V/Q SPECT for the Assessment of Regional Lung Function: Generation of Normal Mean and Standard Deviation 3-D Maps

Background: V/Q SPECT/CT is attractive for regional lung function assessment, but accurate delineation and quantification of functional lung volumes remains a challenge. Physiological intra and inter patient non-uniformity of V/Q SPECT images make conventional delineation methods of functional lung volumes inaccurate. In that context it would be of interest to build statistical maps of normal V/Q SPECT to assess the physiological variability of radiotracers. The aim of this study was to generate normal mean and standard deviation maps of regional lung function as assessed with V/Q SPECT/CT, with (AC) and without (NoAC) attenuation correction. Methods: During a 13 month period, 73 consecutive patients referred for suspected acute pulmonary embolism, that had normal V/Q SPECT/CT based on the interpretation of 2 independent nuclear medicine physicians, were selected. Four set of images were reconstructed: perfusion and ventilation images, AC, and NoAC, respectively. Statistical maps were created as follows: all cases were registered to a reference scan using the CT data, first with a rigid then with a non-rigid method. SPECTs reconstructions were then co-registered and normalized, and mean and standard deviation voxel-wise maps were calculated. To assess the consistency of generated maps to lung physiology and the potential impact of non-rigid registration, visual analysis and quantitative comparison with non-registered data were performed in the whole series. Quantitative comparison was also conducted in two randomly sampled independent subsets. Results: Perfusion mean maps showed a continuous negative posterior to anterior gradient, majored on the AC mean map. Perfusion standard deviation maps showed higher variability in the periphery of the lungs, but especially in the posterior areas. The ventilation mean map showed a slightly positive posterior to anterior gradient on NoAC mean ventilation map, while the AC mean map showed no gradient. The NoAC ventilation SD map showed a higher variability in the periphery of the lungs as compared with AC SD map. No statistical difference in the posterior to anterior gradient measurements was found between the generated mean statistical maps and the non-registered data, either in the whole series or across the two independent datasets. Conclusion: We proposed a methodology to create statistical normal maps for V/Q SPECTs. Maps were consistent with the known physiological non-uniformity and showed the impact of attenuation correction on the posterior to anterior gradient. These maps could be used for a Z-score analysis, and a better segmentation of healthy uptake areas.