川田 奈緒子

RATIONALE AND OBJECTIVES: To analyze morphological changes in patients with COVID-19-associated pneumonia over time, a nonrigid registration technique is required that reduces differences in respiratory phase and imaging position and does not excessively deform the lesion region. A nonrigid registration method using deep learning was applied for lung field alignment, and its practicality was verified through quantitative evaluation, such as image similarity of whole lung region and image similarity of lesion region, as well as visual evaluation by a physician. MATERIALS AND METHODS: First, the lung field positions and sizes of the first and second CT images were roughly matched using a classical registration method based on iterative calculations as a preprocessing step. Then, voxel-by-voxel transformation was performed using VoxelMorph, a nonrigid deep learning registration method. As an objective evaluation, the similarity of the images was calculated. To evaluate the invariance of image features in the lesion site, primary statistics and 3D shape features were calculated and statistically analyzed. Furthermore, as a subjective evaluation, the similarity of images and whether nonrigid transformation caused unnatural changes in the shape and size of the lesion region were visually evaluated by a pulmonologist. RESULTS: The proposed method was applied to 509 patient data points with high image similarity. The variances in histogram characteristics before and after image deformation were confirmed. Visual evaluation confirmed the agreement between the shape and internal structure of the lung field and the natural deformation of the lesion region. CONCLUSION: The developed nonrigid registration method was shown to be effective for quantitative time series analysis of the lungs.

INTRODUCTION: To date, there is limited evidence on the effects of bronchodilators on respiratory dynamics in chronic obstructive pulmonary disease (COPD). Dynamic chest radiography (DCR) is a novel radiographic modality that provides real-time, objective and quantifiable kinetic data, including changes in the lung area (Rs), tracheal diameter, diaphragmatic kinetics and pulmonary ventilation during respiration, at a lower radiation dose than that used by fluoroscopic or CT imaging. However, the therapeutic effect of dual bronchodilators on respiratory kinetics, such as chest wall dynamics and respiratory muscle function, has not yet been prospectively evaluated using DCR. AIM: This study aims to evaluate the effects of bronchodilator therapy on respiratory kinetics in patients with COPD using DCR. METHODS AND ANALYSIS: This is an open-label, prospective, single-centre, non-controlled, comparative study. A total of 35 patients with COPD, aged 40-85 years, with a forced expiratory volume in the first second of 30-80%, will be enrolled. After a 2-4 weeks washout period, patients will receive tiotropium/olodaterol therapy for 6 weeks. Treatment effects will be evaluated based on DCR findings, pulmonary function test results and patient-related outcomes obtained before and after treatment. The primary endpoint is the change in Rs after therapy. The secondary endpoints include differences in other DCR parameters (diaphragmatic kinetics, tracheal diameter change and maximum pixel value change rate), pulmonary function test results and patient-related outcomes between pre-therapy and post-therapy values. All adverse events will be reported. ETHICS AND DISSEMINATION: Ethical approval for this study was obtained from the Ethics Committee of Chiba University Hospital. The results of this trial will be published in a peer-reviewed journal. TRIAL REGISTRATION NUMBER: jRCTs032210543.