Comparison of Various Online Strategies to Account for Interfractional Variations for Pancreatic Cancer

Purpose: To identify practical techniques to address the large interfractional variations for pancreas irradiation by comparing various used/proposed online strategies. Methods and Materials: The daily computed tomography (CT) images acquired using a respiration-gated in-room CT (CTVision; Siemens) for 10 pancreatic cancer patients treated with image guided radiation therapy (IGRT) were analyzed. The contours of the pancreas and organs at risk on each daily CT set were generated by populating from the planning CT using a deformable registration tool (ABAS; Elekta) with manual editing. Nine online strategies were considered: (1) standard IGRT (ie, IGRT with 0-mm additional margin [AM]); (2) IGRT with 2-mm AM; (3) IGRT with 5-mm AM; (4) IGRT with plan renormalized to maintain 95% planning target volume (PTV) coverage; (5) full-scale reoptimization; (6) reoptimization starting from the original plan; (7) segment aperture morphing (SAM) from the original plan, based on PTV shape change; (8) SAM plus segment weight optimization; and (9) reoptimization starting from the SAM plan. One-way analysis of variance was applied to plan qualities for the 9 strategies to assess statistical significance in difference. Results: The 3 IGRT strategies (1-3) lead to either inadequate PTV coverage or higher doses to critical structures, indicating that the additional margins alone are not adequate to account for the changes. The full-scale reoptimization results in the best plan but requires the delineation of several structures, which is time consuming. The SAM strategy (7) was the fastest one, because it requires delineating only 1 structure (target), and its plan quality was comparable to that for the full-scale reoptimization. Conclusion: Online replanning strategies can lead to either reduced organs-at-risk dose and/or improved target coverage as compared with the current practice of IGRT. The SAM-based online replanning is comparable to full-scale reoptimization and is efficient for practical use