Simulation and Synthesis in Medical Imaging 5th International Workshop, SASHIMI 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4, 2020, Proceedings
This book constitutes the refereed proceedings of the 5th International Workshop on Simulation and Synthesis in Medical Imaging, SASHIMI 2020, held in conjunction with MICCAI 2020, in Lima, Peru, in October 2020.The 19 full papers presented were carefully reviewed and selected from 27 submissions. T...
Saved in:
| Main Authors | , , , |
|---|---|
| Format | eBook |
| Language | English |
| Published |
Netherlands
Springer Nature
2020
Springer International Publishing AG Springer International Publishing |
| Edition | 1 |
| Series | Lecture Notes in Computer Science Ser |
| Subjects | |
| Online Access | Get full text |
| ISBN | 9783030595203 303059520X 3030595196 9783030595197 |
Cover
Table of Contents:
- 2.3 Loss Functions -- 3 Experiments -- 3.1 Dataset -- 3.2 Experimental Setup -- 4 Results -- 4.1 Image Enhancement -- 4.2 Multi-structure Segmentation -- 5 Conclusions -- References -- Improving Endoscopic Decision Support Systems by Translating Between Imaging Modalities -- 1 Motivation -- 2 Methods -- 2.1 Image Translation Network -- 2.2 Classification Models -- 2.3 Experimental Details and Data Sets -- 3 Results -- 4 Discussion -- 5 Conclusion -- References -- An Unsupervised Adversarial Learning Approach to Fundus Fluorescein Angiography Image Synthesis for Leakage Detection -- Abstract -- 1 Introduction -- 2 Method -- 2.1 Datasets -- 2.2 Normal-Looking FA Image Synthesis and Leakage Detecting -- 3 Experimental Results -- 3.1 Evaluation Metrics for the Detecting Results -- 3.2 Results on Open-Source Datasets -- 3.3 Results on HRA Datasets -- 4 Discussion and Conclusion -- Appendix: Failure Detection Examples of the Proposed Method -- References -- Towards Automatic Embryo Staging in 3D+t Microscopy Images Using Convolutional Neural Networks and PointNets -- 1 Introduction -- 2 Automatic Embryo Staging as a Regression Problem -- 2.1 CNN-Based Embryo Staging on Downsampled Maximum Intensity Projections -- 2.2 Regression PointNet for Automatic Embryo Staging -- 2.3 Synthetic Embryo Data Set to Identify the Possible Accuracy -- 3 Experiments -- 3.1 Data Acquisition and Training Data Generation -- 3.2 Implementation and Training Details -- 4 Results and Discussion -- References -- Train Small, Generate Big: Synthesis of Colorectal Cancer Histology Images -- 1 Introduction -- 2 Materials and Methods -- 2.1 Dataset -- 2.2 The Proposed Framework -- 3 Results and Discussion -- 3.1 Visual Assessment -- 3.2 Quantitative Assessment -- 3.3 Assessment Through Gland Segmentation -- 4 Conclusions and Future Work -- References
- Intro -- Preface -- Organization -- Contents -- Contrast Adaptive Tissue Classification by Alternating Segmentation and Synthesis -- 1 Introduction -- 2 Methods -- 2.1 Data -- 2.2 Segmentation -- 2.3 Partial Volume Estimation -- 2.4 Synthesis -- 3 Results -- 4 Discussion -- References -- 3D Brain MRI GAN-Based Synthesis Conditioned on Partial Volume Maps -- 1 Introduction -- 2 Methods -- 3 Experiments -- 4 Conclusion -- References -- Synthesizing Realistic Brain MR Images with Noise Control -- 1 Introduction -- 2 Method -- 2.1 Incorporating Randomness in Synthesis -- 2.2 Network Structure -- 3 Experiments -- 3.1 Ablation Study -- 3.2 Observer Study -- 4 Discussion and Conclusion -- References -- Simulated Diffusion Weighted Images Based on Model-Predicted Tumor Growth -- Abstract -- 1 Introduction -- 2 Diffusion-Weighted MRI -- 3 Methods -- 3.1 Creating Mock Tumors Through Mathematical Modeling -- 3.2 Simulating DWIs Based on MRI Physics -- 3.3 Creating ADC Maps from Simulated DWIs -- 4 Results -- 5 Discussion -- 6 Conclusion -- Acknowledgements -- References -- Blind MRI Brain Lesion Inpainting Using Deep Learning -- Abstract -- 1 Introduction -- 2 Materials and Methods -- 2.1 Datasets -- 2.2 Pipeline Description -- 3 Results -- 4 Conclusion -- Acknowledgement -- References -- High-Quality Interpolation of Breast DCE-MRI Using Learned Transformations -- 1 Introduction -- 2 Materials and Methods -- 2.1 Dataset -- 2.2 High-Quality Interpolation of DCE-MRI -- 3 Experiment -- 4 Conclusion -- References -- A Method for Tumor Treating Fields Fast Estimation -- Abstract -- 1 Introduction -- 2 Methods -- 2.1 Key Parameters that Effect TTFields -- 2.2 Random Forests Regression for Estimation of TTFields -- 2.3 Experimental Setup -- 3 Results -- 4 Discussion -- References
- Image Synthesis as a Pretext for Unsupervised Histopathological Diagnosis -- 1 Introduction -- 2 Methodology -- 3 Experiments and Results -- 4 Conclusion -- References -- Auditory Nerve Fiber Health Estimation Using Patient Specific Cochlear Implant Stimulation Models -- Abstract -- 1 Introduction -- 2 Related Works -- 2.1 Biological Nerve Model -- 2.2 Electro-Anatomical Model and Auditory Nerve Fiber Segmentation -- 3 Methods -- 3.1 Dataset -- 3.2 Nerve Model -- 3.3 Optimization Process -- 4 Results -- 5 Conclusion -- Acknowledgements -- References -- Author Index
- Heterogeneous Virtual Population of Simulated CMR Images for Improving the Generalization of Cardiac Segmentation Algorithms -- 1 Introduction -- 2 Methodology -- 2.1 CMR Image Simulation Approach -- 2.2 Generation of a Diverse Virtual Population -- 2.3 Data -- 2.4 Segmentation Approach -- 2.5 Experiments and Results -- 3 Discussion and Conclusion -- References -- DyeFreeNet: Deep Virtual Contrast CT Synthesis -- 1 Introduction -- 2 DyeFreeNet -- 2.1 Self-supervised Learning Pretrained Model -- 2.2 Virtual Contrast CT Predictor -- 3 Experiments -- 4 Conclusion -- References -- A Gaussian Process Model Based Generative Framework for Data Augmentation of Multi-modal 3D Image Volumes -- 1 Introduction -- 2 Method -- 2.1 Cross Modality Space Mapping -- 2.2 Controlled Distribution Within an Image Modality -- 2.3 Data Augmentation Process -- 3 Experiments and Results -- 3.1 Data-Set -- 3.2 Impact of Image Resolution on Sampled Deformation Field -- 3.3 Testing the Ability of the Process to Recover the Reference Image Volume -- 3.4 Experiment on the Consistency of the Coupling Among Generated Samples -- 4 Conclusion -- References -- Frequency-Selective Learning for CT to MR Synthesis -- 1 Introduction -- 2 Methods -- 2.1 Frequency-Selective Learning -- 2.2 Proposed Network Architecture -- 2.3 Implementation Details -- 3 Experiments and Results -- 4 Discussion and Conclusion -- References -- Uncertainty-Aware Multi-resolution Whole-Body MR to CT Synthesis -- 1 Introduction -- 2 Methods -- 2.1 Modelling Heteroscedastic Uncertainty -- 2.2 Modelling Epistemic Uncertainty -- 2.3 Implementation Details -- 3 Experiments and Results -- 3.1 Data -- 3.2 Experiments -- 3.3 Results -- 4 Discussion and Conclusions -- References -- UltraGAN: Ultrasound Enhancement Through Adversarial Generation -- 1 Introduction -- 2 Methodology -- 2.1 Problem Formulation -- 2.2 Model