Reliability and accuracy of three imaging software packages used for 3D analysis of the upper airway on cone beam computed tomography images

摘要

The aim of this study was to assess the reliability and accuracy of three different imaging software packages for three-dimensional analysis of the upper airway using CBCT images. To assess the reliability of the software packages, 15 NewTom 5G(®) (QR Systems, Verona, Italy) CBCT data sets were randomly and retrospectively selected. Two observers measured the volume, minimum cross-sectional area and the length of the upper airway using Amira(®) (Visage Imaging Inc., Carlsbad, CA), 3Diagnosys(®) (3diemme, Cantu, Italy) and OnDemand3D(®) (CyberMed, Seoul, Republic of Korea) software packages. The intra- and inter-observer reliability of the upper airway measurements were determined using intraclass correlation coefficients and Bland & Altman agreement tests. To assess the accuracy of the software packages, one NewTom 5G(®) CBCT data set was used to print a three-dimensional anthropomorphic phantom with known dimensions to be used as the "gold standard". This phantom was subsequently scanned using a NewTom 5G(®) scanner. Based on the CBCT data set of the phantom, one observer measured the volume, minimum cross-sectional area, and length of the upper airway using Amira(®), 3Diagnosys(®), and OnDemand3D(®), and compared these measurements with the gold standard. The intra- and inter-observer reliability of the measurements of the upper airway using the different software packages were excellent (intraclass correlation coefficient ≥0.75). There was excellent agreement between all three software packages in volume, minimum cross-sectional area and length measurements. All software packages underestimated the upper airway volume by -8.8% to -12.3%, the minimum cross-sectional area by -6.2% to -14.6%, and the length by -1.6% to -2.9%. All three software packages offered reliable volume, minimum cross-sectional area and length measurements of the upper airway. The length measurements of the upper airway were the most accurate results in all software packages. All software packages underestimated the upper airway dimensions of the anthropomorphic phantom