Alterations in normal liver doses due to organ motion.

PURPOSE To assess the clinical significance of differences between treatment planning calculations based on static computed tomography (CT) and more realistic predictions of the actual delivered dose to intrahepatic lesions by a geometric convolution approach that accounts for random setup variations and breathing-induced organ motion. MATERIALS AND METHODS We recalculated target and normal liver doses for 40 patients previously treated on a conformal therapy dose escalation protocol to include the effect of setup uncertainties and liver motion due to patient breathing. Initial three-dimensional (3D) dose calculations based on pretreatment CT scans taken with voluntary breath-hold at normal exhalation were convolved with 3D anisotropic probability distribution functions reflecting population measurements of position setup variation. The convolution also included a distribution function (one-dimensional, inferior-superior direction only) representing the asymmetric temporal pattern (biased toward exhalation, based on population measurements) of a typical breathing cycle, scaled in amplitude for each patient. RESULTS After convolution, the minimum clinical target volume (CTV) dose met or exceeded the minimum planning target volume (PTV) dose from the static plan in all but one case, indicating adequate PTV design. However, clinically relevant and statistically significant increases (decreases) in liver normal tissue complication probability (NTCP) from values computed for the static cases occurred for tumors located toward the bottom (top) of the liver, as predicted for these patients scanned at exhalation. The change in liver NTCP (from a nominal 20%) ranged from +12.0% to -11.7% (average magnitude change 3.9% [sigma = 3.3%]). Changes in prescription dose required to restore the original 20% NTCP ranged from -3.7 Gy to +7.9 Gy (average magnitude change 1.9 Gy [sigma = 1.9 Gy]). CONCLUSIONS Although the PTV concept can ensure adequate CTV coverage, the doses to normal liver are incorrectly modeled without including patient-related geometric uncertainties.