0.25
0.5
0.75
1.25
1.5
1.75
2
Supervised Segmentation of Fiber Tracts
Published on Oct 17, 20112789 Views
In this work we study the problem of supervised tract segmentation from tractography data, a vectorial representation of the brain connectivity extracted from diffusion magnetic resonance images. We r
Related categories
Chapter list
Supervised Segmentation of Fiber Tracts00:00
Motivation: Brain Connectivity00:22
Outline01:53
Outline: Fiber Tract Segmentation02:15
Fiber Tract Segmentation: Axons02:16
Fiber Tract Segmentation: Bundles02:33
Fiber Tract Segmentation: Streamlines02:57
Fiber Tract Segmentation: Tractography03:49
Fiber Tract Segmentation: Human Expert04:14
Algorithmic Fiber Tract Segmentation04:59
Supervised Segmentation of Fiber Tracts05:15
Previous Work05:41
Outline: Proposed Solution06:48
Proposed Solution06:50
Definitions and Notation07:39
Issues08:38
Distances between streamlines (from the literature)09:20
k-Nearest Neighbor10:14
Kernel Methods: SVC, GPC, perceptron, etc.10:23
. . . and Indefinite Kernels11:17
(Dis)similarity representation [Pekalska et al., 2002]11:44
(Dis)similarity representation CONT.12:50
Proposed Method13:22
Outline: Experiments13:44
Dataset: enhanced PBCC 200913:45
Evaluation Criterion14:33
Results: Same Subject, Proposed Solution15:11
Results Cross-Subject. Arcuate Fasciculus16:23
Results Cross-Subject. Corticospinal tract17:54
Results Cross-Subject. Forceps Major18:11
Results: Inferior Occipito-Frontal Fasciculus (IOFF)18:14
Results Cross-Subject. Cingulum18:20
Results Cross-Subject. Fornix18:21
Results Cross-Subject. Subcallosal18:22
Results Cross-Subject. Uncinate18:22
Outline: Conclusions & Future Work19:03
Conclusions19:04
Future work19:46
Thank You!21:15