STREM: a robust multidimensional parametric method to segment MS lesions in MRI.: STREM: A Robust Multidimensional Parametric Method to Segment MS Lesions in MRI
- Resource Type
- Authors
- Gilles Edan; Pierre Hellier; L. S. Aït-Ali; Christian Barillot; Sylvain Prima; B. Carsin
- Source
- Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Medical Image Computing and Computer-Assisted Intervention-MICCAI 2005: 8th International Conference, Palm Springs, CA, USA, October 26-29, 2005, Proceedings, Part I
MICCAI 2005
MICCAI 2005, Oct 2005, Palm Springs, United States. pp.409-16, ⟨10.1007/11566465_51⟩
Lecture Notes in Computer Science ISBN: 9783540293279
MICCAI
- Subject
- Multiple Sclerosis
MESH: Algorithms
MESH: Imaging, Three-Dimensional
Sensitivity and Specificity
030218 nuclear medicine & medical imaging
Pattern Recognition, Automated
MESH: Magnetic Resonance Imaging
03 medical and health sciences
MESH: Brain
0302 clinical medicine
Imaging, Three-Dimensional
Artificial Intelligence
Image Interpretation, Computer-Assisted
medicine
Humans
MESH: Artificial Intelligence
MESH: Pattern Recognition, Automated
Segmentation
Parametric statistics
Mahalanobis distance
Signal processing
MESH: Humans
medicine.diagnostic_test
MESH: Sensi
business.industry
Brain
Reproducibility of Results
Pattern recognition
Magnetic resonance imaging
Signal Processing, Computer-Assisted
MESH: Multiple Sclerosis
Mixture model
Image Enhancement
Magnetic Resonance Imaging
MESH: Reproducibility of Results
Pattern recognition (psychology)
Outlier
[SDV.IB]Life Sciences [q-bio]/Bioengineering
Artificial intelligence
MESH: Image Enhancement
business
MESH: Image Interpretation, Computer-Assisted
030217 neurology & neurosurgery
Algorithms
- Language
- English
International audience; We propose to segment Multiple Sclerosis (MS) lesions overtime in multidimensional Magnetic Resonance (MR) sequences. We use a robust algorithm that allows the segmentation of the abnormalities using the whole time series simultaneously and we propose an original rejection scheme for outliers. We validate our method using the BrainWeb simulator. To conclude, promising preliminary results on longitudinal multi-sequences of clinical data are shown.