manufactured (AM) components. AM components often show manufacturing defects such as high porosity, rough surfaces, or a lack of fusion (LoF) between production layers. These imperfections can be detrimental for the fatigue life of components. To better understand how cracks initiate and grow from internal defects, we fabricated Ti-6Al-4V samples with an internal cavity using electron beam powder bed fusion (PBF-EB/M). The samples were tested in the high-cycle fatigue (HCF) and very high-cycle fatigue (VHCF) regime using ultrasonic testing equipment and analyzed with X-ray computed tomography (XCT). X-ray imaging was used to locate crack initiation sites around defects and to measure characteristic properties of the crack and the defects with the aid of deep learning segmentation tools. LoF defects exposed to the outer surface of the samples due to machining and post-processing, were found to be as detrimental to the fatigue life as the printed central artificial defects. The work presented here can benefit industries that utilize the AM of high-strength, light-weight alloys, such as aerospace and medicine, in the design and manufacturing of components by improving part reliability and fatigue life.