2024
Multi-Task Learning for Motion Analysis and Segmentation in 3D Echocardiography
Ta K, Ahn S, Thorn S, Stendahl J, Zhang X, Langdon J, Staib L, Sinusas A, Duncan J. Multi-Task Learning for Motion Analysis and Segmentation in 3D Echocardiography. IEEE Transactions On Medical Imaging 2024, 43: 2010-2020. PMID: 38231820, PMCID: PMC11514714, DOI: 10.1109/tmi.2024.3355383.Peer-Reviewed Original ResearchMulti-task learning networkCross-stitch unitsComposite loss functionAccurate motion estimationTask-specific networksMotion estimationSegmentation masksLearning networkLoss functionSegmentation stepEchocardiography datasetNetworkMotion displacementMotion analysisMultiple time framesTaskAnalysis pipelineSegmentsStrain measurementsDatasetRepresentation
2022
Incremental Learning Meets Transfer Learning: Application to Multi-site Prostate MRI Segmentation
You C, Xiang J, Su K, Zhang X, Dong S, Onofrey J, Staib L, Duncan J. Incremental Learning Meets Transfer Learning: Application to Multi-site Prostate MRI Segmentation. Lecture Notes In Computer Science 2022, 13573: 3-16. PMID: 37415747, PMCID: PMC10323962, DOI: 10.1007/978-3-031-18523-6_1.Peer-Reviewed Original ResearchIncremental learningMedical image segmentation tasksMulti-site datasetImage segmentation tasksMedical image segmentationProstate MRI SegmentationComputation resourcesMedical datasetsSegmentation taskImage segmentationSegmentation frameworkEmbedding featuresBenchmark datasetsMRI segmentationTraining dataTarget domainLearning approachPractical deploymentDomain-specific expertiseCompetitive performanceDatasetTraining schemePrior workSegmentationSingle modelAtlas-Based Semantic Segmentation of Prostate Zones
Zhang J, Venkataraman R, Staib L, Onofrey J. Atlas-Based Semantic Segmentation of Prostate Zones. Lecture Notes In Computer Science 2022, 13435: 570-579. PMID: 38084296, PMCID: PMC10711803, DOI: 10.1007/978-3-031-16443-9_55.Peer-Reviewed Original ResearchSegmentation resultsSemantic segmentation frameworkSemantic segmentation resultsDice similarity coefficient valuesSemantic segmentationInference stageSegmentation frameworkSegmentation performanceExternal test datasetTest datasetRegion of interestSegmentationAnatomical atlasHyperparametersSimilarity coefficient valuesAnatomical informationGitHubUsersDatasetProstate zonesCodeFrameworkInformationIdentifying clinically applicable machine learning algorithms for glioma segmentation: recent advances and discoveries
Tillmanns N, Lum AE, Cassinelli G, Merkaj S, Verma T, Zeevi T, Staib L, Subramanian H, Bahar RC, Brim W, Lost J, Jekel L, Brackett A, Payabvash S, Ikuta I, Lin M, Bousabarah K, Johnson MH, Cui J, Malhotra A, Omuro A, Turowski B, Aboian MS. Identifying clinically applicable machine learning algorithms for glioma segmentation: recent advances and discoveries. Neuro-Oncology Advances 2022, 4: vdac093. PMID: 36071926, PMCID: PMC9446682, DOI: 10.1093/noajnl/vdac093.Peer-Reviewed Original ResearchGlioma segmentationResearch algorithmSegmentation of gliomasHigh accuracy resultsML algorithmsApplicable machineAccuracy resultsTCIA datasetSegmentationAlgorithmMachinePatient dataSystematic literature reviewOverfittingData extractionDatasetBratDatabaseRecent advancesResearch literatureLimitationsExtractionCurrent research literatureMethodLearning Correspondences of Cardiac Motion from Images Using Biomechanics-Informed Modeling
Zhang X, You C, Ahn S, Zhuang J, Staib L, Duncan J. Learning Correspondences of Cardiac Motion from Images Using Biomechanics-Informed Modeling. Lecture Notes In Computer Science 2022, 13593: 13-25. DOI: 10.1007/978-3-031-23443-9_2.Peer-Reviewed Original ResearchDisplacement vector fieldQuantitative evaluation metricsCardiac anatomical structuresTraining complexityExtensive experimentsSegmentation performanceBiomechanical feasibilityEvaluation metricsAvailable datasetsCardiac motionSmoothness constraintGeometric constraintsBiomechanical propertiesDatasetMRI dataPlausible transformationsMotionConstraintsAnatomical structuresRegularizerRegularization schemeMethodIncompressibilityImagesMetrics