Results 1 -
5 of
5
3d segmentation of rodent brain structures using hierarchical shape priors and deformable models
- In International Conference on Medical Image Computing and Computer Assisted Intervention, volume 6893 of LNCS
, 2011
"... ABSTRACT Object boundary extraction is an important task in brain image analysis. Acquiring detailed 3D representations of the brain structures could improve the detection rate of diseases at earlier stages. Deformable model based segmentation methods have been widely used with considerable success ..."
Abstract
-
Cited by 7 (5 self)
- Add to MetaCart
(Show Context)
ABSTRACT Object boundary extraction is an important task in brain image analysis. Acquiring detailed 3D representations of the brain structures could improve the detection rate of diseases at earlier stages. Deformable model based segmentation methods have been widely used with considerable success. Recently, 3D Active Volume Model (AVM) was proposed, which incorporates both gradient and region information for robustness. However, the segmentation performance of this model depends on the position, size and shape of the initialization, especially for data with complex texture. Furthermore, there is no shape prior information integrated. In this paper, we present an approach combining AVM and Active Shape Model (ASM). Our method uses shape information from training data to constrain the deformation of AVM. Experiments have been made on the segmentation of complex structures of the rodent brain from MR images, and the proposed method performed better than the original AVM.
SEGMENTATION OF SUBCORTICAL STRUCTURES IN BRAIN MRI USING GRAPH-CUTS AND SUBJECT-SPECIFIC A-PRIORI INFORMATION
"... We propose a general framework for segmentation of subcor-tical structures in magnetic resonance brain images based on multi-atlas label propagation and graph cuts. The label maps obtained from multi-atlas segmentation are used to build a subject-specific probabilistic atlas of a structure of intere ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
We propose a general framework for segmentation of subcor-tical structures in magnetic resonance brain images based on multi-atlas label propagation and graph cuts. The label maps obtained from multi-atlas segmentation are used to build a subject-specific probabilistic atlas of a structure of interest. From this atlas and an intensity model estimated from the un-seen image, a Markov random field-based energy function is defined and via graph cuts. Compared to a previously pro-posed approach, our method does not rely on manual training of the intensity model and is applied to six subcortical struc-tures. We used this approach to segment the hippocampus on 60 images from the Alzheimer’s Disease Neuroimaging Ini-tiative (ADNI) and achieved an average overlap (Dice) of 0.86 with a manually delineated reference. Index Terms — structural MR images, atlas-based seg-mentation, graph cuts, subcortical structures, MRF 1.
Adaptive processing of thin structures to augment segmentation of dual-channel structural MRI of the human brain
, 2010
"... ..."
Executive Summary
"... This project is about facial asymmetry, its connection to emotional expression, and methods of measuring facial asymmetry in videos of faces. The research was motivated by two factors: firstly, there was a real opportunity to develop a novel measure of asymmetry that required minimal human involveme ..."
Abstract
- Add to MetaCart
(Show Context)
This project is about facial asymmetry, its connection to emotional expression, and methods of measuring facial asymmetry in videos of faces. The research was motivated by two factors: firstly, there was a real opportunity to develop a novel measure of asymmetry that required minimal human involvement and that im-proved on earlier measures in the literature; and secondly, the study of the rela-tionship between facial asymmetry and emotional expression is both interesting in its own right, and important because it can inform neuropsychological theory and answer open questions concerning emotional processing in the brain. The two aims of the research were: first, to develop an automatic frame-by-frame measure of facial asymmetry in videos of faces that improved on previous measures; and second, to use the measure to analyse the relationship between facial asymmetry and emotional expression, and connect our findings with previous research of the relationship. The project is best described as 80 % investigatory and 20 % software development. Since submitting the research review, the main accomplishments have been:
