Conference proceeding
Multi-structure segmentation of multi-modal brain images using artificial neural networks
Proceedings of SPIE, Vol.7623(1), pp.76234B-76234B-12
Medical Imaging 2010: Image Processing
03/05/2010
DOI: 10.1117/12.844613
Abstract
A method for simultaneous segmentation of multiple anatomical brain structures from multi-modal MR images
has been developed. An artificial neural network (ANN) was trained from a set of feature vectors created
by a combination of high-resolution registration methods, atlas based spatial probability distributions, and a
training set of 16 expert traced data sets. A set of feature vectors were adapted to increase performance of ANN
segmentation; 1) a modified spatial location for structural symmetry of human brain, 2) neighbors along the
priors descent for directional consistency, and 3) candidate vectors based on the priors for the segmentation of
multiple structures. The trained neural network was then applied to 8 data sets, and the results were compared
with expertly traced structures for validation purposes. Comparing several reliability metrics, including a relative
overlap, similarity index, and intraclass correlation of the ANN generated segmentations to a manual trace are
similar or higher to those measures previously developed methods. The ANN provides a level of consistency
between subjects and time efficiency comparing human labor that allows it to be used for very large studies.
Details
- Title: Subtitle
- Multi-structure segmentation of multi-modal brain images using artificial neural networks
- Creators
- Eun Young Kim - The Univ. of Iowa (United States)Hans Johnson - The Univ. of Iowa (United States)
- Resource Type
- Conference proceeding
- Publication Details
- Proceedings of SPIE, Vol.7623(1), pp.76234B-76234B-12
- Conference
- Medical Imaging 2010: Image Processing
- DOI
- 10.1117/12.844613
- ISSN
- 0277-786X
- Language
- English
- Date published
- 03/05/2010
- Academic Unit
- The Iowa Initiative for Artificial Intelligence; Psychiatry; The Iowa Institute for Biomedical Imaging; Electrical and Computer Engineering; Roy J. Carver Department of Biomedical Engineering; Iowa Informatics Initiative
- Record Identifier
- 9984221730702771
Metrics
7 Record Views