Conference proceeding
Tissue classification of large-scale multi-site MR data using fuzzy k-nearest neighbor method
Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Vol.9784, pp.97841V-97841V-7
Progress in Biomedical Optics and Imaging - Proceedings of SPIE
03/21/2016
DOI: 10.1117/12.2216625
Abstract
This paper describes enhancements to automate classification of brain tissues for multi-site degenerative magnetic resonance imaging (MRI) data analysis. Processing of large collections of MR images is a key research technique to advance our understanding of the human brain. Previous studies have developed a robust multi-modal tool for automated tissue classification of large-scale data based on expectation maximization (EM) method initialized by group-wise prior probability distributions. This work aims to augment the EM-based classification using a non-parametric fuzzy k-Nearest Neighbor (k-NN) classifier that can model the unique anatomical states of each subject in the study of degenerative diseases. The presented method is applicable to multi-center heterogeneous data analysis and is quantitatively validated on a set of 18 synthetic multi-modal MR datasets having six different levels of noise and three degrees of bias-field provided with known ground truth. Dice index and average Hausdorff distance are used to compare the accuracy and robustness of the proposed method to a state-of-the-art classification method implemented based on EM algorithm. Both evaluation measurements show that presented enhancements produce superior results as compared to the EM only classification.
Details
- Title: Subtitle
- Tissue classification of large-scale multi-site MR data using fuzzy k-nearest neighbor method
- Creators
- Ali Ghayoor - University of IowaJane S Paulsen - University of Iowa Hospitals and ClinicsRegina E. Y Kim - University of Iowa Hospitals and ClinicsHans J Johnson - University of Iowa
- Contributors
- Martin A Styner (Editor) - The Univ. of North Carolina at Chapel Hill (United States)Elsa D Angelini (Editor) - Columbia Univ. (United States)
- Resource Type
- Conference proceeding
- Publication Details
- Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Vol.9784, pp.97841V-97841V-7
- Conference
- Progress in Biomedical Optics and Imaging - Proceedings of SPIE
- Publisher
- SPIE
- DOI
- 10.1117/12.2216625
- ISSN
- 1605-7422
- Language
- English
- Date published
- 03/21/2016
- Academic Unit
- Psychological and Brain Sciences; Psychiatry; Electrical and Computer Engineering; Roy J. Carver Department of Biomedical Engineering
- Record Identifier
- 9984185364602771
Metrics
3 Record Views