Phase-based user-steered image segmentation

L. O'Donnell, C. F. Westin, W. E. L. Grimson, J. Ruiz-Alzola, M. E. Shenton, R. Kikinis
Proceedings of the 4th International Conference on Medical Image Computing and Computer Assisted Intervention MICCAI
Pages 1022-1030
2001

Download full paper

Abstract

This paper presents a user-steered segmentation algorithm based on the livewire paradigm. Livewire is an image-feature driven method that finds the optimal path between user-selected image locations, thus reducing the need to manually define the complete boundary. We introduce an image feature based on local phase, which describes local edge symmetry independent of absolute gray value. Because phase is amplitude invariant, the measurements are robust with respect to smooth variations, such as bias field inhomogeneities present in all MR images. In order to enable validation of our segmentation method, we have created a system that continuously records user interaction and automatically generates a database containing the number of user interactions, such as mouse events, and time stamps from various editing modules. We have conducted validation trials of the system and obtained expert opinions regarding its functionality.

Reference

O'Donnell L, Westin CF, Grimson WEL, Ruiz-Alzola J, Shenton ME, Kikinis R. Phase-based user-steered image segmentation. In Proceedings of the 4th International Conference on Medical Image Computing and Computer Assisted Intervention MICCAI. Springer-Verlag GmbH, 2001;1022-1030.

Grants

NIH RO1 MH50747, NIH/NIMH 2K02 MH01110, VA Merit Award(MES) 2000-2008, CIMIT, NIH P41 RR13218, NationalScienceFellowship, NIH R01 RR11747, 1FD97-0881-C02-0

Research area

segmentation
© 2013 Psychiatry Neuroimaging Laboratory | Last updated 04.15.2013