Title :
A feature-based approach for refinement of Model-based segmentation of low contrast structures
Author :
Qazi, Arish A. ; Kim, John ; Jaffray, David A. ; Pekar, Vladimir
Author_Institution :
Princess Margaret Hosp., Toronto, ON, Canada
fDate :
Aug. 30 2011-Sept. 3 2011
Abstract :
Accuracy and robustness are fundamental requirements of any automated method used for segmentation of medical images. Model-based segmentation (MBS) is a well established technique, where uncertainties in image content can be to a certain extent compensated by the use of prior shape information. This approach is, however, often problematic in cases where image information does not allow for generating a strong feature response, one example being soft tissue organs in CT data, which typically appear in low contrast. In this paper, we enhance our recently proposed framework for voxel classification-based refinement of MBS using a level-set segmentation technique with shape priors. We also introduce a novel feature weighting methodology that improves the performance of the classifier, demonstrating results superior to the previous feature selection method. Results of fully automated segmentation of low contrast organs in head and neck CT are presented. Compared to our previous approach, we have achieved an increase of up to 22% in segmentation accuracy.
Keywords :
computerised tomography; feature extraction; image classification; image segmentation; medical image processing; CT data; feature weighting; feature-based approach; level-set segmentation technique; low contrast structures; medical image segmentation; model-based segmentation; soft tissue organs; voxel classification; Accuracy; Head; High definition video; Image segmentation; Neck; Probabilistic logic; Shape; Model-based segmentation; classification; feature weighting; level-sets; radiation therapy planning; Algorithms; Area Under Curve; Humans; Image Enhancement; Models, Theoretical; Tomography, X-Ray Computed;
Conference_Titel :
Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE
Conference_Location :
Boston, MA
Print_ISBN :
978-1-4244-4121-1
Electronic_ISBN :
1557-170X
DOI :
10.1109/IEMBS.2011.6091967