Abstract: Measurement of multiphase flow faces critical challenges in capturing mesoscale dynamic structures due to the limitation from spatial and temporal resolution of current measuring techniques. Dynamic X-ray computed tomography (CT), as a non-invasive multiphase flow measurement technique, is promising for measuring the mesoscale structures of multiphase flow. Focusing on the gas-liquid two-phase flow in multiphase flow, this paper addresses limited angle artifacts and excessive reconstruction time in mesoscale dynamic structures, and designs a U-Net enhanced SIRT reconstruction algorithm for bubble structure measurement of gas-liquid two-phase flow. Based on the hardware designing of Flowfield Dynamic Measurement System (FDMS), a limited-angle dynamic X-ray CT system, a simulated gas-liquid two-phase flow dataset for training the deep learning model is constructed from 3D bubble structures collected from hydrogel phantoms. The proposed method achieved good results in the training and testing of the constructed dataset and significantly reduced the reconstruction time, providing a new technical approach for the efficient measurement of multiphase flow mesoscale structures.