Multiple Sclerosis Detection in Multispectral Magnetic Resonance Images with Principal Components Analysis.
logo

Please use this identifier to cite or link to this publication: http://hdl.handle.net/10380/1441
This paper presents a local feature vector based method for automated Multiple Sclerosis (MS) lesion segmentation of multi spectral MRI data. Twenty datasets from MS patients with FLAIR, T1,T2, MD and FA data with expert annotations are available as training set from the MICCAI 2008 challenge on MS, and 24 test datasets. Our local feature vector method contains neighbourhood voxel intensities, histogram and MS probability atlas information. Principal Component Analysis(PCA) cite{PCA} with log-likelihood ratio is used to classify each voxel. MRI suffers from intensity inhomogenities. We try to correct this ''bias field'' with 3 methods: a genetic algorithm, edge preserving filtering and atlas based correction. A large observer variability exist between expert classifications, but the similarity scores between model and expert classifications are often lower. Our model gives the best classification results with raw data, because bias correction gives artifacts at the edges and flatten large MS lesions.

Reviews
plus PCA based Local feature vector classification for MS lesion segmentation by Martin Styner on 07-28-2008 for revision #1
starstarstarstarstar expertise: 5 sensitivity: 4.5
plus Review by Simon Warfield on 07-25-2008 for revision #1
starstarstarstarstar expertise: 5 sensitivity: 4.5
Add a new review
Quick Comments


Resources
backyellow
Download All

Statistics more
backyellow
Global rating: starstarstarstarstar
Review rating: starstarstarstarstar [review]
Paper Quality: plus minus

Information more
backyellow
Categories: Anisotropic blurring filters, Atlas-based segmentation, Blurring filters, Classification, Component Analysis and Discriminants, Data, Deformable registration, Density Estimation, Density Functions, Distance maps, Edge Detection, Error Estimation, Feature extraction, Filtering, Generic Programming, Images, IO, Linear Algebra, Mathematics, Missing and Noisy Features, Multi-modality registration, Optimization, Parameter Techniques, Probability, Programming, Registration, Registration metrics, Registration optimizers, Resampling, Segmentation, Spatial Objects, Thresholding, Transforms
Keywords: Multiple Sclerosis, Lesions, PCA, MR, Bias Field, Non-rigid Registration, FLAIR, Feature Vector
Export citation:

Share
backyellow
Share

Linked Publications more
backyellow
Reader/Writer for Analyze Object Maps for ITK Reader/Writer for Analyze Object Maps for ITK
by Hawley J., Johnson H.
3D Segmentation in the Clinic: A Grand  Challenge II: MS lesion segmentation 3D Segmentation in the Clinic: A Grand Challenge II: MS lesion segmentation
by Styner M., Lee J., Chin B., Chin M.S., Commowick O., Tran H., Markovic-Plese S., Jewells V., Warfield S.

View license
Loading license...

Send a message to the author
main_flat
Powered by Midas