Journal article
White matter lesion segmentation based on feature joint occurrence probability and χ2 random field theory from magnetic resonance (MR) images
Pattern Recognition Letters, Vol.31(9), pp.781-790
2010
Abstract
Lesions of the brain's white matter are common findings in MR examinations of elderly subjects. A fully automatic method for segmenting white matter lesions is proposed here. The joint probability of multi-modality MR image intensities is used as a feature to segment lesions, because lesion intensities usually are outliers of the normal tissue intensities and the lesions' joint intensity probability appears much smaller than those of normal brain tissues. The χ2 random field theory is used to determine the significance of a detected lesion and provides a strict statistical analysis to exclude small-sized false-positive lesions. Experimental results show that the automatic segmentation of lesions is in high agreement with manual segmentation, and the χ2 random-field-based statistical analysis greatly improves lesion segmentation results.
Details
- Title
- White matter lesion segmentation based on feature joint occurrence probability and χ2 random field theory from magnetic resonance (MR) images
- Authors
- F Yang (Author) - University of California, IrvineZack Y Shan (Author) - St. Jude Children's Research HospitalF Kruggel (Author) - University of California, Irvine
- Publication details
- Pattern Recognition Letters, Vol.31(9), pp.781-790
- Publisher
- Elsevier BV, North-Holland
- Date published
- 2010
- DOI
- 10.1016/j.patrec.2010.01.025
- ISSN
- 0167-8655; 1872-7344; 0167-8655
- Organisation Unit
- University of the Sunshine Coast, Queensland; Thompson Institute
- Language
- English
- Record Identifier
- 99513902402621
- Output Type
- Journal article
Metrics
83 Record Views
InCites Highlights
These are selected metrics from InCites Benchmarking & Analytics tool, related to this output
- Collaboration types
- Domestic collaboration
- Web Of Science research areas
- Computer Science, Artificial Intelligence
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
Source: InCites