A super-voxel-based method for generating surrogate lung ventilation images from CT.

This study aimed to develop and evaluate a super-voxel-based method for surrogate computed tomography ventilation imaging (CTVI). The study used four-dimensional CT (4DCT) and single-photon emission computed tomography (SPECT) images and corresponding lung masks from 21 patients with lung cancer obtained from the Ventilation And Medical Pulmonary Image Registration Evaluation dataset. The lung volume of the exhale CT for each patient was segmented into hundreds of super-voxels using the Simple Linear Iterative Clustering (SLIC) method. These super-voxel segments were applied to the CT and SPECT images to calculate the mean density values ( ) and mean ventilation values ( ), respectively. The final CT-derived ventilation images were generated by interpolation from the values to yield . For the performance evaluation, the voxel- and region-wise differences between and SPECT were compared using Spearman's correlation and the Dice similarity coefficient index. Additionally, images were generated using two deformable image registration (DIR)-based methods, and , and compared with the SPECT images. The correlation between the and of the super-voxel was 0.59 ± 0.09, representing a moderate-to-high correlation at the super-voxel level. In the voxel-wise evaluation, the method achieved a stronger average correlation (0.62 ± 0.10) with SPECT, which was significantly better than the correlations achieved with the (0.33 ± 0.14, < 0.05) and (0.23 ± 0.11, < 0.05) methods. For the region-wise evaluation, the Dice similarity coefficient of the high functional region for (0.63 ± 0.07) was significantly higher than the corresponding values for the (0.43 ± 0.08, < 0.05) and (0.42 ± 0.05, < 0.05) methods. The strong correlation between and SPECT demonstrates the potential usefulness of this novel method of ventilation estimation for surrogate ventilation imaging.