DTU Medical Visionday May 27, 2009 Generative models for automated brain MRI segmentation Koen Van Leemput Athinoula A. Martinos Center for Biomedical Imaging Department of Radiology, MGH Harvard Medical School, USA Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology, USA
50
Embed
DTU Medical Visionday May 27, 2009 Generative models for automated brain MRI segmentation Koen Van Leemput Athinoula A. Martinos Center for Biomedical.
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
DTU Medical Visionday May 27, 2009
Generative models for automated brain MRI segmentation
Koen Van Leemput
Athinoula A. Martinos Center for Biomedical Imaging
Department of Radiology, MGH
Harvard Medical School, USA
Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology, USA
MRI of the brain
Magnetic resonance imaging:– Harmless– Three dimensional (3-D)– High soft tissue contrast– High spatial resolution– Extremely versatile– Possibly multi-spectral
Ideal for studying the living human brain
“voxel”
Koen Van Leemput DTU Medical Visionday May 27, 2009
Segmentation of brain MRI
– Delineating structures of interest in the images
Koen Van Leemput DTU Medical Visionday May 27, 2009
Whole-brain segmentation
– Tetrahedral mesh-based atlas– The labeling model parameters are the location of the
mesh nodes– The prior is the topology-preserving MRF model
(penalizes deformations)
“labeling model”
“imaging model”
Koen Van Leemput DTU Medical Visionday May 27, 2009
MRI image Label image
Whole-brain segmentation
“labeling model”
“imaging model”
+
Gaussian mixture model polynomial bias field model
Koen Van Leemput DTU Medical Visionday May 27, 2009
MRI image Label image
– Model parameter estimation:
– Fully automated segmentation procedure• No need for pre-processing (skull stripping, bias field corr., …)• Automatically adapts to different scanners and acquisition sequences!• Fast!
Whole-brain segmentation
Improve the imaging model parameters (Generalized Expectation-Maximization;
closed-form expressions)
Improve the atlas warp (registration; gradient in analytical form)
Koen Van Leemput DTU Medical Visionday May 27, 2009
Examples (validation under way)
Koen Van Leemput DTU Medical Visionday May 27, 2009
Examples (validation under way)
Koen Van Leemput DTU Medical Visionday May 27, 2009
Examples (validation under way)
Koen Van Leemput DTU Medical Visionday May 27, 2009
Examples (validation under way)
Koen Van Leemput DTU Medical Visionday May 27, 2009
Examples (validation under way)
Koen Van Leemput DTU Medical Visionday May 27, 2009
Examples (validation under way)
Koen Van Leemput DTU Medical Visionday May 27, 2009
Thanks!
Koen Van Leemput DTU Medical Visionday May 27, 2009