ABSTRACT
Purpose: To develop and validate a set of atlases for auto-contouring cardiac substructures from noncontrast computed tomography (CT) images and evaluate the feasibility of using auto-contouring for cardiac dosimetry and toxicity analyses for patients with non-small cell lung cancer (NSCLC) after radiotherapy.
Methods: Eight radiation oncologists manually and independently delineated 15 cardiac substructures from noncontrast CT images of six patients by referring to their respective fused contrast CT images. Individual contours were fused together for each structure, edited by two physicians, and became atlases to delineate six other patients. The auto-delineated contours of the six additional patients became templates for manual contouring. These 12 patients with well-defined contours composed the final atlases for multi-atlas segmentation and were used to automatically delineate cardiac substructures from the averaged 4D-CT planning images of 49 patients with NSCLC, followed by modifications from radiation oncologists. The modified contours were compared with the auto-segmented contours to evaluate the extent of modification.
Results: The average time for manually contouring the 15 cardiac substructures was about 40 minutes. Inter-observer variability was small for the heart, the chambers, and the aorta compared with that for other structures that were not clearly distinguishable in CT images. The mean Dice similarity coefficient and mean surface distance of auto-segmented contours were within one standard deviation of expert contouring variability. Good agreement between auto-segmented and manual contours was observed for the heart, the chambers, and the great vessels. For auto-segmented contours of the 49 NSCLC patients, the overall modifications were small, with the largest modifications in the pulmonary vein and the inferior vena cava. The heart V30 (volume receiving dose ≥30 Gy) and the mean dose to the whole heart and the four heart chambers were not different for the modified versus the auto-segmented contours based on the statistically significant condition of p < 0.05. Also, the maximum dose to the great vessels was no different except for the pulmonary vein.
Conclusions: It is possible to automatically delineate the heart, the heart chambers, and the great vessels from noncontrast CT images for radiation oncology applications. Automatic segmentation of cardiac substructures did not require substantial modifications, and dosimetric evaluation showed no statistically significant differences between the auto-segmented and modified contours except for the pulmonary vein, suggesting that using auto-segmented contours to study cardiac dose-response is feasible in current clinical practice.
