2023
Learning Sequential Information in Task-Based fMRI for Synthetic Data Augmentation
Wang J, Dvornek N, Staib L, Duncan J. Learning Sequential Information in Task-Based fMRI for Synthetic Data Augmentation. Lecture Notes In Computer Science 2023, 14312: 79-88. DOI: 10.1007/978-3-031-44858-4_8.Peer-Reviewed Original ResearchFunctional magnetic resonance imagesData augmentationClassification taskSpecific cognitive tasksMedical image analysisSynthetic data augmentationEffective data augmentationDownstream learning tasksCognitive tasksVariational autoencoder modelLearning taskTraining dataAutoencoder modelTemporal informationTraining datasetSequential informationSynthetic imagesTaskFMRI sequencesImage analysisMultiple perspectivesMagnetic resonance imagesImagesDifferent alternativesPersistent issue
2022
SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation
You C, Zhou Y, Zhao R, Staib L, Duncan JS. SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation. IEEE Transactions On Medical Imaging 2022, 41: 2228-2237. PMID: 35320095, PMCID: PMC10325835, DOI: 10.1109/tmi.2022.3161829.Peer-Reviewed Original ResearchConceptsMedical image segmentationImage segmentationSemi-supervised medical image segmentationRobust Medical Image SegmentationMedical image analysisUnsupervised training strategyAtrial Segmentation ChallengeLearning-based approachMedical image synthesisAverage Dice scoreSemi-supervised approachPair-wise similarityContrastive objectiveData augmentationSegmentation challengePopular datasetsDice scoreSemantic informationDistillation frameworkSegmentation accuracyDownstream tasksImage synthesisPrevious best resultSupervised counterpartMedical data
2019
Dual Adversarial Autoencoder for Dermoscopic image Generative Modeling
Yang H, Staib L. Dual Adversarial Autoencoder for Dermoscopic image Generative Modeling. 2019, 00: 1247-1250. DOI: 10.1109/isbi.2019.8759293.Peer-Reviewed Original ResearchComputer-Aided DiagnosisAdversarial trainingGenerative modelingComputer vision tasksSkin lesion classificationNew training dataNovel generative modelRealistic synthetic dataVision tasksEnd trainableData augmentationManual effortTraditional autoencoderAided DiagnosisDiscriminator networkAdversarial autoencoderTraining dataTraining iterationsTraining algorithmGenerative modelLesion classificationNumerous tasksImage denoisingAutoencoderDermoscopic images