Bildverarbeitung für die Medizin 2021

Name: Bildverarbeitung für die Medizin 2021 | Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7-9, 2021
Brand: Springer Vieweg
Price: 69.99 EUR
Availability: OnlineOnly

Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7-9, 2021

Christoph Palm Thomas M. Deserno Heinz Handels Andreas Maier Klaus Maier-Hein Thomas Tolxdorff(Herausgeber*in)

Springer Vieweg (Verlag)

Erschienen am 26. Februar 2021

XXV, 361 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-658-33198-6 (ISBN)

69,99 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Bildverarbeitung für die Medizin 2021
Sponsoren und Unterstützer des Workshops BVM 2021
Preisträger der BVM 2020 in Berlin
Vorwort
Inhaltsverzeichnis
1 Learning from Imperfect Data. Weak Labels, Shifting Domains, and Small Datasets in Medical Imaging
2 Interactive Design of Convolutional Neural Networks for Medical Image Analysis
3 Artificial Intelligence in Endoscopy
4 Learning-based Patch-wise Metal Segmentation with Consistency Check
1 Introduction
2 Materials and methods
2.1 Network architectures
2.2 Data
2.3 Experiment protocol
2.4 Consistency check
3 Results
4 Discussion
Acknowledgement.
Disclaimer.
References
5 Localization of the Locus Coeruleus in MRI via Coordinate Regression
1 Introduction
2 Materials and methods
2.1 Data
2.2 Network architecture
2.3 Evaluation scheme
3 Results
4 Discussion
Acknowledgement.
References
6 Semantically Guided 3D Abdominal Image Registration with Deep Pyramid Feature Learning
1 Introduction
2 Material and method
2.1 Semantic feature extraction
2.2 Registration networks
2.3 Image data
3 Results
4 Discussion and conclusion
References
7 Heatmap-based 2D Landmark Detection with a Varying Number of Landmarks
1 Introduction
2 Materials and methods
2.1 Network architecture
2.2 Dataset
2.3 Evaluation
3 Results
4 Discussion
Acknowledgement.
References
8 Ultrasound-based Navigation of Scaphoid Fracture Surgery
1 Introduction
2 Materials and methods
2.1 Architectures
2.2 Datasets
2.3 Training
2.4 Testing
3 Results
4 Discussion
Acknowledgement.
References
9 Abstract: 3D Guidance Including Shape Sensing of a Stentgraft System
References
10 Abstract: Move Over There One-click Deformation Correction for Image Fusion during Endovascular Aortic Repair
References
11 Interactive Visualization of Cerebral Blood Flow for Arteriovenous Malformation Embolisation
1 Introduction
2 Materials and methods
2.1 Medical image dataset
2.2 Embolization and blood flow simulation
2.2.1 Simulation of embolization.
2.2.2 Blood flow simulation.
2.2.3 Usage of Unity's VFX graph.
3 Results
3.1 Interactive blood flow application
3.2 Evaluation
4 Discussion and outlook
References
12 Rotation Invariance for Unsupervised Cell Representation Learning. Analysis of The Impact of Enforcing Rotation Invariance or Equivariance on Representation for Cell Classification
1 Introduction
2 Materials and methods
2.1 Image data
2.2 Rotation loss
2.3 Harmonic convolutions
2.4 Experimental setup
3 Results
4 Discussion
Acknowledgement.
References
13 Abstract: Deep Learning-based Quantification of Pulmonary Hemosiderophages in Cytology Slides
References
14 Learning the Inverse Weighted Radon Transform
1 Introduction
2 Methods
2.1 Inverse weighted radon transform
2.2 Data
2.3 Experiments
3 Results
4 Discussion and outlook
References
15 Table Motion Detection in Interventional Coronary Angiography
1 Introduction
2 Materials and methods
2.1 Datasets and annotation
2.2 Preprocessing
2.3 Network architectures
3 Results
4 Discussion
References
16 Semi-permeable Filters for Interior Region of Interest Dose Reduction in X-ray Microscopy
1 Introduction
2 Materials and methods
2.1 Filter design
2.2 Image reconstruction
2.3 Experimental setup
3 Results
4 Discussion
References
17 An Optical Colon Contour Tracking System for Robot-aided Colonoscopy. Localization of a Balloon in an Image using the Hough-transform
1 Introduction
2 Material and methods
2.1 Mechanical setup
2.2 Algorithm
2.3 Experimental setup
3 Results
4 Discussion
Acknowledgement.
References
18 Externe Ventrikeldrainage mittels Augmented Reality und Peer-to-Peer-Navigation
1 Einleitung
2 Material und Methoden
2.1 Algorithmus
2.2 Kalibrierung der statischen Transformationen
3 Ergebnisse
4 Diskussion
Literatur
19 Abstract: Contour-based Bone Axis Detection for X-ray-guided Surgery on the Knee
References
20 Novel Evaluation Metrics for Vascular Structure Segmentation
1 Introduction
2 Materials and methods
2.1 Existing algorithm
2.2 Modification of the algorithm
2.2.1 Piece-wise curvature of retinal vessel trees.
2.2.2 Modifications based on singular value decomposition.
2.2.3 Modifications based on directed Hausdorff distance.
2.3 Database
3 Results
4 Discussion
References
21 A Machine Learning Approach Towards Fatty Liver Disease Detection in Liver Ultrasound Images
1 Introduction
2 Material and methods
2.1 Training and output pipelines
2.2 Texture feature extraction
2.3 Model evaluation
3 Results
4 Discussions
References
22 Automated Deep Learning-based Segmentation of Brain, SEEG and DBS Electrodes on CT Images
1 Introduction
2 Materials and methods
2.1 Dataset description
2.2 Network architecture
2.3 Performance assessment
3 Results
4 Discussion
5 Acknowledgement
References
23 Segmentation of the Fascia Lata in Magnetic Resonance Images of the Thigh. Comparison of an Unsupervised Technique with a U-Net in 2D and Patch-wise 3D
1 Introduction
2 Methods
2.1 Data acqusition
2.2 Deep learning architecture and training
2.3 Evaluation of the results
3 Results
3.1 2D U-Net model
3.2 3D U-Net model
3.3 Post-processing time
4 Discussion and conclusion
References
24 Abstract: Automatic CAD-RADS Scoring using Deep Learning
References
25 Towards Deep Learning-based Wall Shear Stress Prediction for Intracranial Aneurysms
1 Introduction
2 Materials and methods
2.1 Artificial aneurysm configuration
2.2 Hemodynamic simulations
2.3 Deep learning segmentation
3 Results
4 Discussion
References
26 Evaluating Design Choices for Deep Learning Registration Networks Architecture Matters
1 Introduction
2 Materials and methods
3 Results
4 Discussion
References
27 Learning the Update Operator for 2D/3D Image Registration
1 Introduction
2 Methods
2.1 PPC-based 2D/3D registration framework
2.2 Learnable update operator for PPC-based 2D/3D registration framework
2.3 Experimental setup
3 Results
4 Discussion and conclusion
Disclaimer.
References
28 Abstract: Generation of Annotated Brain Tumor MRIs with Tumor-induced Tissue Deformations for Training and Assessment of Neural Networks
References
29 Abstract: Multi-camera, Multi-person, and Real-time Fall Detection using Long Short Term Memory
References
30 Abstract: Probabilistic Dense Displacement Networks for Medical Image Registration Contributions to the Learn2Reg Challenge
References
31 Abstract: Joint Imaging Platform for Federated Clinical Data Analytics
References
32 Towards Mouse Bone X-ray Microscopy Scan Simulation
1 Introduction
2 Materials and methods
2.1 Database
2.2 Simulation for data augmentation
2.2.1 Bone shape simulation.
2.2.2 Bone crack simulation.
2.2.3 Lacunae simulation.
2.2.4 Blood vessel simulation.
3 Results
4 Discussion
References
33 Dataset on Bi- and Multi-nucleated Tumor Cells in Canine Cutaneous Mast Cell Tumors
1 Introduction
2 Materials and methods
2.1 Labeling of bi- and multi-nucleated tumor cells
2.2 Dataset validation
2.2.1 Performance validation on the ground truth dataset.
2.2.2 Performance validation against pathologists.
2.3 Co-localisation of bi-, multi-nucleated and mitotic tumor cells
3 Results
4 Discussion
Acknowledgement.
References
34 Abstract: Data Augmentation for Information Transfer. Why Controlling for Confounding Effects in Radiomic Studies is Important and How to do it
References
35 Reduction of Stain Variability in Bone Marrow Microscopy Images. Influence of Augmentation and Normalization Methods on Detection and Classification of Hematopoietic Cells
1 Introduction
2 Materials and methods
2.1 Image data
2.2 Normalization methods
2.2.1 Macenko.
2.2.2 Grayscale.
2.2.3 LAB.
2.3 Augmentation methods
2.3.1 Macenko.
2.3.2 HSV.
2.3.3 PCA.
2.4 Experimental setup
3 Results
4 Discussion
Acknowledgement.
References
36 Cell Detection for Asthma on Partially Annotated Whole Slide Images. Learning to be EXACT
1 Introduction
2 Material and methods
2.1 Label generation and training pipeline
2.2 Live patch selection and sampling strategy
2.3 Object detection methods
3 Results
4 Discussion and outlook
Acknowledgement.
References
37 Combining Reconstruction and Edge Detection in Computed Tomography
1 Introduction
2 Materials and methods
2.1 Method 1: An FBP-type approach for calculating the gradient
2.2 Method 2: gradient calculation using sparse regularization
3 Results
4 Discussion
Acknowledgement.
References
38 2D Respiration Navigation Framework for 3D Continuous Cardiac Magnetic Resonance Imaging
1 Introduction
2 Method
2.1 Sampling pattern
2.2 Navigation motion extraction pipeline
3 Experiments and results
3.1 Experimental setup
3.2 Results
4 Discussion and conclusion
References
39 Residual Neural Network for Filter Kernel Design in Filtered Back-projection for CT Image Reconstruction
1 Introduction
2 Materials and methods
2.1 resFBP
2.2 Experimental setup
3 Results
4 Discussion
References
40 Abstract: Automatic Plane Adjustment in Surgical Cone Beam CT-volumes
References
41 Abstract: Towards Automatic C-arm Positioning for Standard Projections in Orthopedic Surgery
References
42 Open-Science Gefäßphantom für neurovaskuläre Interventionen
1 Einleitung
2 Material und Methoden
2.1 Herstellungsprozess
2.2 Evaluierung des Phantoms
3 Ergebnisse
4 Diskussion
Danksagung.
Literatur
43 Abstract: Semi-supervised Segmentation Based on Error-correcting Supervision
References
44 Abstract: Efficient Biomedical Image Segmentation on EdgeTPUs
References
45 Human Axon Radii Estimation at MRI Scale. Deep Learning Combined with Large-scale Light Microscopy
1 Introduction
2 Materials and methods
2.1 Ensemble mean axon radii
2.2 Normalized root-mean-square deviation and mean bias
2.3 Dataset
2.4 Axon radius estimation pipeline
2.5 Experiment 1: Segmentation performance
2.6 Experiment 2: Accuracy of mean axon radii estimation
3 Results
3.1 Experiment 1: Segmentation performance
3.2 Experiment 2: Accuracy of mean axon radii estimation
4 Discussion
References
46 Age Estimation on Panoramic Dental X-ray Images using Deep Learning
1 Introduction
2 Material and methods
2.1 Data
2.2 Network architecture
2.2.1 Training.
2.2.2 Metrics.
3 Results
4 Discussion
References
47 Multi-modal Unsupervised Domain Adaptation for Deformable Registration Based on Maximum Classifier Discrepancy
1 Introduction
1.1 Contribution
1.2 Related work
2 Materials and methods
3 Results and discussion
Acknowledgement.
References
48 Abstract: A Completely Annotated Whole Slide Image Dataset of Canine Breast Cancer to Aid Human Breast Cancer Research
References
49 Acquisition Parameter-conditioned Magnetic Resonance Image-to-image Translation
1 Introduction
2 Materials and methods
3 Results
4 Discussion
Acknowledgement.
References
50 Fine-tuning Generative Adversarial Networks using Metaheuristics. A Case Study on Barrett's Esophagus Identification
1 Introduction
2 Materials and methods
3 Results
3.1 Datasets
3.2 Experimental setup
3.3 Optimization results
3.4 Classification results
4 Discussion
Acknowledgement.
References
51 Neural Networks with Fixed Binary Random Projections Improve Accuracy in Classifying Noisy Data
1 Introduction
2 Material and methods
2.1 Model
2.2 Dataset
3 Results
4 Discussion
References
52 M3d-CAM. A PyTorch Library to Generate 3D Attention Maps for Medical Deep Learning
1 Introduction
2 Materials and methods
2.1 Injection
2.2 Layer retrieval
2.3 Evaluation
2.4 Backends
2.4.1 Grad-CAM.
2.4.2 Guided backpropagation.
2.4.3 Guided Grad-CAM.
2.4.4 Grad-CAM++.
3 Results
4 Discussion
References
53 Coronary Plaque Analysis for CT Angiography Clinical Research
1 Introduction
2 Material and methods
2.1 General workflow
2.2 Plaque analysis
3 Results
4 Discussion
References
54 Robust Slide Cartography in Colon Cancer Histology Evaluation on a Multi-scanner Database
1 Introduction
2 Materials and methods
2.1 Materials
2.2 Methods
3 Results
4 Discussion
Acknowledgement.
References
55 Digital Staining of Mitochondria in Label-free Live-cell Microscopy
1 Introduction
2 Materials and methods
2.1 Data acquisition
2.2 cGAN architecture
2.3 Training details
3 Proposed loss function
4 Results
5 Discussion and conclusion
References
56 Influence of Inter-Annotator Variability on Automatic Mitotic Figure Assessment
1 Introduction
2 Material and methods
2.1 Creation of databases
2.2 Deep learning-based mitotic figure detection
2.3 Model evaluation
3 Results
4 Discussion
Acknowledgement.
References
57 Automatic Vessel Segmentation and Aneurysm Detection Pipeline for Numerical Fluid Analysis
1 Introduction
2 Methods
2.1 Dataset
2.2 Marker-based watershed vessel tree segmentation
2.2.1 Skeletonization.
2.2.2 Marker-based watershed segmentation.
2.2.3 Post-processing.
2.3 Aneurysm detection and segmentation
2.3.1 Surface pre-processing.
2.3.2 Aneurysm candidate generation.
2.3.3 Growing of aneurysm candidates.
2.3.4 Candidate classification.
3 Results
3.1 Segmentation
3.2 Aneurysm detection
4 Discussion
References
58 Abstract: Widening the Focus. Biomedical Image Segmentation Challenges and the Underestimated Role of Patch Sampling and Inference Strategies
References
59 End-to-end Learning of Body Weight Prediction from Point Clouds with Basis Point Sets
1 Introduction
1.1 Related work
1.2 Contribution
2 Materials and methods
2.1 Pre-processing
2.2 Basis point set and neural network
2.3 Adapted sampling of basis points
3 Results
3.0.1 Dataset.
3.0.2 Implementation Details.
3.0.3 Baselines.
4 Discussion
Acknowledgement.
References
60 Abstract: Deep Learning Algorithms Out-perform Veterinary Pathologists in Detecting the Mitotically Most Active Tumor Region
References
61 Abstract: Maximum A-posteriori Signal Recovery for OCT Angiography Image Generation
References
62 Abstract: Simultaneous Estimation of X-ray Back-scatter and Forward-scatter using Multi-task Learning
References
63 Deep Learning-based Spine Centerline Extraction in Fetal Ultrasound
1 Introduction
2 Materials and methods
2.1 Data
2.2 Preprocessing
2.3 Spine probability map generation
2.4 Centerline tracing
2.5 Evaluation metrics
2.6 Experiment set-up
3 Results
4 Discussion
References
64 Abstract: Studying Robustness of Semantic Segmentation under Domain Shift in Cardiac MRI
References
65 On Efficient Extraction of Pelvis Region from CT Data
1 Introduction
2 Materials and methods
2.1 Methods
2.2 Evaluation measures
3 Results and discussion
4 Conclusion
References
66 CT Normalization by Paired Image-to-image Translation for Lung Emphysema Quantification
1 Introduction
2 Materials and methods
2.1 Materials
2.2 Image-to-image translation with UNet
2.3 Experiments
3 Results
3.1 Quantitative results
3.2 Visual assessment by experts
4 Discussion
References
67 Ultrasound Breast Lesion Detection using Extracted Attention Maps from a Weakly Supervised Convolutional Neural Network
1 Introduction
2 Materials and methods
3 Results
4 Discussion
4.1 Conclusion and future work
References
68 Abstract: Extracting and Leveraging Nodule Features with Lung Inpainting for Local Feature Augmentation
References
69 Abstract: Automatic Dementia Screening and Scoring by Applying Deep Learning on Clock-drawing Tests
References
70 Deep Learning Compatible Differentiable X-ray Projections for Inverse Rendering
1 Introduction
2 Methods
2.1 Differentiable rasterizer
2.2 X-ray rendering
2.3 Application: inverse rendering
3 Evaluation and results
4 Discussion and conclusion
Disclaimer.
References
71 Abstract: Are Fast Labeling Methods Reliable? A Case Study of Computer-aided Expert Annotations on Microscopy Slides
References
72 Abstract: Time Matters. Handling Spatio-temporal Perfusion Information for Automated Treatment in Cerebral Ischemia Scoring
References
73 A Geometric and Textural Model of the Colon as Ground Truth for Deep Learning-based 3D-reconstruction
1 Introduction
1.1 Panorama endoscopy
1.2 Objective
2 Materials and methods
2.1 Model texture
2.2 Colonoscope tip, light and camera
3 Results
4 Discussion
Acknowledgement.
References
74 Deep Learning-basierte Oberflächenrekonstruktion aus Binärmasken
1 Einleitung
2 Material und Methoden
2.1 Trainingsdaten
2.2 Netzwerk Architektur
2.3 Training
3 Ergebnisse
4 Diskussion
Literatur
75 A Novel Trilateral Filter for Digital Subtraction Angiography
1 Introduction
2 Materials and methods
2.1 Bilateral filter
2.2 Frangi vessel enhancement filter
2.3 Trilateral filter
3 Results
4 Discussion
References
76 Abstract: JBFnet. Low Dose CT-denoising by Trainable Joint Bilateral Filtering
References
77 Interactive Visualization of 3D CNN Relevance Maps to Aid Model Comprehensibility. Application to the Detection of Alzheimer's Disease in MRI Images
1 Introduction
2 Materials and methods
3 Results
4 Discussion
References
78 Abstract: VirtualDSA++. Automated Segmentation, Vessel Labeling, Occlusion Detection, and Graph Search on CT Angiography Data
References
79 Interval Neural Networks as Instability Detectors for Image Reconstructions
1 Introduction
1.1 Overview and contributions
2 Materials and methods
2.1 Uncertainty quantification methods
2.1.1 Interval neural network.
2.1.2 Monte Carlo dropout.
2.1.3 Mean and variance estimation.
2.2 Inverse problem, neural network and data
3 Results
3.1 Adversarial artifact detection (AdvDetect)
3.2 Atypical artifact detection (ArtDetect)
4 Discussion
Acknowledgement.
References
80 Invertible Neural Networks for Uncertainty Quantification in Photoacoustic Imaging
1 Introduction
2 Materials and methods
2.1 Virtual photoacoustic imaging environment
2.2 Approach to uncertainty quantification
2.3 Experiments
2.3.1 S1: Single vessel, single illumination unit (IU).
2.3.2 S2: Multiple vessels, single IU.
2.3.3 S2b: Multiple vessels, shifted single IU.
2.3.4 S3: Multiple vessels, multiple IUs.
3 Results
4 Discussion
Acknowledgement.
References
81 Abstract: Inertial Measurements for Motion Compensation in Weight-bearing Cone-beam CT of the Knee
References
82 Abstract: Reduktion der Kalibrierungszeit für die Magnetpartikelbildgebung mittels Deep Learning
Literatur
83 Autoencoder-based Quality Assessment for Synthetic Diffusion-MRI Data
1 Introduction
2 Materials and methods
2.1 Data
2.2 Synthetic data creation
2.2.1 Syn.
2.2.2 Sampled.
2.2.3 SampleAndMean.
2.2.4 RandomWM.
2.3 Denoising autoencoder
3 Results
4 Discussion
Acknowledgement.
References
84 Analysis of Generative Shape Modeling Approaches Latent Space Properties and Interpretability
1 Introduction
2 Materials and methods
2.1 Material
2.2 Statistical shape models and locality-based multi-resolution SSMs
2.3 Autoencoders and variational autoencoders
2.4 Generative adversarial networks
2.5 Deformable autoencoders
3 Experiments and results
4 Discussion and conclusion
References
85 Latent Shape Constraint for Anatomical Landmark Detection on Spine Radiographs
1 Introduction
2 Materials and methods
2.1 Geometric constraint via latent shape encoding
2.2 Architecture design variants
2.3 Data and experiment protocol
3 Results
4 Discussion
Acknowledgement.
Disclaimer.
References
Autorenverzeichnis

Systemvoraussetzungen

Als PDF speichern Als Link merken