Journal article
A hybrid tissue segmentation approach for brain MR images
Medical & biological engineering & computing, Vol.44(3), pp.242-249
03/2006
DOI: 10.1007/s11517-005-0021-1
PMID: 16937165
Abstract
A novel hybrid algorithm for the tissue segmentation of brain magnetic resonance images is proposed. The core of the algorithm is a probabilistic neural network (PNN) in which weighting factors are added to the summation layer, such that partial volume effects can be taken into account in the modeling process. The mean vectors for the probability density function estimation and the corresponding weighting factors are generated by a hierarchical scheme involving a self-organizing map neural network and an expectation maximization algorithm. Unlike conventional PNN, this approach circumvents the need for training sets. Tissue segmentation results from various algorithms are compared and the effectiveness and robustness of the proposed approach are demonstrated.
Details
- Title: Subtitle
- A hybrid tissue segmentation approach for brain MR images
- Creators
- Tao Song - Radiology Department, Radiology Imaging Lab University of California at San Diego 3510 Dunhill Street San Diego CA 92121 USACharles Gasparovic - The MIND Institute Albuquerque NM USANancy Andreasen - The MIND Institute Albuquerque NM USAJeremy Bockholt - The MIND Institute Albuquerque NM USAMo Jamshidi - Electrical and Computer Engineering Department University of New Mexico Albuquerque NM USARoland Lee - Radiology Department, Radiology Imaging Lab University of California at San Diego 3510 Dunhill Street San Diego CA 92121 USAMingxiong Huang - Radiology Department, Radiology Imaging Lab University of California at San Diego 3510 Dunhill Street San Diego CA 92121 USA
- Resource Type
- Journal article
- Publication Details
- Medical & biological engineering & computing, Vol.44(3), pp.242-249
- Publisher
- Springer-Verlag; Berlin/Heidelberg
- DOI
- 10.1007/s11517-005-0021-1
- PMID
- 16937165
- ISSN
- 0140-0118
- eISSN
- 1741-0444
- Language
- English
- Date published
- 03/2006
- Academic Unit
- Psychiatry; Iowa Neuroscience Institute
- Record Identifier
- 9984003919902771
Metrics
33 Record Views