Active Shape Model Segmentation with Optimal Features

DMCA

Active Shape Model Segmentation with Optimal Features (2002)

Cached

Download Links

Other Repositories/Bibliography

CiteULike
DBLP

by Bram van Ginneken , Alejandro F. Frangi , Ro F. Frangi , Joes J. Staal , Bart M. Ter Haar Romeny , Max A. Viergever

Venue:	IEEE Transactions on Medical Imaging
Citations:	70 - 6 self

BibTeX

@ARTICLE{Ginneken02activeshape,
    author = {Bram van Ginneken and Alejandro F. Frangi and Ro F. Frangi and Joes J. Staal and Bart M. Ter Haar Romeny and Max A. Viergever},
    title = {Active Shape Model Segmentation with Optimal Features},
    journal = {IEEE Transactions on Medical Imaging},
    year = {2002},
    volume = {21},
    pages = {924--933}
}

OpenURL

Abstract

An active shape model segmentation scheme is presented that is steered by optimal local features, contrary to normalized first order derivative profiles, as in the original formulation [Cootes and Taylor, 1995, 1999, and 2001]. A nonlinear kNN-classifier is used, instead of the linear Mahalanobis distance, to find optimal displacements for landmarks. For each of the landmarks that describe the shape, at each resolution level taken into account during the segmentation optimization procedure, a distinct set of optimal features is determined. The selection of features is automatic, using the training images and sequential feature forward and backward selection. The new approach is tested on synthetic data and in four medical segmentation tasks: segmenting the right and left lung fields in a database of 230 chest radiographs, and segmenting the cerebellum and corpus callosum in a database of 90 slices from MRI brain images. In all cases, the new method produces significantly better results in terms of an overlap error measure ( p < 0.001 using a paired T-test) than the original active shape model scheme.

Keyphrases

optimal feature active shape model segmentation new method paired t-test new approach active shape model segmentation scheme training image segmentation optimization procedure optimal local feature sequential feature forward lung field optimal displacement synthetic data resolution level overlap error measure distinct set first order derivative profile linear mahalanobis distance original active shape model scheme backward selection nonlinear knn-classifier original formulation cootes medical segmentation task corpus callosum mri brain image

DMCA