Lung isolation is primarily accomplished using a double-lumen tube (DLT) or bronchial blocker. A precise and accurate size of the DLT is a prerequisite for ensuring its accurate placement. Three-dimensional (3D) reconstruction technology can be used to accurately reproduce tracheobronchial structures to improve the accuracy of DLT size selection. Therefore, we have developed automatic comparison software for 3D reconstruction based on CT data (3DRACS). In this study, we aimed to evaluate the efficiency of using 3DRACS to select the DLT size for endobronchial intubation in comparison with using the 'blind' DLT intubation method to determine the DLT size, which is based on height and sex.This is a prospective, single-centre, double-blind randomised controlled trial. In total, 200 patients scheduled for lung resection using a left DLT will be randomly allocated to the 3D group or the control group at a 1:1 ratio. A 3DRACS will be used for the 3D group to determine the size of the DLT, while in the case of the control group, the size of the DLT will be determined according to patient height and sex. The primary outcome is the success rate of placement of the left DLT without fibreoptic bronchoscopy (FOB). The secondary outcomes include the following: successful intubation time, degree of pulmonary atrophy, grade of airway injury, oxygenation during one-lung ventilation, postoperative sore throat and hoarseness, and number of times FOB is used.Ethical approval has been obtained from our local ethics committee (approval number: SCCHEC-02-2022-155). Written informed consent will be obtained from all participants before randomisation, providing them with clear instructions about the purpose of the study. The results will be disseminated through peer-reviewed publications and conferences.NCT06258954.© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.