Reproducibility of Tumor Perfusion Measurements Using 15O-Labeled Water and PET

PET and O-15-labeled water ((H2O)-O-15) can be used to noninvasively monitor tumor perfusion. This allows evaluation of the direct target of antiangiogenic drugs, that is, tumor vasculature. Because these drugs often result in consolidation rather than regression of the tumor mass, a change in perfusion might be a more sensitive way to evaluate response than are indirect size measures on a CT scan. However, to use the technique for serial imaging of individual patients, good reproducibility is essential. The purpose of the present study was to evaluate the reproducibility of quantitative (H2O)-O-15 measurements. Methods: Nine patients with non-small-cell lung cancer (NSCLC) were scanned twice within 7 d and before any therapy. All (H2O)-O-15 scans were followed by an F-18-fluorothymidine scan to allow for adequate volume-of-interest (VOI) definition. VOIs were defined using a 3-dimensional threshold technique. Tumor perfusion and the volume of distribution (V-T) were obtained using a 1-tissue-compartment model including an arterial blood volume component and an image-derived input function. The level of agreement between test and retest values was assessed using the intraclass correlation coefficient (ICC) and Bland-Altman analyses. Possible dependency on absolute values and lesion size was assessed by linear regression. Results: All primary tumors and more than 90% of clinically suspected locoregional metastases could be delineated. In total, 14 lesions in 9 patients were analyzed. Tumor perfusion showed excellent reproducibility, with an ICC of 0.95 and SD of 9%. The V-T was only moderately reproducible, with an ICC of 0.52 and SD of 16%. No dependency was found on absolute values of perfusion (P = 0.14) and V-T (P = 0.15). In addition, tumor volume did not influence the reproducibility of perfusion (P = 0.46) and V-T (P = 0.25). Conclusion: Quantitative measurements of tumor perfusion using (H2O)-O-15 and PET are reproducible in NSCLC. When patients are repeatedly being scanned during therapy, changes of more than 18% in tumor perfusion and 32% in V-T (>1.96 x SD) are likely to represent treatment effects.