Large Deformation Diffeomorphism and Momentum Based Hippocampal Shape Discrimination in Dementia of the Alzheimer type

Wang, Lei; Beg, Faisal; Ratnanather, J. Tilak; Ceritoglu, Can; Younes, Laurent; Morris, John C.; Csernansky, John G.; Miller, Michael I.

doi:10.1109/tmi.2006.887380

Cited by 146 publications

(115 citation statements)

References 41 publications

Supporting

Mentioning

113

Contrasting

Order By: Relevance

“…This problem therefore directly relates to geodesics in groups of diffeomorphisms, namely to the EPDiff equation [1,18,14], and the conserved initial momentum that specifies the solution has been used in statistical studies in order to provide anatomical characterizations of mental disorders [22,31]. One of the issues in problems formulated as (1) is that the error term breaks the metric aspects inherited from the distance d on diffeomorphisms.…”

Section: Find Arg Min D(id G)mentioning

confidence: 99%

The Euler-Poincaré theory of metamorphosis

Holm¹,

Trouvé²,

Younes³

2009

Quart. Appl. Math.

Self Cite

105

View full text Add to dashboard Cite

Abstract. In the pattern matching approach to imaging science, the process of "metamorphosis" is template matching with dynamical templates (Trouvé and Younes, Found. Comp. Math., 2005). Here, we recast the metamorphosis equations of that paper into the Euler-Poincaré variational framework of Holm, Marsden, and Ratiu, Adv. in Math., 1998 and show that the metamorphosis equations contain the equations for a perfect complex fluid (Holm, Springer, 2002). This result connects the ideas underlying the process of metamorphosis in image matching to the physical concept of an order parameter in the theory of complex fluids. After developing the general theory, we reinterpret various examples, including point set, image and density metamorphosis. We finally discuss the issue of matching measures with metamorphosis, for which we provide existence theorems for the initial and boundary value problems.1. Overview. Pattern matching is an important component of imaging science, with privileged applications in computerized anatomical analysis of medical images (computational anatomy) [2,4,12,23]. When comparing images, the purpose is to find, based on the conservation of photometric cues, an optimal nonrigid alignment between the images.

show abstract

Section: Find Arg Min D(id G)mentioning

confidence: 99%

The Euler-Poincaré theory of metamorphosis

Holm¹,

Trouvé²,

Younes³

2009

Quart. Appl. Math.

Self Cite

105

View full text Add to dashboard Cite

show abstract

“…However, voxelwise labeling methods that employ probabilistic-atlases often involve averaging a training set which may cause some fine details to be lost when labeling voxels in a target scan. Also, similar to manual segmentations, voxel-wise labeling can also lead to non-smooth subcortical segmentations that may confound downstream shape analysis algorithms Wang et al (2007a) due to "shape-noise". Another limitation is with respect to the adaptability to differing protocols for defining subcortical shapes.…”

mentioning

confidence: 99%

FreeSurfer-initiated fully-automated subcortical brain segmentation in MRI using Large Deformation Diffeomorphic Metric Mapping

Wang²,

2008

Self Cite

View full text Add to dashboard Cite

Fully-automated brain segmentation methods have not been widely adopted for clinical use because of issues related to reliability, accuracy, and limitations of delineation protocol. By combining the probabilistic-based FreeSurfer (FS) method with the Large Deformation Diffeomorphic Metric Mapping (LDDMM) based label propagation method, we are able to increase reliability and accuracy, and allow for flexibility in template choice. Our method uses the automated FreeSurfer subcortical labeling to provide a coarse to fine introduction of information in the LDDMM template-based segmentation resulting in a fully-automated subcortical brain segmentation method (FS+LDDMM).One major advantage of the FS+LDDMM-based approach is that the automatically generated segmentations generated are inherently smooth, thus subsequent steps in shape analysis can directly follow without manual post-processing or loss of detail.We have evaluated our new FS+LDDMM method on several databases containing a total of 50 subjects with different pathologies, scan sequences and manual delineation protocols for labeling the basal ganglia, thalamus, and hippocampus. In healthy controls we report Dice overlap measures of 0. 81, 0.83, 0.74, 0.86 and 0.75 for the right caudate nucleus, putamen, pallidum, thalamus and hippocampus respectively. We also find statistically significant improvement of accuracy in FS +LDDMM over FreeSurfer for the caudate nucleus and putamen of Huntington's disease and Tourette's syndrome subjects, and the right hippocampus of Schizophrenia subjects.

show abstract

“…Wang et al describe how in the framework of a largedeformation diffeomorphic metric mapping (LDDMM) the diffeomorphic matching of images is modeled as the change with time of a flow of an associated smooth velocity vector field v controlling the evolution [53]. The initial momentum parameterizes the whole geodesic and encodes the shape and form of the target image.…”

Section: Automatic Methodsmentioning

confidence: 99%

Automatic Morphological Analysis of Medial Temporal Lobe

Chincarini¹,

Corosu²,

Gemme³

et al. 2010

TONMEDJ

View full text Add to dashboard Cite

Abstract:Research in Alzheimer's disease (AD) has seen a tremendous growth of candidate biomarkers in the last decade. The role of such established or putative biomarkers is to allow an accurate diagnosis of AD, to infer about its prognosis, to monitor disease progression and evaluate changes induced by disease-modifying drugs. An ideal biomarker should detect a specific pathophysiological feature of AD, not present in the healthy condition, in other primary dementias, or in confounding conditions. Besides being reliable, a biomarker should be detectable by means of procedures which must be relatively non-invasive, simple to perform, widely available and not too expensive. At present, no candidate meets these requirements representing the high standards aimed at by researchers. Among others, various morphological brain measures performed by means of magnetic resonance imaging (MRI), ranging from the total brain volume to some restricted regions such as the hippocampal volume, have been proposed. Nowadays the efforts are directed toward finding an automated, unsupervised method of evaluating atrophy in some specific brain region, such as the medial temporal lobe (MTL). In this work we provide an extensive review of the state of the art on the automatic and semi-automatic image processing techniques for the early assessment of patients at risk of developing AD. Our main focus is the relevance of the morphological analysis of MTL, and in particular of the hippocampal formation, in making the diagnosis of AD and in distinguishing it from other dementias.

show abstract

Large Deformation Diffeomorphism and Momentum Based Hippocampal Shape Discrimination in Dementia of the Alzheimer type

Cited by 146 publications

References 41 publications

The Euler-Poincaré theory of metamorphosis

The Euler-Poincaré theory of metamorphosis

FreeSurfer-initiated fully-automated subcortical brain segmentation in MRI using Large Deformation Diffeomorphic Metric Mapping

Automatic Morphological Analysis of Medial Temporal Lobe

Contact Info

Product

Resources

About