Temporal Changes in IMRT Contouring of Organs at Risk for Nasopharyngeal Carcinoma - The Learning Curve Blues and a Tool that Could Help

With improved target conformality, the transition to IMRT for nasopharyngeal cancer (NPC) has moved contouring accuracy and consistency to the forefront. At NUH, IMRT for NPC was implemented in 2005, with more than 70 patients treated since then. The objective was to measure the accuracy and variability of contouring organs at risk (OAR) over time. The first 10 patients, 5 from each of the two head and neck (H&N) Radiation Oncologists, treated by IMRT in 2005 formed cohort A. Ten patients, matched by stage, treated by IMRT in 2007 formed cohort B. The RTOG 0225 protocol was followed. These 20 plans were retrieved from archive. A H&N Radiologist, who is a member of the UICC Expert Panel for the TNM Staging of NPC, reviewed the original OAR contours and developed a standardized OAR contouring template. Using the template, the OAR volumes were then re-contoured in all 20 cases, representing the gold standard against which the original volume was compared. For each patient, comparisons were made between the original and standardized contours using volumetric and spatial parameters. Cohort A was then compared with cohort B to determine whether accuracy and variability changed over time. Evaluated OAR volumes included the temporal lobes, brainstem, optic nerves, optic chiasm, pituitary, temporo-mandibular joint (TMJ), parotid glands, inner ears, eyes, and thyroid. While the original temporal lobe contours were significantly larger in cohort 8 (60.2 vs. 106.8 mL, p=0.02), the absolute difference between the original and standardized volumes was reduced by 53% (p=0.02) and there was no difference in the centroid coordinates and the overlapping fraction. While the inner ear was consistently contoured between cohort A and B, there was systematic exclusion of the cochlea in the contours. The original optic nerve contours decreased from cohort A to 6 (p=0.008), with an improvement in overlap fraction (p=0.06). The TMJ original volumes were smaller for cohort B than A, with a correspondingly significant improvement in overlapping fraction (p=0.02) with the standardized volumes. No difference was seen in the remaining OAR.