Data driven image models through continuous joint alignment

Learned-Miller, Erik

doi:10.1109/tpami.2006.34

Cited by 268 publications

(188 citation statements)

References 21 publications

(27 reference statements)

Supporting

Mentioning

185

Contrasting

Order By: Relevance

“…To achieve common anatomical coordinates across subjects, a group-average FA data set was constructed from the FA data from all 120 subjects with group-wise affine registration (Learned-Miller, 2006) followed by an iterative non-rigid averaging (Rohlfing et al, 2001;Rohlfing and Maurer, 2003).…”

Section: Warping To Common Coordinatesmentioning

confidence: 99%

Quantitative fiber tracking of lateral and interhemispheric white matter systems in normal aging: Relations to timed performance

Sullivan

Rohlfing

Pfefferbaum

2010

Neurobiology of Aging

305

307

View full text Add to dashboard Cite

The integrity of white matter, as measured in vivo with diffusion tensor imaging (DTI), is disrupted in normal aging. A current consensus is that in adults advancing age affects anterior brain regions disproportionately more than posterior regions; however, the mainstay of studies supporting this anterior-posterior gradient is based primarily on measures of the corpus callosum. Using our quantitative fiber tracking approach, we assessed fiber tract integrity of samples of major white matter cortical, subcortical, interhemispheric, and cerebellar systems (11 bilateral and 2 callosal) on DTI data collected at 1.5 T magnet strength. Participants were 55 men (age 20-78 years) and 65 women (age 28-81 years), deemed healthy and cognitively intact following interview and behavioral testing. Fiber integrity was measured as orientational diffusion coherence (fractional anisotropy, FA) and magnitude of diffusion, which was quantified separately for longitudinal diffusivity (λL), an index of axonal length or number, and transverse diffusivity (λT), an index of myelin integrity. Aging effects were more evident in diffusivity than FA measures. Men and women, examined separately, showed similar age-related increases in longitudinal and transverse diffusivity in fibers of the internal and external capsules bilaterally and the fornix. FA was lower and diffusivity higher in anterior than posterior fibers of regional paired comparisons (genu versus splenium and frontal versus occipital forceps). Diffusivity with older age was generally greater or FA lower in the superior than inferior fiber systems (longitudinal fasciculi, cingulate bundles), with little to no evidence for age-related degradation in pontine or cerebellar systems. The most striking sex difference emerged for the corpus callosum, for which men showed significant decline in FA and increase in longitudinal and transverse diffusivity in the genu but not splenium. By contrast, in women the age effect was present in both callosal regions, albeit modestly more so in the genu than splenium. Functional meaningfulness of these age-related differences was supported by significant correlations between DTI signs of white matter degradation and poorer performance on cognitive or motor tests. This survey of multiple fiber systems throughout the brain revealed a differential pattern of age's effect on regional FA and diffusivity and suggests mechanisms of functional degradation, attributed at least in part to compromised fiber microstructure affecting myelin and axonal morphology.

show abstract

Section: Warping To Common Coordinatesmentioning

confidence: 99%

Quantitative fiber tracking of lateral and interhemispheric white matter systems in normal aging: Relations to timed performance

Sullivan

Rohlfing

Pfefferbaum

2010

Neurobiology of Aging

305

307

View full text Add to dashboard Cite

show abstract

“…Face alignment requires the automated or manual detection of fiducial points (Mäkinen and Raisamo, 2008;Gallagher and Chen, 2009) or a congealling previous step (aligning all the images in a set by reducing entropy (Learned-Miller, 2006)). In their work, (Mäkinen and Raisamo, 2008) report that, although manual face alignment does increase gender classification rates, the performance improvements achieved by automatic methods are not significant.…”

Section: Introductionmentioning

confidence: 99%

Robust gender recognition by exploiting facial attributes dependencies

Bekios-Calfa

Buenaposada

Baumela

2014

Pattern Recognition Letters

View full text Add to dashboard Cite

Estimating human face gender from images is a problem that has been extensively studied because of its relevant applications. Recent works report significant drops in performance for state-of-the-art gender classifiers when evaluated "in the wild," i.e. with uncontrolled demography and environmental conditions. We hypothesize that this is caused by the existence of dependencies among facial demographic attributes that have not been considered when building the classifier. In the paper we study the dependencies among gender, age and pose facial attributes. By considering the relation between gender and pose attributes we also avoid the use of computationally expensive and fragile face alignment procedures. In the experiments we confirm the existence of dependencies among gender, age and pose facial attributes and prove that we can improve the performance and robustness of gender classifiers by exploiting these dependencies.

show abstract

“…Joshi et al [3] extends a large deformation diffeomorphic mapping algorithm [4] to work in a groupwise manner for unbiased atlas construction. A congealing framework [5] based groupwise registration scheme is proposed in [6], where intensity based entropy drives a gradient-based stochastic optimizer and pushes each image to the population center simultaneously. This method, which originally works for affine transformation only, is further extended by Balci et al [7] to incorporate B-Splines to model nonrigid deformation.…”

Section: Introductionmentioning

confidence: 99%

Attribute Vector Guided Groupwise Registration

Yap

Shen

2009

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009

View full text Add to dashboard Cite

Abstract. Groupwise registration has been recently introduced for simultaneous registration of a group of images with the goal of constructing an unbiased atlas. To this end, direct application of information-theoretic entropy measures on image intensity has achieved various successes. However, simplistic voxelwise utilization of image intensity often neglects important contextual information, which can be provided by more comprehensive geometric and statistical features. In this paper, we employ attribute vectors, instead of image intensities, to guide groupwise registration. In particular, for each voxel, the attribute vector is computed from its multiple-scale neighborhoods to capture geometric information at different scales. Moreover, the probability density function (PDF) of each attribute in the vector is then estimated from the local neighborhood, providing a statistical summary of the underlying anatomical structure. For the purpose of registration, Jensen-Shannon (JS) divergence is used to measure the PDF dissimilarity of each attribute at corresponding locations of different individual images. By minimizing the overall JS divergence in the whole image space and estimating the deformation field of each image simultaneously, we can eventually register all images and build an unbiased atlas. Experimental results indicate that our method yields better registration quality, compared with a popular groupwise registration method.

show abstract

Data driven image models through continuous joint alignment

Cited by 268 publications

References 21 publications

Quantitative fiber tracking of lateral and interhemispheric white matter systems in normal aging: Relations to timed performance

Quantitative fiber tracking of lateral and interhemispheric white matter systems in normal aging: Relations to timed performance

Robust gender recognition by exploiting facial attributes dependencies

Attribute Vector Guided Groupwise Registration

Contact Info

Product

Resources

About