Development of an accelerated GVF semi-automatic contouring algorithm for radiotherapy treatment planning

Authors:
Xingen Wu;Sharon A. Spencer;Sui Shen;John B. Fiveash;Jun Duan;Ivan A. Brezovich
Affiliations:
Department of Radiation Oncology, University of Alabama at Birmingham, 1824 6th Avenue South, Birmingham, AL 35249, USA;Department of Radiation Oncology, University of Alabama at Birmingham, 1824 6th Avenue South, Birmingham, AL 35249, USA;Department of Radiation Oncology, University of Alabama at Birmingham, 1824 6th Avenue South, Birmingham, AL 35249, USA;Department of Radiation Oncology, University of Alabama at Birmingham, 1824 6th Avenue South, Birmingham, AL 35249, USA;Department of Radiation Oncology, University of Alabama at Birmingham, 1824 6th Avenue South, Birmingham, AL 35249, USA;Department of Radiation Oncology, University of Alabama at Birmingham, 1824 6th Avenue South, Birmingham, AL 35249, USA
Venue:
Computers in Biology and Medicine
Year:
2009

Citing 3
Cited 1

Gradient Vector Flow: A New External Force for Snakes

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Automated segmentation of the left ventricle including papillary muscles in cardiac magnetic resonance images

FIMH'07 Proceedings of the 4th international conference on Functional imaging and modeling of the heart
Snakes, shapes, and gradient vector flow

IEEE Transactions on Image Processing

Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation

Computers in Biology and Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

Fast contouring is important in image-guided radiation therapy (IGRT) and adaptive radiation therapy (ART) where large computed tomography (CT) volumes have to be segmented. In this study, a modified active contour (also called snake) segmentation method based on a faster gradient-vector-flow (GVF) calculation algorithm is proposed. The accelerated method was tested on multiple organs, including lung, right ventricle, kidney and prostate. Compared to the original algorithm, the improved one reduced GVF calculation times to one-half or less without compromising contour accuracy.