Note: Intro -- Preface -- Organization -- Contents -- Deep Learning for Magnetic Resonance Imaging -- Recon-GLGAN: A Global-Local Context Based Generative Adversarial Network for MRI Reconstruction -- 1 Introduction -- 2 Methodology -- 2.1 Problem Formulation -- 2.2 Generative Adversarial Networks (GAN) -- 2.3 Proposed Reconstruction Global-Local GAN (Recon-GLGAN) -- 2.4 Network Architecture -- 2.5 Loss Function -- 3 Experiments and Results -- 3.1 Dataset -- 3.2 Evaluation Metrics -- 3.3 Implementation Details -- 3.4 Results and Discussion -- 4 Conclusion -- References -- Self-supervised Recurrent Neural Network for 4D Abdominal and In-utero MR Imaging -- 1 Introduction -- 2 Method -- 2.1 Data Acquisition -- 2.2 The Reconstruction Pipeline -- 2.3 Self-supervised RNN -- 2.4 Super-Resolution Reconstruction (SR-net) -- 2.5 Implementation Details -- 3 Results -- 3.1 Simulated Experiment -- 3.2 Real Data Reconstructions -- 4 Discussion and Conclusion -- References -- Fast Dynamic Perfusion and Angiography Reconstruction Using an End-to-End 3D Convolutional Neural Network -- 1 Introduction -- 2 Proposed Approach -- 2.1 Problem -- 2.2 Proposed Network -- 2.3 Dataset Generation -- 3 Experimental Results -- 4 Conclusion -- References -- APIR-Net: Autocalibrated Parallel Imaging Reconstruction Using a Neural Network -- 1 Introduction -- 2 Methods -- 2.1 Conventional Parallel Imaging Reconstruction griswold2002generalized -- 2.2 APIR-Net Reconstruction -- 3 Experiments -- 3.1 Evaluation with Phantom Acquisition -- 3.2 Comparison to RAKI -- 3.3 Evaluation with In-Vivo Acquisitions -- 4 Results -- 4.1 Evaluation with Phantom Acquisition -- 4.2 Comparison to RAKI -- 4.3 Evaluation with In-Vivo Acquisitions -- 5 Discussion and Conclusion -- References -- Accelerated MRI Reconstruction with Dual-Domain Generative Adversarial Network -- 1 Introduction -- 2 Methods. , 2.1 Accelerated MRI with Deep Generative Model -- 2.2 Network Architecture -- 2.3 Loss Function -- 2.4 Sampling Patterns -- 2.5 Datasets -- 2.6 Evaluation Metrics -- 3 Results -- 4 Discussion and Conclusions -- References -- Deep Learning for Low-Field to High-Field MR: Image Quality Transfer with Probabilistic Decimation Simulator -- 1 Introduction -- 2 Methods -- 2.1 Formulation -- 2.2 Probabilistic Decimation Simulator -- 2.3 Deep Learning Framework -- 3 Experiments -- 3.1 Implementation Details -- 3.2 Evaluation on Fixed SNR Data Sets -- 3.3 Evaluation on Variable SNR Data Sets -- 3.4 Test on Patient Data -- 4 Discussion and Conclusion -- References -- Joint Multi-anatomy Training of a Variational Network for Reconstruction of Accelerated Magnetic Resonance Image Acquisitions -- Abstract -- 1 Introduction -- 2 Methods -- 2.1 Image Acquisition -- 2.2 Variational Network -- 2.3 Network Training -- 2.4 Evaluation of Reconstructed Images -- 3 Results -- 4 Discussion -- 5 Conclusion -- Acknowledgements -- References -- Modeling and Analysis Brain Development via Discriminative Dictionary Learning -- 1 Introduction -- 2 The Proposed Approach -- 2.1 Discriminative Dictionary Learning -- 2.2 Training Algorithm -- 2.3 Classification -- 3 Experiments -- 3.1 Prediction of Brain Age -- 3.2 Exploring the Cortical Brain Development -- 4 Conclusion -- References -- Deep Learning for Computed Tomography -- Virtual Thin Slice: 3D Conditional GAN-based Super-Resolution for CT Slice Interval -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Objective Function -- 3.2 Network Architecture -- 3.3 Training Data -- 3.4 Conditioning Vector -- 4 Experiments -- 4.1 Datasets and Data Augmentation -- 4.2 Results -- 5 Conclusion -- References -- Data Consistent Artifact Reduction for Limited Angle Tomography with Deep Learning Prior -- 1 Introduction -- 2 Method. , 2.1 The U-Net Architecture -- 2.2 Data Consistent Artifact Reduction -- 2.3 Experimental Setup -- 3 Results -- 4 Discussion and Conclusion -- References -- Measuring CT Reconstruction Quality with Deep Convolutional Neural Networks -- 1 Background -- 2 Methodology -- 2.1 Data -- 2.2 Quality Estimation with Gradient Structural Similarity -- 2.3 Image Normalization -- 2.4 Convolutional Neural Network for Image Quality Score Estimation -- 2.5 Heatmap Regression -- 3 Experiments and Results -- 3.1 Comparison with Conventional Quality Metrics -- 3.2 Qualitative Results -- 4 Discussion -- 5 Conclusion -- References -- Deep Learning Based Metal Inpainting in the Projection Domain: Initial Results -- 1 Introduction -- 2 Proposed Method -- 2.1 Network Architectures -- 2.2 Training the Network -- 3 Results -- 3.1 Implicitly Learned Segmentation -- 3.2 Inpainting Results -- 4 Discussion -- 5 Conclusion -- References -- Deep Learning for General Image Reconstruction -- Flexible Conditional Image Generation of Missing Data with Learned Mental Maps -- 1 Introduction -- 2 Method -- 3 Experiments and Results -- 3.1 Initial Experiments -- 3.2 Exp1: ADNI MRI and Thorax CT -- 3.3 Exp2: Fetal Brain Template Volume -- 4 Conclusion and Discussion -- References -- Spatiotemporal PET Reconstruction Using ML-EM with Learned Diffeomorphic Deformation -- 1 Introduction -- 1.1 Survey of Existing Works -- 1.2 Proposed Method -- 2 Methods -- 2.1 Mathematical Background -- 2.2 General Approach -- 2.3 Motion Estimation -- 2.4 Reconstruction -- 2.5 Full Algorithm -- 2.6 Complexity -- 3 Results -- 3.1 Derenzo Phantom -- 3.2 Methods Without Motion Correction -- 3.3 Proposed Method -- 3.4 Implementation Details -- 4 Perspectives -- References -- Stain Style Transfer Using Transitive Adversarial Networks -- 1 Introduction -- 2 Methodology -- 2.1 The Framework. , 2.2 Network Architectures -- 3 Experiments and Results -- 3.1 Dateset and Details -- 3.2 Results with Different Levels of Downsampling -- 3.3 Comparisons of Results Using Different Generators -- 3.4 Comparison with State-of-the-Art Method -- 4 Discussion and Conclusion -- References -- Blind Deconvolution Microscopy Using Cycle Consistent CNN with Explicit PSF Layer -- 1 Introduction -- 2 Theory -- 2.1 Loss Function -- 2.2 Multi patchGANs in CycleGAN -- 3 Network Architecture -- 4 Method -- 5 Experimental Results -- 6 Discussion and Conclusion -- References -- Deep Learning Based Approach to Quantification of PET Tracer Uptake in Small Tumors -- 1 Introduction -- 1.1 Positron Emission Tomography -- 1.2 Deep Learning in PET Imaging -- 2 Materials and Method -- 2.1 Generation of 3D Shapes and Radionuclide Distribution -- 2.2 Network Architecture -- 2.3 Testing the Procedure -- 3 Results -- 3.1 Normalization -- 3.2 Different Spatial Resolutions -- 3.3 Physical Phantom PET Scans -- 4 Discussion and Conclusion -- References -- Task-GAN: Improving Generative Adversarial Network for Image Reconstruction -- 1 Introduction -- 2 Proposed Method: Task-GAN -- 2.1 Designs -- 2.2 Formulation -- 3 Experiments -- 3.1 Ultra-low-dose Amyloid PET Reconstruction Task -- 3.2 Multi-contrast MR Reconstruction Task -- 4 Discussion -- 5 Conclusion -- References -- Gamma Source Location Learning from Synthetic Multi-pinhole Collimator Data -- 1 Introduction -- 2 Methods and Materials -- 3 Results -- 4 Discussion and Conclusion -- References -- Neural Denoising of Ultra-low Dose Mammography -- Abstract -- 1 Introduction -- 2 Methods -- 2.1 The LC-NLM Algorithm -- 2.2 The Convolutional LC-NLM (CLC-NLM) Algorithm -- 2.3 Enforcing Local-Consistency -- 3 Experiments -- 3.1 Dataset -- 3.2 Setup -- 3.3 Comparison with State-of-the-Art -- 3.4 Ablation Study -- 4 Conclusions. , References -- Image Reconstruction in a Manifoldpg of Image Patches: Applicationpg to Whole-Fetus Ultrasound Imaging -- 1 Introduction -- 2 Method -- 2.1 Image Patch Fusion with Classical Manifold Embedding -- 2.2 Image Patch Fusion with a Variational Autoencoder -- 3 Materials and Experiments -- 3.1 Materials -- 3.2 Experiments -- 4 Results -- 5 Discussion and Conclusions -- References -- Image Super Resolution via Bilinear Pooling: Application to Confocal Endomicroscopy -- 1 Introduction -- 2 Method -- 3 Results and Discussion -- 4 Conclusion -- References -- TPSDicyc: Improved Deformation Invariant Cross-domain Medical Image Synthesis -- 1 Introduction -- 2 Previous Works -- 3 Method -- 3.1 Architecture of Generator -- 3.2 Loss and Training -- 4 Experiments -- 4.1 Evaluation Metrics -- 4.2 Results and Discussion -- 5 Conclusion -- References -- PredictUS: A Method to Extend the Resolution-Precision Trade-Off in Quantitative Ultrasound Image Reconstruction -- 1 Introduction -- 2 Method -- 2.1 ACE Computation -- 2.2 Network Architecture -- 3 Experiments and Results -- 3.1 Data -- 3.2 Training and Testing -- 3.3 RF Data Processing and Analysis -- 3.4 Performance Metrics -- 3.5 Results -- 4 Conclusion -- References -- Correction to: Gamma Source Location Learning from Synthetic Multi-pinhole Collimator Data -- Correction to: Chapter "Gamma Source Location Learning from Synthetic Multi-pinhole Collimator Data" in: F. Knoll et al. (Eds.): Machine Learning for Medical Image Reconstruction, LNCS 11905, https://doi.org/10.1007/978-3-030-33843-5_19 -- Author Index.