Methane (CH4) hydrate dissociation and CH4 release are potential geohazards currently investigated using X-ray computed tomography (XCT) imaging in laboratory experiments. Image segmentation constitutes an important data processing step for this type of research, but it is often time consuming, computing resource-intensive and operator-dependent. Furthermore, segmentation procedures are frequently tailored for each XCT data set due to differences in image characteristics, such as greyscale contrast variations. To address these issues, an investigation has been carried out using U-Nets, a novel class of Convolutional Neural Network, to segment synchrotron radiation XCT (SRXCT) images of CH4-bearing sand during hydrate formation. Three U-Net deployment methodologies previously untried for this task were assessed: (1) 3D hierarchical, (2) 2D multilabel and (3) RootPainter, a 2D application that implements interactive corrections. Results show high segmentation accuracy, with RootPainter slightly outperforming the alternative approaches. Greyscale contrast between material phases was found to affect segmentation performance, with the lowest metrics corresponding to data exhibiting the lowest contrast. Segmentation accuracy affected derived parameters such as CH4-saturation and porosity, but errors were small compared with gravimetric methods. It was also found that U-Net models trained on low greyscale contrast images could be used to segment higher-contrast data sets and produce accurate 3D visualizations of CH4 distribution, demonstrating model portability. Such portability is anticipated to be advantageous when the segmentation of large XCT data sets needs to be delivered over short timespans.