Contour Propagation Using Feature-based Deformable Registration for Lung Cancer

Purpose: Accurate target delineation of CT image is a critical step in radiotherapy treatment planning. This paper describes a novel strategy for automatic contour propagation, based on deformable registration, for CT images of lung cancer. Methods: The proposed strategy starts with a manual-delineated contour in one slice of a 3D CT image. By means of feature-based deformable registration, the initial contour in other slices of the image can be propagated automatically, and then refined by active contour approach. Three algorithms are employed in the strategy: the Speeded-Up Robust Features (SURF), used to automatically detect the feature control point pairs; Thin-Plate Spline (TPS), used to register a structure characterized by the control points; an adapted active contour (Snake), used to refine and modify the initial contours. Five pulmonary cancer cases with about 400 slices and 1000 contours have been used to verify the proposed strategy. Results: Experiments demonstrate that the proposed strategy can improve the segmentation performance in the pulmonary CT images. Jaccard similarity (JS) mean is about 0.88 and the maximum of Hausdorff distance (HD) is about 90%. In addition, delineation time consume has been considerably reduced. Conclusions: The proposed feature-based deformable registration method in the automatic contour propagation improves the delineation efficiency significantly. Robustness and accuracy of the method is also showed. The proposed method can be applied in various clinical applications, such as treatment planning, adaptive radiation therapy, and 3D tumor tracking et al.