Machine learning for medical image reconstruction : 5th international workshop, MLMIR 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022 : proceedings / / Nandinee Haq [and five others]

• Pubblicazione: Cham, Switzerland : , : Springer International Publishing, , [2022]; ©2022
• Descrizione fisica: 1 online resource (162 pages)
• Disciplina: 610.28563
• Soggetto topico: Artificial intelligence - Medical applications; Diagnostic imaging - Data processing
• Persona (resp. second.): HaqNandinee
• Nota di contenuto: Intro -- Preface -- Organization -- Contents -- Deep Learning for Magnetic Resonance Imaging -- Rethinking the Optimization Process for Self-supervised Model-Driven MRI Reconstruction -- 1 Introduction -- 2 Theory -- 2.1 Model Based Deep Learning Network -- 2.2 Self-supervised MRI Reconstruction -- 2.3 Derivation of K-Space Calibration -- 3 Experiments and Results -- 3.1 Dataset -- 3.2 Implementation Details -- 3.3 Results -- 4 Conclusion -- References -- NPB-REC: Non-parametric Assessment of Uncertainty in Deep-Learning-Based MRI Reconstruction from Undersampled Data -- 1 Introduction -- 2 Methods -- 2.1 MRI Reconstruction -- 2.2 Non-parametric Bayesian MRI Reconstruction -- 2.3 The Reconstruction Network -- 3 Experiments -- 3.1 Database -- 3.2 Experimental Setup -- 3.3 Results -- 4 Conclusions -- References -- Adversarial Robustness of MR Image Reconstruction Under Realistic Perturbations -- 1 Introduction -- 2 Methods -- 3 Experiments and Results -- 4 Conclusion -- References -- High-Fidelity MRI Reconstruction with the Densely Connected Network Cascade and Feature Residual Data Consistency Priors -- 1 Introduction -- 2 Method -- 2.1 Problem Formulation -- 2.2 Reconstruction Framework -- 2.3 Objective Function -- 3 Experiment -- 3.1 Comparison Results -- 3.2 Ablation Studies on Model Components -- 3.3 Ablation Studies on Bottleneck Design in DC Blocks -- 4 Conclusions and Discussion -- References -- Metal Artifact Correction MRI Using Multi-contrast Deep Neural Networks for Diagnosis of Degenerative Spinal Diseases -- 1 Introduction -- 2 Method -- 2.1 Data Preprocessing -- 2.2 Multi-contrast SEMAC Acceleration -- 2.3 Implementation Details -- 3 Experiment -- 3.1 Results of SEMAC Acceleration -- 3.2 Results of SEMAC/Phase-Encoding Acceleration -- 4 Discussion and Conclusion -- References -- Segmentation-Aware MRI Reconstruction. ; 1 Introduction -- 2 Methods -- 2.1 Proposed Framework -- 2.2 Stabilization -- 2.3 Model Architectures -- 2.4 Implementation Details -- 3 Experimental Results -- 4 Conclusion -- References -- MRI Reconstruction with Conditional Adversarial Transformers -- 1 Introduction -- 2 Theory -- 2.1 Deep MRI Reconstruction -- 2.2 Conditional Adversarial Transformers -- 3 Methods -- 4 Results -- 5 Discussion -- 6 Conclusion -- References -- Deep Learning for General Image Reconstruction -- A Noise-Level-Aware Framework for PET Image Denoising -- 1 Introduction -- 2 Noise-Level-Aware Framework -- 2.1 Quantification of Local Relative Noise Level -- 3 Experiments -- 3.1 Experimental Setup -- 3.2 Implementation Details -- 3.3 Results and Analysis -- 4 Conclusion -- References -- DuDoTrans: Dual-Domain Transformer for Sparse-View CT Reconstruction -- 1 Introduction and Motivation -- 2 Method -- 2.1 Network Architecture -- 3 Experimental Results -- 3.1 Ablation Study and Analysis -- 3.2 Sparse-View CT Reconstruction Analysis -- 4 Conclusion -- References -- Deep Denoising Network for X-Ray Fluoroscopic Image Sequences of Moving Objects -- 1 Introduction -- 2 Methods -- 2.1 Overall Architecture -- 2.2 Parallel Warping -- 2.3 Self-attention -- 2.4 Optimization of the Network -- 3 Experimental Results -- 3.1 Dataset Acquisition -- 3.2 Experimental Setup -- 3.3 Performance Comparison with State-of-the-Art Methods -- 3.4 Ablation Study -- 4 Discussion and Conclusion -- References -- PP-MPI: A Deep Plug-and-Play Prior for Magnetic Particle Imaging Reconstruction -- 1 Introduction -- 2 Background -- 2.1 MPI Signal Model -- 2.2 MPI Image Reconstruction -- 3 Methods -- 3.1 Plug-and-Play MPI Reconstruction (PP-MPI) -- 3.2 Analyses -- 4 Results -- 5 Discussion -- References -- Learning While Acquisition: Towards Active Learning Framework for Beamforming in Ultrasound Imaging. ; 1 Introduction -- 2 Active Learning for US Beamforming -- 3 Results -- 4 Discussion and Conclusions -- References -- DPDudoNet: Deep-Prior Based Dual-Domain Network for Low-Dose Computed Tomography Reconstruction -- 1 Introduction -- 2 Method -- 2.1 The DPDudo Algorithm -- 2.2 The DPDudoNet -- 2.3 Interpretability of the DPDudoNet -- 2.4 Training Loss -- 3 Experimental Results -- 3.1 Clinical Data -- 3.2 Evaluation Metrics -- 3.3 Training Details -- 3.4 Performance Evaluation -- 3.5 Ablation Study -- 4 Conclusion -- References -- MTD-GAN: Multi-task Discriminator Based Generative Adversarial Networks for Low-Dose CT Denoising -- 1 Introduction -- 1.1 Deep Denoiser -- 1.2 Multi-task Learning -- 2 Methods -- 2.1 Multi-task Discriminator -- 2.2 Non-difference Suppression Loss and Consistency Loss -- 2.3 FFT-Generator -- 3 Experiments and Results -- 3.1 Experiments Settings -- 3.2 Comparison Results -- 4 Conclusion -- References -- Uncertainty-Informed Bayesian PET Image Reconstruction Using a Deep Image Prior -- 1 Introduction and Related Work -- 2 Methods -- 3 Data and Experiments -- 4 Results and Discussion -- 5 Conclusion -- References -- Author Index.
• Titolo autorizzato: Machine Learning for Medical Image Reconstruction
• ISBN: 3-031-17247-7
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 996490353503316
• Lo trovi qui: Univ. di Salerno
• Serie: Lecture notes in computer science.