Information-Theoretic Algorithms for Diffusion Tensor Imaging

author:Baba C. Vemuri, University of Florida
published: Dec. 5, 2008, recorded: November 2008, views: 364

You might be experiencing some problems with Your Video player.

Slides

Slides
0:00	Information theoretic methods for diffusion-weighted MRI analysis
0:54	Outline
1:59	Outline - Introduction
2:01	Motivation
2:57	Diagnosis of Injury and Disease
4:48	Outline
4:50	Diffusion Process (1)
5:11	Diffusion Process (2)
5:28	Diffusion in Tissue
5:56	Diffusion MRI
7:41	Diffusion MRI (Contd.)
7:43	Diffusion-Weighted Imaging
8:00	Diffusion Tensor Imaging
9:05	DT-MRI Contd.
9:22	DTI Examples of Ellipsoid Visualization
9:54	Fiber Tract Visualizations
9:56	Fiber Tract Mapping
10:25	Fiber Tract Mapping from Restored DTI
10:40	Fiber Tract Mapping (Contd.)
10:56	DTI Segmentation
13:27	DTI Segmentation Using an Information Theoretic Tensor Dissimilarity Measure
14:27	Definition of a New DT "Distance"
14:52	Definition of a New DT "Distance" (Cont’)
15:33	Affine Invariant Property
16:06	Comparison of tensor field segmentations.
16:43	Tensor Field Mean Value
17:46	Tensor Field Mean Value (Cont’)
17:54	Evolution of a Curve and its Level-set Formulation (1)
18:22	Evolution of a Curve and its Level-set Formulation (2)
19:18	A Bimodal Tensor Field Segmentation Model
19:54	Curve Evolution Equation and Levelset Formulation
20:05	The Mumford-shah functional for Piecewise Smooth DTI Segmentation.
20:33	Discontinuity Preserving Smoothing
20:56	Curve Evolution Equation
21:07	Level Set Formulation
21:14	Regions of Different Orientations
21:31	Regions of Different Orientations (With Additive Noise)
21:39	Regions of Different Scales
22:02	Regions of Different Scales (With Additive Noises)
22:11	DTI of a Normal Rat Spinal Cord
22:50	2D DTI Segmentation of a Normal Rat Spinal Cord
23:01	DTI of a Normal Rat Brain
23:04	2D DTI Segmentation of the Corpus Callosum
23:21	2D DTI Segmentation of the Corpus Callosum using the Piecewise Smooth Model
23:31	3D DTI Segmentation of a Normal Spinal Cord
23:34	3D DTI Segmentation of the Corpus Callosum
23:35	3D DTI Segmentation of the Corpus Callosum (Cont’)
23:37	3D Segmented CC w/Mapped LIC
24:02	What is the Problem with DTI?
25:02	State of the Art (1)
25:08	State of the Art (2)
25:09	State of the Art (3)
25:11	State of the Art (4)
26:09	State of the Art (5)
27:25	Fundamental relationship
27:33	The Diffusion tensor model
27:37	Stejskal-Tanner equation and ADC profiles
27:43	Approaches using finite mixture model (1)
28:48	Approaches using finite mixture model (2)
28:52	Proposed work: a novel statistical model (1)
29:10	Proposed work: a novel statistical model (2)
29:18	Approaches using finite mixture model (2)
29:34	Proposed work: a novel statistical model (2)
29:51	Proposed work: Highlights (1)
29:53	Proposed work: Highlights (2)
29:53	Proposed work: Highlights (3)
30:26	Proposed work: Applications (1)
30:28	Proposed work: Applications (2)
30:28	Our formulation
32:06	The Laplace transform on Pn
32:08	The Statistical model
32:21	The Wishart distributed tensor model for DW-MRI
32:58	Mono-exponential model as a limiting case
33:10	Multi-fiber reconstruction (1)
33:44	Multi-fiber reconstruction (2)
33:46	Linear system again!
34:38	Probability surfaces from simulated data
35:14	Resistance to noise (2-fibers, o = 0.08)
35:25	Resistance to noise (3-fibers, o = 0.04)
35:30	Comparison with Q-ball ODF
36:00	Real data: excised rat optic chiasm (1)
36:02	Real data: excised rat optic chiasm (2)
36:30	Real data: excised rat brain
36:32	S0 maps of control rat brain data
36:43	Probability surfaces from control rat brain data
37:09	S0 map of epileptic rat brain data
37:15	Probability surfaces from epileptic rat brain data
37:29	Summary of Main Contributions
38:34	Summary (Contd.)
38:49	Acknowledgements

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.

Lecture popularity: You need to login to cast your vote.

Description

Concepts from Information Theory have been used quite widely in Image Processing, Computer Vision and Medical Image Analysis for several decades now. Most widely used concepts are that of KL-divergence, minimum description length (MDL), etc. These concepts have been popularly employed for image registration, segmentation, classification etc. In this chapter we review several methods, mostly developed by our group at the Center for Vision, Graphics & Medical Imaging in the University of Florida, that glean concepts from Information Theory and apply them to achieve analysis of Diffusion-Weighted Magnetic Resonance (DW-MRI) data. This relatively new MRI modality allows one to non-invasively infer axonal connectivity patterns in the central nervous system. The focus of this chapter is to review automated image analysis techniques that allow us to automatically segment the region of interest in the DWMRI image wherein one might want to track the axonal pathways and also methods to reconstruct complex local tissue geometries containing axonal fiber crossings. Implementation results illustrating the algorithm application to real DW-MRI data sets are depicted to demonstrate the effectiveness of the methods reviewed.