Bildverarbeitung für die Medizin 2022

Name: Bildverarbeitung für die Medizin 2022 | Proceedings, German Workshop on Medical Image Computing, Heidelberg, June 26-28, 2022
Brand: Springer Vieweg
Price: 62.99 EUR
Availability: OnlineOnly

Proceedings, German Workshop on Medical Image Computing, Heidelberg, June 26-28, 2022

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

Springer Vieweg (Verlag)

Erschienen am 4. April 2022

XX, 356 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-658-36932-3 (ISBN)

62,99 €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 2022
Preisträger der BVM 2021 in Regensburg
Vorwort
Inhaltsverzeichnis
1 Unsupervised Segmentation of Wounds in Optical Coherence Tomography Images Using Invariant Information Clustering
1 Introduction
2 Methods
2.1 Data acquisition
2.2 Preprocessing
2.3 Clustering network
2.4 Loss functions
3 Results
4 Discussion
References
2 Iterative 3D CNN Based Segmentation of Vascular Trees in Liver CT
1 Introduction
1.1 Contributions
2 Materials and methods
2.1 Segmentation of sub-regions
2.2 Removal of components from other paths
2.3 Detection of next sub-regions
3 Results
4 Discussion
References
3 Robust Liver Segmentation with Deep Learning Across DCE-MRI Contrast Phases
1 Introduction
2 Materials and methods
2.1 Image and reference data
2.2 Neural network and training
2.3 Evaluation
3 Results
4 Discussion
References
4 Abstract: Light-weight Semantic Segmentation and Labelling of Vertebrae in 3D-CT Scans
References
5 Few-shot Unsupervised Domain Adaptation for Multi-modal Cardiac Image Segmentation
1 Introduction
2 Materials and methods
2.1 Dataset
2.2 Problem statement
2.3 RAIN Module
2.4 Few-shot UDA for cardiac MRI segmentation
2.5 Training
3 Results
4 Discussion
References
6 Unsupervised Anomaly Detection in the Wild
1 Introduction
2 Methods
2.1 Anomaly detection
2.2 Metrics
2.3 Datasets
2.4 Model and parameter selection
3 Experiments and results
3.1 Basic metrics
3.2 Expert evaluation
4 Discussion
5 Conclusion
References
7 Epistemic and Aleatoric Uncertainty Estimation for PED Segmentation in Home OCT Images
1 Introduction
2 Materials and methods
2.1 Segmentation of PED and uncertainty estimation
2.2 Metrics for quantification and evaluation uncertainties
3 Experiments and results
4 Discussion
References
8 Quality Monitoring of Federated Covid-19 Lesion Segmentation
1 Introduction
2 Materials and methods
2.1 Data
2.2 Proposed features
2.3 Models and training
2.4 Evaluation
3 Results
4 Discussion
References
9 Detection of Large Vessel Occlusions Using Deep Learning by Deforming Vessel Tree Segmentations
1 Introduction
2 Materials and methods
2.1 Data
2.2 Methodology
2.3 Augmentation
3 Results
4 Discussion
References
10 Abstract: nnDetection. A Self-configuring Method for Medical Object Detection
References
11 Machine Learning-based Detection of Spherical Markers in CT Volumes
1 Introduction
2 Materials and methods
2.1 3D region proposal network
2.2 Dataset and experiments
2.3 Training and testing
2.4 Evaluation
3 Results
4 Discussion
References
12 A Keypoint Detection and Description Network Based on the Vessel Structure for Multi-modal Retinal Image Registration
1 Introduction
2 Materials and methods
2.1 Network for multi-modal keypoint detection and description
2.1.1 Detector and descriptor loss functions.
2.1.2 Keypoint detection, descriptor matching, and homography estimation.
2.2 Multi-modal retinal datasets
2.3 Experimental details
3 Results
4 Discussion
References
13 Training Deep Learning Models for 2D Spine X-rays Using Synthetic Images and Annotations Created from 3D CT Volumes
1 Introduction
2 Materials and methods
2.1 Synthetic X-ray image generation
2.2 Annotation generation
2.3 Vertebra detection with Faster R-CNN
2.4 Dataset
2.5 Evaluation
3 Results
4 Discussion
References
14 Robust Intensity-based Initialization for 2D-3D Pelvis Registration (RobIn)
1 Introduction
2 Materials and methods
3 Results
4 Discussion
References
15 Learning an Airway Atlas from Lung CT Using Semantic Inter-patient Deformable Registration
1 Introduction
2 Materials and methods
2.1 Dataset and segmentation
2.2 Inter-patient registration
3 Results
4 Discussion
References
16 Abstract: Guided Filter Regularization for Improved Disentanglement of Shape and Appearance in Diffeomorphic Autoencoders
References
17 Abstract: Automatic Path Planning for Safe Guide Pin Insertion in PCL Reconstruction Surgery
References
18 Heads up A Study of Assistive Visualizations for Localisation Guidance in Virtual Reality
1 Introduction
2 Materials and methods
2.1 Study setup
3 Results
4 Discussion
References
19 Support Point Sets for Improving Contactless Interaction in Geometric Learning for Hand Pose Estimation
1 Introduction
2 Materials and methods
2.1 Support point sets
2.2 Network architecture
3 Results
4 Discussion
References
20 Automatic Switching of Organ Programs in Interventional X-ray Machines Using Deep Learning
1 Introduction
2 Materials and methods
2.1 Data properties and preparation
2.2 Network architecture and training protocol
3 Results
4 Discussion
References
21 Ermittlung der Geometrie von Amputationsstümpfen mittels Ultraschall
1 Einleitung
2 Materialien und Methoden
2.1 Phantombau
2.2 B-Mode Messungen
2.3 A-Mode Messungen
3 Ergebnisse
4 Diskussion
References
22 Monte Carlo Dose Simulation for In-Vivo X-Ray Nanoscopy
1 Introduction
2 Materials and methods
2.1 X-ray physics
2.2 Realistic mouse tibia bone phantom
2.3 Monte Carlo simulation
2.4 Calibration to the XRM system
3 Results
4 Discussion
References
23 Abstract: How to Generate Patient Benefit with Surgical Data Science Results of an International Delphi Process
References
24 Abstract: The Importance of Dataset Choice. Lessons Learned from COVID-19 X-ray Imaging Models
References
25 Analysis of Celiac Disease with Multimodal Deep Learning
1 Introduction
2 Materials and methods
2.1 Dataset
2.2 Preprocessing
2.3 Model architecture
2.3.1 Feature fusion module.
2.4 Training
3 Results
4 Discussion
References
26 Form Follows Function Smart Network Design Enables Zero-shot Network Reuse
1 Introduction
2 Methods and material
2.1 Proposed methods
2.2 Data
2.2.1 Fundus database.
2.2.2 OCTA database.
3 Results
4 Discussion
References
27 Abstract: C-arm Positioning for Spinal Standard Projections in Different Intra-operative Settings
References
28 Abstract: Verbesserung des 2D U-Nets für die 3D Mikrotomographie mit Synchrotronstrahlung mittels Multi-Axes Fusing
References
29 Efficient Patient Orientation Detection in Videofluoroscopy Swallowing Studies
1 Introduction
2 Materials and methods
3 Results
4 Discussion
References
30 Towards Weakly Supervised Segmentation of Orthopaedic X-ray Images Using Constrained-CNN Losses
1 Introduction
2 Materials and methods
2.1 Size loss
2.1.1 Loose.
2.1.2 Equal.
2.1.3 Precise.
2.2 Data
2.3 Experiments
3 Results
4 Discussion
References
31 3D Reconstruction of the Colon from Monocular Sequences Evaluation by 3D-printed Phantom Data
1 Introduction
1.1 Challenges
1.2 Related work
2 Methods and material
2.1 Methods
2.1.1 Preprocessing.
2.1.2 Depth-map approximation.
2.1.3 Point-cloud fusion.
2.2 Material
2.2.1 3D-printed colon phantom.
2.2.2 Recordings.
3 Results
4 Discussion
References
32 Diffusion MRI Specific Pretraining by Self-supervision on an Auxiliary Dataset
1 Introduction
2 Materials and methods
2.1 Data
2.2 Network architecture and training details
2.3 Diffusion-MRI specific pretraining procedure
2.4 Experiments for evaluation
2.4.1 Segmentation.
2.4.2 Fiber direction.
2.4.3 Fiber crossings.
3 Results
4 Discussion
References
33 Thrombus Detection in Non-contrast Head CT Using Graph Deep Learning
1 Introduction
2 Materials and methods
2.1 Input data
2.2 Candidate detection model
2.3 Candidate classification model
3 Results
4 Discussion
References
34 Abstract: A Database and Neural Network for Highly Accurate Classification of Single Bone Marrow Cells
References
35 Comparison of Depth Estimation Setups from Stereo Endoscopy and Optical Tracking for Point Measurements
1 Introduction
2 Materials and methods
2.1 Dataset
2.2 Optical tracking and hand-eye calibration
2.3 Image-based point detection
2.3.1 Ground truth.
2.3.2 Deep learning.
2.4 Evaluation
3 Results and discussion
References
36 Abstract: M2aia: Mass Spectrometry Imaging Applications for Interactive Analysis in MITK
References
37 Learning Features via Transformer Networks for Cardiomyocyte Profiling
1 Introduction
2 Materials and methods
2.1 Cell preparation and imaging
2.2 Image prepossessing
2.3 Data set
2.4 Network architecture
2.5 Feature extraction
2.6 Feature aggregation
2.7 Experiments
3 Results
4 Discussion
References
38 Effect of Random Histogram Equalization on Breast Calcification Analysis Using Deep Learning
1 Introduction
2 Materials and methods
2.1 Data
2.2 Experimental setup
3 Results
4 Discussion
References
39 Longitudinal Analysis of Disease Progression Using Image and Laboratory Data for Covid-19 Patients
1 Introduction
2 Materials and methods
2.1 Dataset
2.2 Image data preprocessing: segmentation and registration
2.2.1 Segmentation.
2.2.2 Registration.
2.3 Progression analysis
2.4 Correlation analysis and feature selection
3 Results
4 Discussion
References
40 Adipose and Muscular Tissue Removal for Direct Volume Rendering of the Visceral Region in Abdominal 3D CT Images
1 Introduction
2 Materials and methods
2.1 Top slice boundary detection
2.1.1 Inner SAT border segmentation.
2.1.2 Subcutaneous muscle layer segmentation.
2.1.3 Boundary candidate connection.
2.2 Top-down segmentation boundary adjustment
3 Results
4 Discussion and conclusion
References
41 Elektromagnetisches Instrumententracking für die Schlaganfallbehandlung mittels Thrombektomie
1 Einleitung
2 Material und Methoden
3 Ergebnisse
4 Diskussion
References
42 Abstract: Synthesis of Annotated Pathological Retinal OCT Data with Pathology-Induced Deformations
References
43 Comparison of Evaluation Metrics for Landmark Detection in CMR Images
1 Introduction
2 Materials and methods
2.1 Data pre-processing and ground truth
2.2 Model pipeline
2.3 Evaluation
2.3.1 Detection-based metrics.
2.3.2 Localisation-based metrics.
3 Results
4 Discussion
References
44 Deep Learning Models for 3D MRI Brain Classification. A Multi-sequence Comparison
1 Introduction
2 Materials and methods
2.1 Dataset
2.2 Methodology
3 Results
4 Discussion
References
45 Towards Super-resolution CEST MRI for Visualization of Small Structures
1 Introduction
2 Theory and methods
3 Results
4 Discussion
References
46 Multi-organ Segmentation with Partially Annotated Datasets
1 Introduction
2 Material and methods
2.1 Dataset
2.2 Modified training pipeline
2.3 Experiments setting
3 Result
4 Discussion
4.1 Hints for using partially annotated datasets
References
47 Abstract: C-MORE: A High-content Single-cell Morphology Recognition Methodology for Liquid Biopsies Toward Personalized Cardiovascular Medicine
References
48 First Steps on Gamification of Lung Fluid Cells Annotations in the Flower Domain
1 Introduction
2 Materials and methods
2.1 Lung fluid cells data set
2.2 Flowers data set
2.3 Image transformation
2.4 Experimental design
3 Results
4 Discussion
References
49 Computation of Traveled Distance of Pigs in an Open Field with Fully Convolutional Neural Networks
1 Introduction and previous work
2 Materials and methods
2.1 Image data and annotations
2.2 Fully convolutional keypoint detection network
2.3 Keypoint processing and tracking
3 Experiments and results
4 Discussion
5 Conclusion and outlook
References
50 Spatiotemporal Attention for Realtime Segmentation of Corrupted Sequential Ultrasound Data Improving Usability of AI-based Image Guidance
1 Introduction
2 Materials and methods
2.1 Data
2.2 Method
3 Results
4 Discussion
References
51 Virtual DSA Visualization of Simulated Blood Flow Data in Cerebral Aneurysms
1 Introduction
2 Materials and methods
2.1 Data acquisition
2.2 General concept of virtual DSA
2.3 Implementation
2.3.1 Vessel surface rendering.
2.3.2 Path line rendering.
3 Results
4 Discussion
4.1 Limitations
4.2 Future work
References
52 Reconstruction of 1D Images with a Neural Network for Magnetic Particle Imaging
1 Introduction
2 Materials and methods
2.1 Dataset
2.2 Neural network
2.3 Conventional reconstruction
3 Results
3.1 Neural network training
3.2 Reconstruction results
4 Discussion
References
53 Abstract: 3D Stent Graft Guidance Based on Tracking Systems
References
54 Superpixel Pre-segmentation of HER2 Slides for Efficient Annotation
1 Introduction
2 Materials and methods
2.1 Superpixel methods
2.1.1 Adjusted SLIC.
2.1.2 Pre-trained ResNet-50.
2.1.3 HER2 autoencoder.
2.2 Hierarchical clustering
2.3 Dataset
2.4 Evaluation metrics
3 Results
4 Discussion
References
55 Abstract: Task Fingerprinting for Meta Learning in Biomedical Image Analysis
References
56 Initial Investigations Towards Non-invasive Monitoring of Chronic Wound Healing Using Deep Learning and Ultrasound Imaging
1 Introduction
2 Material and methods
2.1 Dataset
2.2 Deep learning networks and training strategy
2.3 Evaluation metrics
2.4 Wound intensity evaluation
3 Results
4 Discussion
References
57 Classification of Vascular Malformations Based on T2 STIR Magnetic Resonance Imaging
1 Introduction
2 Materials and methods
2.1 Data
2.2 Network architectures
2.3 Training and experimental setup
3 Results
4 Discussion
References
58 DICOM Whole Slide Imaging for Computational Pathology Research in Kaapana and the Joint Imaging Platform
1 Introduction
2 Materials and methods
2.1 Data standardization
2.2 Viewing and annotating pathological imaging data
2.3 Computational pathology
3 Results
3.1 Data conversion
3.2 Remote viewing and telepathology
3.3 Computational pathology
4 Discussion
References
59 Efficient DICOM Image Tagging and Cohort Curation Within Kaapana
1 Introduction
2 Materials and methods
3 Results
4 Discussion
References
60 Automatic Classification of Neuromuscular Diseases in Children Using Photoacoustic Imaging
1 Introduction
2 Materials and methods
2.1 Datasets
2.2 Pre-processing
2.3 Experimental setup
3 Results
4 Discussion
References
61 Realistic Evaluation of FixMatch on Imbalanced Medical Image Classification Tasks
1 Introduction
2 Materials and methods
2.1 Datasets
2.1.1 Chest X-ray.
2.1.2 Retina images.
2.2 Semi-supervised learning with FixMatch
2.3 Methods for imbalanced classification
2.4 Model selection and evaluation
3 Results
3.1 Out-of-the-box utility of FixMatch
3.2 Effect of label balancing methods
4 Discussion
References
62 Initialisation of Deep Brain Stimulation Parameters with Multi-objective Optimisation Using Imaging Data
1 Introduction
2 Method
2.1 Target and electrode reconstruction
2.2 Initialisation of DBS parameters
2.2.1 Ranking the contacts.
2.2.2 Optimisation problem.
2.3 Performance evaluation
2.4 Amplitude evaluation
3 Results
3.1 Case study 1
3.2 Case study 2
3.3 Evaluation of ranking and time efficiency
4 Discussion
References
63 Pathologiespezifische Behandlung von Labelunsicherheit bei der Klassifikation von Thorax-Röntgenbildern
1 Einleitung
2 Material und Methoden
2.1 Material
2.2 Bisherige Ansätze
2.3 Pathologiespezifische Behandlung
2.4 Experimentaufbau
3 Ergebnisse
4 Diskussion
References
64 3D CNN-based Identification of Hyperdensities in Cranial Non-contrast CT After Thrombectomy
1 Introduction
2 Materials and methods
2.1 Data
2.2 Preprocessing
2.3 Proposed network
3 Results
4 Discussion
References
65 Predicting Aneurysm Rupture with Deep Learning on 3D Models
1 Introduction
2 Materials and methods
3 Results
4 Discussion
References
66 GAN-based Augmentation of Mammograms to Improve Breast Lesion Detection
1 Introduction
2 Materials and methods
2.1 UKE dataset
2.2 INbreast dataset
2.3 Cycle-consistent GAN
2.3.1 Loss functions.
2.4 Breast lesion detection
3 Results
4 Discussion
References
67 Multiscale Softmax Cross Entropy for Fovea Localization on Color Fundus Photography
1 Introduction
2 Materials and methods
2.1 Dataset
2.2 Network architecture
2.3 Loss
2.4 Hyperparameters
3 Results
4 Discussion
5 Conclusion
References
68 Tibia Cortical Bone Segmentation in Micro-CT and X-ray Microscopy Data Using a Single Neural Network
1 Introduction
2 Materials and methods
2.1 Sample preparation
2.2 µCT and XRM measurements
2.3 Neural network training and prediction
3 Results
4 Discussion
References
69 Reinforcement learning-basierte Patchpriorisierung zur beschleunigten Segmentierung von hochauflösenden Endoskopievideodaten
1 Einleitung
2 Material und Methoden
2.1 Synthetische Koloskopiebilder
2.2 Realdaten
2.3 RL-Environment
2.4 Training
2.5 Evaluierung
3 Ergebnisse
4 Diskussion
References
70 Offer Proprietary Algorithms Still Protection of Intellectual Property in the Age of Machine Learning? A Case Study Using Dual Energy CT Data
1 Introduction
2 Methods
3 Experiments and results
3.1 Single energy estimation
3.2 Iodine map prediction
4 Discussion
5 Conclusion
References
71 Abstract: Face Detection From In-car Video for Continuous Health Monitoring
References
Autorenverzeichnis

Systemvoraussetzungen

Als PDF speichern Als Link merken