Joint spectral quantification of MR spectroscopic imaging using linear tangent space alignment‐based manifold learning
Ma C, Han P, Zhuo Y, Djebra Y, Marin T, Fakhri G. Joint spectral quantification of MR spectroscopic imaging using linear tangent space alignment‐based manifold learning. Magnetic Resonance In Medicine 2022, 89: 1297-1313. PMID: 36404676, PMCID: PMC9892363, DOI: 10.1002/mrm.29526.Peer-Reviewed Original ResearchConceptsSubspace-based methodsManifold learningIntrinsic low-dimensional structureGlobal coordinationLearning-based methodsNumerical simulation dataSpatial smoothness constraintSparsity constraintSpace alignmentSubspace modelSmoothness constraintSuperior performanceRoot mean square errorLinear transformationMechanical simulationsLow-dimensionalSquare errorSubspaceExperimental dataSpectroscopic imagingQuantum mechanical simulationsCoordinate alignmentMR spectroscopic imagingSpectral quantificationSimulated dataUnsupervised 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