SU‐E‐J‐97: Recursive Contour Propagation Using Feature‐Based Deformable Registration for Lung Cancer
2013
Purpose: Accurate target delineation of CT image is a critical step in treatment planning of radiotherapy.This paper describes a novel strategy of automatic recursive registration for lung segmentation in CT images. Methods: The proposed method started with a manual‐delineated contour in one slice, then by the means of feature‐based deformable registration, its correspondence in other slices could be recursively obtained.There are three algorithms would be implemented:the scale‐invariant feature transform (SIFT),used to automatically detect the feature control point pairs; thin‐plate spline (TPS),used to register a structure characterized by the control points;active contour(Snake), used to refine and correct the autocontour. 5 pulmonary cancer cases would be tested in,each comprising of three target delineation. Results: The use of the proposed recursive feature‐based registration method in the clinical cases leads to an improvement in the manual segmentation and intensity‐based contrast performance in the pulmonary CT planning images, obtaining a mean growth of overlap volume index=8% nearly.In addition,the time consumption decreased by nearly 98%,which largely improve the delineated efficiency of physicians. Conclusion: The application of the feature‐based deformable registration method in the recursive contour propagation during pulmonary cancer treatment planning, greatly improves the delineated efficiency,well agreed with a physician's manual contours. Furthermore, this method could be available in other cases, such as head‐neck, rectum, 3 dimension tumour tracking etc. This work is supported in part by grants from National Natural Science Foundation of China (NSFC: 81171402), NSFC Joint Research Fund for Overseas Research Chinese, Hong Kong and Macao Young Scholars (30928030), National Basic Research Program 973 (2010CB732606) from Ministry of Science and Technology of China, and Guangdong Innovative Research Team Program (No. 2011S013) of China.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
0
References
1
Citations
NaN
KQI