An optimized optical-flow-based method for quantitative tracking of ultrasound-guided right diaphragm deformation

Abstract

Abstract Objectives To develop a quantitative analysis method for right diaphragm deformation. This method is based on optical flow and applied to diaphragm ultrasound imaging. Methods This study enrolls six healthy subjects and eight patients under mechanical ventilation. Dynamic images with 3–5 breathing cycles were acquired from three directions of right diaphragm by a portable ultrasound system. Filtering and density clustering algorithms are used for denoising Digital Imaging and Communications in Medicine (DICOM) data. An optical flow based method is applied to track movements of the right diaphragm. An improved drift correction algorithm is used to optimize the results. The method can automatically analyze the respiratory cycle, inter-frame/cumulative vertical and horizontal displacements, and strain of the input right diaphragm ultrasound image. Results The optical-flow-based diaphragm ultrasound image motion tracking algorithm can accurately track the right diaphragm during respiratory motion. There are significant differences in horizontal and vertical displacements in each section (p-values 0.05 for all). Conclusions The developed method can quantitatively evaluate the inter-frame/cumulative displacement of the diaphragm in both horizontal and vertical directions, as well as the global strain in three different imaging planes. The above indicators can be used to evaluate diaphragmatic dynamics.

Keywords

• Diaphragm
• Optical flow
• Ultrasound
• Strain
• Deformation