TubeTK/Events/2011.07.06: Difference between revisions
Ilknur.kabul (talk | contribs) No edit summary |
Ilknur.kabul (talk | contribs) No edit summary |
||
| Line 4: | Line 4: | ||
'''Problem:''' | '''Problem:''' | ||
Tissue classification is available at the chronic time point.Because of diadema, tracking tissue and classifying white and gray matter at the acquired time point is hard. In acute phase, we need to hand segment lesion boundaries. How to label a voxel based on 5 modalities is a problem. | Tissue classification is available at the chronic time point.Because of diadema, tracking tissue and classifying white and gray matter at the acquired time point is hard. In acute phase, we need to hand segment lesion boundaries. How to label a voxel based on 5 modalities is a problem. | ||
Whether a diadema is hemorrhagic or non-hemorrhagic cannot be generalized. Micro bleeds happens and they are visible in SWI (not visible in the others). | Whether a diadema is hemorrhagic or non-hemorrhagic cannot be generalized. Micro bleeds happens and they are visible in SWI (not visible in the others). | ||
'''Possible approach:''' | '''Possible approach:''' | ||
With the classification in the chronic image, acute image and Gabe&Marc`s algorithm, can this be done (segmentation) in the acute image? | With the classification in the chronic image, acute image and Gabe&Marc`s algorithm, can this be done (segmentation) in the acute image? | ||
| Line 15: | Line 17: | ||
# Data: At least 4-5 channels (T1, T2, SWI, DTI, GRE) are available. They are good for differenting diademas. | # Data: At least 4-5 channels (T1, T2, SWI, DTI, GRE) are available. They are good for differenting diademas. | ||
# Lesion classes: How to distinguish between lesion classes? Andrei has a submitted paper about that. | # Lesion classes: How to distinguish between lesion classes? Andrei has a submitted paper about that. | ||
TODO: | |||
# Andrei will give us the manual segmentation of the subject | |||
# We will do segmentation for diadema (hemorrhage or not). | |||
== Deformation due to swelling == | |||
'''Problem:''' | |||
How brain changes its shape due to swelling? Inflammation of brain? | |||
Can the approach in Gabe and Marc`s paper be applied to solve that problem? | |||
'''Possible solution:''' | |||
There is a filter called, JacobianDeformationField, in ITK. The challenge here is how do we interpolate in brain region which is consistently swelling or shrinking. Localization of the swelling is important. Swelling will be gone in the chronic image. | |||
For example: When the primary injury is small and there is a lot of swelling. | |||
Questions: | |||
# How brain swells? How brain inflamms as a result of injury? How gray&white matter gets effected by that? These are important. | |||
# How swelling benefits the injury parts? (Ventriculoscopy pressure, inflammation) | |||
# What are the measures that tell us there is swelling? If gray&white matter segmentation and labelling diadema gives information about that, we can do that. | |||
Vocabulary: | Vocabulary: | ||
Ventriculoscopy pressure: [[http://www.atlantabrainandspine.com/subject.php?pn=ventriculoscopy]] | |||
Revision as of 13:29, 7 July 2011
UCLA Meeting Notes:
Segmentation in the chronic image
Problem:
Tissue classification is available at the chronic time point.Because of diadema, tracking tissue and classifying white and gray matter at the acquired time point is hard. In acute phase, we need to hand segment lesion boundaries. How to label a voxel based on 5 modalities is a problem. Whether a diadema is hemorrhagic or non-hemorrhagic cannot be generalized. Micro bleeds happens and they are visible in SWI (not visible in the others).
Possible approach:
With the classification in the chronic image, acute image and Gabe&Marc`s algorithm, can this be done (segmentation) in the acute image?
Kitware can do multivariant classification. PDFSegmenter is available in TubeTK. This method is semiautomatic, multivariant, and multiclass (2 types of diadema & tumor). In this approach, you should indicate couple of points in diadema and some other points. Andrei told that Marcel has something similar to that one. Both can be tried and the results can be compared.
Input:
- Data: At least 4-5 channels (T1, T2, SWI, DTI, GRE) are available. They are good for differenting diademas.
- Lesion classes: How to distinguish between lesion classes? Andrei has a submitted paper about that.
TODO:
- Andrei will give us the manual segmentation of the subject
- We will do segmentation for diadema (hemorrhage or not).
Deformation due to swelling
Problem:
How brain changes its shape due to swelling? Inflammation of brain? Can the approach in Gabe and Marc`s paper be applied to solve that problem?
Possible solution:
There is a filter called, JacobianDeformationField, in ITK. The challenge here is how do we interpolate in brain region which is consistently swelling or shrinking. Localization of the swelling is important. Swelling will be gone in the chronic image. For example: When the primary injury is small and there is a lot of swelling.
Questions:
- How brain swells? How brain inflamms as a result of injury? How gray&white matter gets effected by that? These are important.
- How swelling benefits the injury parts? (Ventriculoscopy pressure, inflammation)
- What are the measures that tell us there is swelling? If gray&white matter segmentation and labelling diadema gives information about that, we can do that.
Vocabulary: Ventriculoscopy pressure: [[1]]
