Expectation-Maximization with Image-Weighted Markov Random Fields to Handle Severe Pathology
This paper describes an automatic tissue segmentation algorithm for brain MRI of children with cerebral palsy (CP) who exhibit severe cortical malformations. Many of the currently popular brain segmentation techniques rely on registered atlas priors and so generalize poorly to severely injured data...
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference Paper |
| Published: |
2016
|
| Online Access: | http://hdl.handle.net/20.500.11937/31119 |
| _version_ | 1848753286482493440 |
|---|---|
| author | Pagnozzi, A. Dowson, N. Bradley, A. Boyd, Roslyn Bourgeat, P. Rose, S. |
| author_facet | Pagnozzi, A. Dowson, N. Bradley, A. Boyd, Roslyn Bourgeat, P. Rose, S. |
| author_sort | Pagnozzi, A. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | This paper describes an automatic tissue segmentation algorithm for brain MRI of children with cerebral palsy (CP) who exhibit severe cortical malformations. Many of the currently popular brain segmentation techniques rely on registered atlas priors and so generalize poorly to severely injured data sets, because of large discrepancies between the target brain and healthy (or injured) atlases. We propose a prior-less approach combined with a modification of the Expectation Maximization (EM)/Markov Random Field (MRF) segmentation by imposing a continuous weighting scheme to penalize intensity discrepancies between pairs of neighbors within each clique neighborhood, to provide robustness to the unique clinical problem of severe anatomical distortion. This approach was applied to gray matter segmentations in 20 3D T1-weighted MRIs, of which 17 were of CP patients exhibiting severe malformation. We compare our adaptive algorithm to the popular 'FreeSurfer', 'NiftySeg', 'FAST' and 'Atropos' segmentations, which collectively are state-of-The-Art surface deformation and EM approaches. The algorithm driven approach yielded improved segmentations (DSC 0.66 v 0.44 (FreeSurfer) v 0.60 (NiftySeg with 100% atlas prior relaxation) v 0.59 (FAST) v 0.64 (Atropos)) of the cerebral cortex relative to several ground-Truth manual segmentations, when compared to the existing approaches. |
| first_indexed | 2025-11-14T08:22:06Z |
| format | Conference Paper |
| id | curtin-20.500.11937-31119 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T08:22:06Z |
| publishDate | 2016 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-311192017-09-13T15:34:02Z Expectation-Maximization with Image-Weighted Markov Random Fields to Handle Severe Pathology Pagnozzi, A. Dowson, N. Bradley, A. Boyd, Roslyn Bourgeat, P. Rose, S. This paper describes an automatic tissue segmentation algorithm for brain MRI of children with cerebral palsy (CP) who exhibit severe cortical malformations. Many of the currently popular brain segmentation techniques rely on registered atlas priors and so generalize poorly to severely injured data sets, because of large discrepancies between the target brain and healthy (or injured) atlases. We propose a prior-less approach combined with a modification of the Expectation Maximization (EM)/Markov Random Field (MRF) segmentation by imposing a continuous weighting scheme to penalize intensity discrepancies between pairs of neighbors within each clique neighborhood, to provide robustness to the unique clinical problem of severe anatomical distortion. This approach was applied to gray matter segmentations in 20 3D T1-weighted MRIs, of which 17 were of CP patients exhibiting severe malformation. We compare our adaptive algorithm to the popular 'FreeSurfer', 'NiftySeg', 'FAST' and 'Atropos' segmentations, which collectively are state-of-The-Art surface deformation and EM approaches. The algorithm driven approach yielded improved segmentations (DSC 0.66 v 0.44 (FreeSurfer) v 0.60 (NiftySeg with 100% atlas prior relaxation) v 0.59 (FAST) v 0.64 (Atropos)) of the cerebral cortex relative to several ground-Truth manual segmentations, when compared to the existing approaches. 2016 Conference Paper http://hdl.handle.net/20.500.11937/31119 10.1109/DICTA.2015.7371257 restricted |
| spellingShingle | Pagnozzi, A. Dowson, N. Bradley, A. Boyd, Roslyn Bourgeat, P. Rose, S. Expectation-Maximization with Image-Weighted Markov Random Fields to Handle Severe Pathology |
| title | Expectation-Maximization with Image-Weighted Markov Random Fields to Handle Severe Pathology |
| title_full | Expectation-Maximization with Image-Weighted Markov Random Fields to Handle Severe Pathology |
| title_fullStr | Expectation-Maximization with Image-Weighted Markov Random Fields to Handle Severe Pathology |
| title_full_unstemmed | Expectation-Maximization with Image-Weighted Markov Random Fields to Handle Severe Pathology |
| title_short | Expectation-Maximization with Image-Weighted Markov Random Fields to Handle Severe Pathology |
| title_sort | expectation-maximization with image-weighted markov random fields to handle severe pathology |
| url | http://hdl.handle.net/20.500.11937/31119 |