2024
Towards mitigating uncann(eye)ness in face swaps via gaze-centric loss terms
Wilson E, Shic F, Jörg S, Jain E. Towards mitigating uncann(eye)ness in face swaps via gaze-centric loss terms. Computers & Graphics 2024, 119: 103888. DOI: 10.1016/j.cag.2024.103888.Peer-Reviewed Original ResearchAssessment of valve regurgitation severity via contrastive learning and multi-view video integration
Kim S, Ren H, Charton J, Hu J, Gonzalez C, Khambhati J, Cheng J, DeFrancesco J, Waheed A, Marciniak S, Moura F, Cardoso R, Lima B, McKinney S, Picard M, Li X, Li Q. Assessment of valve regurgitation severity via contrastive learning and multi-view video integration. Physics In Medicine And Biology 2024, 69: 045020. PMID: 38271727, DOI: 10.1088/1361-6560/ad22a4.Peer-Reviewed Original ResearchConceptsRepresentation learningContrastive learningMulti-view video processingState-of-the-art methodsContrastive learning frameworkState-of-the-artIn-house datasetVideo processingContrastive networkEmbedding spaceImage inputLearning frameworkVideo integrationIntricate taskLoss termMulti-modal clinical dataLearningRepresentationLabor-intensiveAccuracyEfficient methodVideo seriesEmbeddingDatasetNetwork
2022
Unsupervised arterial spin labeling image superresolution via multiscale generative adversarial network
Cui J, Gong K, Han P, Liu H, Li Q. Unsupervised arterial spin labeling image superresolution via multiscale generative adversarial network. Medical Physics 2022, 49: 2373-2385. PMID: 35048390, DOI: 10.1002/mp.15468.Peer-Reviewed Original ResearchConceptsPeak signal-to-noise ratioStructural similarity indexNearest neighbor interpolationSignal-to-noise ratioTrilinear interpolationNeighbor interpolationAblation studiesB-spline interpolationLow-pass-filterLayer-by-layer trainingLoss termLow resolutionClearer structure boundariesLow signal-to-noise ratioIn vivo datasetsImage superresolutionGAN frameworkAdversarial networkB-spline interpolation methodReduce image noiseWeak labelsPrior informationSimilarity indexDipping methodSimulated data
2021
Learning-Based Regularization for Cardiac Strain Analysis via Domain Adaptation
Lu A, Ahn SS, Ta K, Parajuli N, Stendahl JC, Liu Z, Boutagy NE, Jeng GS, Staib LH, O’Donnell M, Sinusas AJ, Duncan JS. Learning-Based Regularization for Cardiac Strain Analysis via Domain Adaptation. IEEE Transactions On Medical Imaging 2021, 40: 2233-2245. PMID: 33872145, PMCID: PMC8442959, DOI: 10.1109/tmi.2021.3074033.Peer-Reviewed Original Research
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply