2023
Outlier Robust Disease Classification via Stochastic Confidence Network
Lee K, Lee H, El Fakhri G, Sepulcre J, Liu X, Xing F, Hwang J, Woo J. Outlier Robust Disease Classification via Stochastic Confidence Network. Lecture Notes In Computer Science 2023, 14394: 80-90. DOI: 10.1007/978-3-031-47425-5_8.Peer-Reviewed Original ResearchDeep learningState-of-the-art modelsAccuracy of deep learningState-of-the-artMedical image dataMedical imaging modalitiesImage patchesIrrelevant patchesCategorical featuresPresence of outliersDL modelsConfidence networkConfidence predictionsClassifying outliersData samplesImage dataOutliersExperimental resultsDisease classificationImprove diagnostic performanceClassificationDiagnosing breast tumorsUltrasound imagingPerformanceImages
2022
Variational inference for quantifying inter-observer variability in segmentation of anatomical structures
Liu X, Xing F, Marin T, Fakhri G, Woo J. Variational inference for quantifying inter-observer variability in segmentation of anatomical structures. Proceedings Of SPIE--the International Society For Optical Engineering 2022, 12032: 120321m-120321m-6. PMID: 36303579, PMCID: PMC9603619, DOI: 10.1117/12.2604547.Peer-Reviewed Original ResearchSegmentation mapImage dataVariational inference frameworkVariational autoencoder networkMedical image dataInherent information lossMagnetic Resonance (MRSegmentation datasetAutoencoder networkVariational inferenceLatent vectorsInformation lossManual annotationSegmentation methodAleatoric uncertaintyInference frameworkSacrificing accuracyExperimental resultsAnnotationOrgan boundariesInter-observer variabilityImagesELBOMapsSegmentsVoxelHop: Successive Subspace Learning for ALS Disease Classification Using Structural MRI
Liu X, Xing F, Yang C, Kuo C, Babu S, Fakhri G, Jenkins T, Woo J. VoxelHop: Successive Subspace Learning for ALS Disease Classification Using Structural MRI. IEEE Journal Of Biomedical And Health Informatics 2022, 26: 1128-1139. PMID: 34339378, PMCID: PMC8807766, DOI: 10.1109/jbhi.2021.3097735.Peer-Reviewed Original ResearchConceptsConvolutional neural networkLearning modelsDimension reductionSubspace learning modelConcatenation of featuresState-of-the-artUnsupervised dimension reductionDeep learning modelsMedical image dataSupervised dimension reductionImage dataClassification of amyotrophic lateral sclerosisSubspace learningClassification taskDeep learningDataset sizeNeural networkSubspace approximationMemory requirementsTraining datasetClassification approachAUC scoreAccurate classificationDatasetExperimental results