2024
Generation of Synthetic brain PET images of synaptic density from MRI and FDG-PET using a Multi-stage U-Net
Zheng X, Worhunsky P, Liu Q, Zhou B, Chen X, Guo X, Xie H, Sun H, Zhang J, Toyonaga T, Mecca A, O’Dell R, van Dyck C, Carson R, Radhakrishnan R, Liu C. Generation of Synthetic brain PET images of synaptic density from MRI and FDG-PET using a Multi-stage U-Net. 2024, 00: 1-2. DOI: 10.1109/nss/mic/rtsd57108.2024.10655600.Peer-Reviewed Original Research
2023
Direct respiratory motion correction of whole-body PET images using a deep learning framework incorporating spatial information
Miao T, Tsai Y, Zhou B, Menard D, Schleyer P, Hong I, Casey M, Liu C. Direct respiratory motion correction of whole-body PET images using a deep learning framework incorporating spatial information. Progress In Biomedical Optics And Imaging 2023, 12463: 124633x-124633x-9. DOI: 10.1117/12.2654472.Peer-Reviewed Original ResearchDeep learning frameworkRespiratory motion correctionMotion-corrected imagesLearning frameworkImage domainSpatial informationData-driven gating methodMotion correctionMotion detection techniqueGround truth imagesU-NetTruth imagesPET imagesData driving methodImage reconstructionWhole-body PET imagesMotion sensorsDetection techniquesExternal motion sensorsCross validationImagesConvenient mannerFrameworkRespiratory motionInformation
2022
An Adaptive Patch Sampling Scheme for Deep Learning Based PET Image Denoising
Wu J, Tan H, Liu H, Liu C, Onofrey J. An Adaptive Patch Sampling Scheme for Deep Learning Based PET Image Denoising. 2022, 00: 1-3. DOI: 10.1109/nss/mic44845.2022.10399313.Peer-Reviewed Original ResearchOver-smoothing effectSignal-to-noise ratioU-NetImage denoisingDeep learning-based approachPET image denoisingL1 loss functionPatch-based strategyLearning-based approachSampling schemeMean square errorHigh signal-to-noise ratioDenoising performanceLow-dose PET imagesNetwork trainingWeight mapData augmentationDenoisingLoss functionNetworkImage noiseSquare errorPatch samplesSampling rateSchemeMCP-Net: Inter-frame Motion Correction with Patlak Regularization for Whole-body Dynamic PET
Guo X, Zhou B, Chen X, Liu C, Dvornek N. MCP-Net: Inter-frame Motion Correction with Patlak Regularization for Whole-body Dynamic PET. Lecture Notes In Computer Science 2022, 13434: 163-172. PMID: 38464686, PMCID: PMC10923180, DOI: 10.1007/978-3-031-16440-8_16.Peer-Reviewed Original ResearchConvolutional long short-term memory (ConvLSTM) layersLong short-term memory layersMotion estimation moduleShort-term memory layersDeep learning benchmarksEnhanced network performanceImage registration problemMotion correction frameworkMotion correctionU-NetNetwork performanceLearning benchmarksSimilarity measurementEstimation moduleRegistration problemGradient lossMemory layerLoss functionDynamic frameDynamic positron emission tomographyFitting errorSpatial alignmentSpatial misalignmentPatient motionModuleDeep-Learning-Based Few-Angle Cardiac SPECT Reconstruction Using Transformer
Xie H, Thorn S, Liu Y, Lee S, Liu Z, Wang G, Sinusas A, Liu C. Deep-Learning-Based Few-Angle Cardiac SPECT Reconstruction Using Transformer. IEEE Transactions On Radiation And Plasma Medical Sciences 2022, 7: 33-40. PMID: 37397179, PMCID: PMC10312390, DOI: 10.1109/trpms.2022.3187595.Peer-Reviewed Original ResearchConvolutional neural networkLimitations of CNNMedical imaging tasksDeep U-NetImage reconstruction taskCardiac SPECT imagesComputer visionVision TransformerConvolutional kernelsTransformer networkAttention blockInput imageU-NetNeural networkMemory burdenImage sizeInductive biasInformative featuresImage volumesImaging tasksTesting dataNetworkWhole 3D volumeNetwork structureCardiac single photon emission
2021
Investigation of Direct and Indirect Approaches of Deep-Learning-Based Attenuation Correction for General Purpose and Dedicated Cardiac SPECT Scanners
Chen X, Zhou B, Xie H, Shi L, Liu H, Liu C. Investigation of Direct and Indirect Approaches of Deep-Learning-Based Attenuation Correction for General Purpose and Dedicated Cardiac SPECT Scanners. 2021, 00: 1-2. DOI: 10.1109/nss/mic44867.2021.9875517.Peer-Reviewed Original ResearchNovel neural networkConventional U-NetMulti-channel inputDeep learningU-NetAttenuation mapNeural networkMap generationCardiac SPECTGeneral purposeSuperior performanceImagesDatasetIterative reconstructionAttenuation-corrected imagesCT transmission scanningAveraged errorNovel methodParallel-hole SPECTAttenuation correctionSPECT scannerMapsEmission imagesDirect approachScanner