An Overview of Medical Image Segmentation Flashcards
What are many different types of objectives for segmentation?
- Identify grey matter, white matter and CSF
- Identify tumours, strokes etc
- Identify different brain structures, hippocampus etc
What are the many different types of iamges?
Segmentation quality depends on what is visible in the images
What is region growing?
Approach available within many software tools
Define an approximate region within a structure
Scribbles, points, etc
Maybe define some regions outside the structure
What does algorithm try to find?
A suitable boundary
Lots of different strategies involved
What is classification?
Rather than classify individuals (e.g. patient vs. control), the aim is to classify voxels (e.g. hippocampus vs. not hippocampus).
What are the information that can be combined probabilistically for classificatiion?
Voxel intensity
Position within the image
Classes of neighbouring voxels
Texture
What is the probability for classifitis (Fatal disease afflicting one in every thousand people)
Out of 1000 people, 999 will not have classifitis.
Of these, 5% will have a positive result – about 50.
One person will have classifitis, with a 99% chance of having a positive result.
About one positive result from someone with classifitis.
About 50 positive results from people without classifitis.
A positive result means about a 2% chance of having classifitis.
What does the Bayes rule say?
P(C+ | T+) = P(T+ | C+) P(C+) / P(T+)
= 0.99×0.001 / (0.99×0.001 + 0.05×0.999)
= 0.0194 2%
What is tissue classification?
Whereby voxels are assigned to a tissue class according to their intensities the intensity distribution ofeach tissue class needs to be characterised, often from voxelschosen to represent each class.
What is another approach?
involves some kind of registration, where atemplate brain is warped to match the brain volume to besegmented (Collins et al., 1995).
Why is automated and reliable intensity-based tissue classification complicated?
Spectral overlap of MR intensities if different tissue classes and by the presence of a spatially smoothly varying intensity inhomogeneity or bias field
What is iterative expectation-maximisation (EM) procedures?
Interleaved tissue classification with estimation of tissue-class-specific intensity models and bias field correction
What does initialisation of the iterative process use?
Digital brain atlas with a priori probability maps for the different tissue classes
Avoids all manual intervention
What is the Markov random field (MRF) designed to facilitate?
Discrimination between brain and non brain tissues, while preserving the detailed interfaces between the various tissue classes within the brain
What does the algorithm iteratively interleave?
- Voxel classification
- Intensity distribution parameter estimation
- MR bias field correction
- MRF parameter estimation