2018
Segmenting the Brain Surface From CT Images With Artifacts Using Locally Oriented Appearance and Dictionary Learning
Onofrey JA, Staib LH, Papademetris X. Segmenting the Brain Surface From CT Images With Artifacts Using Locally Oriented Appearance and Dictionary Learning. IEEE Transactions On Medical Imaging 2018, 38: 596-607. PMID: 30176584, PMCID: PMC6476428, DOI: 10.1109/tmi.2018.2868045.Peer-Reviewed Original Research
2015
Learning intervention-induced deformations for non-rigid MR-CT registration and electrode localization in epilepsy patients
Onofrey JA, Staib LH, Papademetris X. Learning intervention-induced deformations for non-rigid MR-CT registration and electrode localization in epilepsy patients. NeuroImage Clinical 2015, 10: 291-301. PMID: 26900569, PMCID: PMC4724039, DOI: 10.1016/j.nicl.2015.12.001.Peer-Reviewed Original Research
2013
Contour tracking in echocardiographic sequences via sparse representation and dictionary learning
Huang X, Dione DP, Compas CB, Papademetris X, Lin BA, Bregasi A, Sinusas AJ, Staib LH, Duncan JS. Contour tracking in echocardiographic sequences via sparse representation and dictionary learning. Medical Image Analysis 2013, 18: 253-271. PMID: 24292554, PMCID: PMC3946038, DOI: 10.1016/j.media.2013.10.012.Peer-Reviewed Original ResearchConceptsContour trackerSparse representationEchocardiographic sequencesRegion-based level set segmentationLevel set segmentationLocal image appearanceManual tracingExpert manual tracingsMultiscale sparse representationImage sequencesSegmentation resultsAppearance modelSpatiotemporal priorsFirst frameMultilevel informationHuman data setsEjection fraction estimatesLocal appearanceImage appearanceDictionary learningShape modelContour trackingManual resultsData setsContour estimation
2009
Using Perturbation theory to reduce noise in diffusion tensor fields
Bansal R, Staib LH, Xu D, Laine AF, Liu J, Peterson BS. Using Perturbation theory to reduce noise in diffusion tensor fields. Medical Image Analysis 2009, 13: 580-597. PMID: 19540791, PMCID: PMC2782748, DOI: 10.1016/j.media.2009.05.001.Peer-Reviewed Original ResearchConceptsTensor fieldsDiffusion tensor fieldsPerturbation theoryMarkov random fieldPrior termDifferent spatial directionsRandom fieldsSymmetric tensorsRiemannian distanceSpatial directionsWhite matter fiber bundlesSmoothed fieldsLikelihood termEigenvaluesOriginal fieldEigenvectorsTensorReal-world datasetsDTI datasetsHomogeneous regionsTheoryLow signalNoiseNoise ratioFine structure