Automatic delineation of functional lung volumes with 68Ga-ventilation/perfusion PET/CT

Background: Functional volumes computed from Ga-68-ventilation/perfusion (V/Q) PET/CT, which we have shown to correlate with pulmonary function test parameters (PFTs), have potential diagnostic utility in a variety of clinical applications, including radiotherapy planning. An automatic segmentation method would facilitate delineation of such volumes. The aim of this study was to develop an automated threshold-based approach to delineate functional volumes that best correlates with manual delineation. Thirty lung cancer patients undergoing both V/Q PET/CT and PFTs were analyzed. Images were acquired following inhalation of Galligas and, subsequently, intravenous administration of Ga-68-macroaggreted-albumin (MAA). Using visually defined manual contours as the reference standard, various cutoff values, expressed as a percentage of the maximal pixel value, were applied. The average volume difference and Dice similarity coefficient (DSC) were calculated, measuring the similarity of the automatic segmentation and the reference standard. Pearson's correlation was also calculated to compare automated volumes with manual volumes, and automated volumes optimized to PFT indices. Results: For ventilation volumes, mean volume difference was lowest (-0.4%) using a 15% max threshold with Pearson's coefficient of 0.71. Applying this cutoff, median DSC was 0.93 (0.87-0.95). Nevertheless, limits of agreement in volume differences were large (-31.0 and 30.2%) with differences ranging from -40.4 to + 33.0%. For perfusion volumes, mean volume difference was lowest and Pearson's coefficient was highest using a 15% max threshold (3.3% and 0.81, respectively). Applying this cutoff, median DSC was 0.93 (0.88-0.93). Nevertheless, limits of agreement were again large (-21.1 and 27.8%) with volume differences ranging from -18.6 to + 35.5%. Using the 15% max threshold, moderate correlation was demonstrated with FEV1/FVC (r = 0.48 and r = 0.46 for ventilation and perfusion images, respectively). No correlation was found between other PFT indices. Conclusions: To automatically delineate functional volumes with Ga-68-V/Q PET/CT, the most appropriate cutoff was 15% max for both ventilation and perfusion images. However, using this unique threshold systematically provided unacceptable variability compared to the reference volume and relatively poor correlation with PFT parameters. Accordingly, a visually adapted semi-automatic method is favored, enabling rapid and quantitative delineation of lung functional volumes with Ga-68-V/Q PET/CT.