Surgical Planning Laboratory - Brigham & Women's Hospital - Boston, Massachusetts USA - a teaching affiliate of Harvard Medical School

Surgical Planning Laboratory

The Publication Database hosted by SPL

All Publications | Upload | Advanced Search | Gallery View | Download Statistics | Help | Import | Log in

Efficient Descriptor-Based Segmentation of Parotid Glands with Non-Local Means

Computer Science and Artificial Intelligence Laboratory, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA.
Publication Date:
IEEE Trans Biomed Eng
Volume Number:
Issue Number:
IEEE Trans Biomed Eng. 2017 Jul; 64(7): 1492–1502.
PubMed ID:
Appears in Collections:
P41 EB015902/EB/NIBIB NIH HHS/United States
P41 RR013218/RR/NCRR NIH HHS/United States
U54 EB005149/EB/NIBIB NIH HHS/United States
Generated Citation:
Wachinger C., Brennan M., Sharp G., Golland P. Efficient Descriptor-Based Segmentation of Parotid Glands with Non-Local Means. IEEE Trans Biomed Eng. 2017 Jul; 64(7): 1492–1502. PMID: 28113224. PMCID: PMC5469701.
Downloaded: 402 times. [view map]
Paper: Download, View online
Export citation:
Google Scholar: link

OBJECTIVE: We introduce descriptor-based segmentation that extends existing patch-based methods by combining intensities, features and location information. Since it is unclear which image features are best suited for patch selection, we perform a broad empirical study on a multitude of different features. We extend non-local means segmentation by including image features and location information. We search larger windows with an efficient nearest neighbor search based on kd-trees. We compare a large number of image features. RESULTS: The best results were obtained for entropy image features, which have not yet been used for patch-based segmentation.We further show that searching larger image regions with an approximate nearest neighbor search and location information yields a significant improvement over the bounded nearest neighbor search traditionally employed in patch-based segmentation methods. CONCLUSION: Features and location information significantly increase the segmentation accuracy. The best features highlight boundaries in the image. SIGNIFICANCE: Our detailed analysis of several aspects of non-local means based segmentation yields new insights about patch and neighborhood sizes together with the inclusion of location information. The presented approach advances the state-of-the-art in the segmentation of parotid glands for radiation therapy planning.